Dr. rer. nat. Fabian Isensee

Head of Engineering and Support Unit at DKFZ

During his PhD at the Division of Medical Image Computing of the German Cancer Research Center, Fabian Isensee has researched deep learning techniques for semantic segmentation of (three-dimensional) datasets in the biological and medical domain. He has been particularly active in the development of methods for automated segmentation pipeline design. His most prominent effort in that regard, nnU-Net, has become the de-facto standard for segmentation in the medical domain and was recently accepted for publication in Nature Methods. Throughout his PhD, Fabian Isensee has consistently enabled the translation of state-of-the-art algorithms into real-world applications. He is furthermore adamant about making his research publicly available. The methods he developed have won multiple international segmentation competitions.

Since 2020, Fabian Isensee is heading the HI Support Unit ‘Applied Computer Vision Lab’ at the DKFZ with the goal of translating state-of-the-art AI methods to the many diverse research applications found across the Helmholtz association. The support unit is working in close collaboration with Helmholtz researchers, provides consulting, develops domain agnostic state-of-the art software for AI-based image analysis and provides solutions for algorithm and competition evaluation.

Publications

4725570 Isensee 1 https://helmholtz-imaging.de/apa-bold-title.csl 50 date desc 749 https://helmholtz-imaging.de/wp-content/plugins/zotpress/
%7B%22status%22%3A%22success%22%2C%22updateneeded%22%3Afalse%2C%22instance%22%3Afalse%2C%22meta%22%3A%7B%22request_last%22%3A50%2C%22request_next%22%3A50%2C%22used_cache%22%3Atrue%7D%2C%22data%22%3A%5B%7B%22key%22%3A%22QBP6Y3WY%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Isensee%20et%20al.%22%2C%22parsedDate%22%3A%222025-03-11%22%2C%22numChildren%22%3A2%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BIsensee%2C%20F.%2C%20Rokuss%2C%20M.%2C%20Kr%26%23xE4%3Bmer%2C%20L.%2C%20Dinkelacker%2C%20S.%2C%20Ravindran%2C%20A.%2C%20Stritzke%2C%20F.%2C%20Hamm%2C%20B.%2C%20Wald%2C%20T.%2C%20Langenberg%2C%20M.%2C%20Ulrich%2C%20C.%2C%20Deissler%2C%20J.%2C%20Floca%2C%20R.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20%282025%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BnnInteractive%3A%20Redefining%203D%20Promptable%20Segmentation%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2503.08373%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2503.08373%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2503.08373%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22nnInteractive%3A%20Redefining%203D%20Promptable%20Segmentation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%22%2C%22lastName%22%3A%22Rokuss%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Kr%5Cu00e4mer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Stefan%22%2C%22lastName%22%3A%22Dinkelacker%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ashis%22%2C%22lastName%22%3A%22Ravindran%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Stritzke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Benjamin%22%2C%22lastName%22%3A%22Hamm%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tassilo%22%2C%22lastName%22%3A%22Wald%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Moritz%22%2C%22lastName%22%3A%22Langenberg%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jonathan%22%2C%22lastName%22%3A%22Deissler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ralf%22%2C%22lastName%22%3A%22Floca%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22Accurate%20and%20efficient%203D%20segmentation%20is%20essential%20for%20both%20clinical%20and%20research%20applications.%20While%20foundation%20models%20like%20SAM%20have%20revolutionized%20interactive%20segmentation%2C%20their%202D%20design%20and%20domain%20shift%20limitations%20make%20them%20ill-suited%20for%203D%20medical%20images.%20Current%20adaptations%20address%20some%20of%20these%20challenges%20but%20remain%20limited%2C%20either%20lacking%20volumetric%20awareness%2C%20offering%20restricted%20interactivity%2C%20or%20supporting%20only%20a%20small%20set%20of%20structures%20and%20modalities.%20Usability%20also%20remains%20a%20challenge%2C%20as%20current%20tools%20are%20rarely%20integrated%20into%20established%20imaging%20platforms%20and%20often%20rely%20on%20cumbersome%20web-based%20interfaces%20with%20restricted%20functionality.%20We%20introduce%20nnInteractive%2C%20the%20first%20comprehensive%203D%20interactive%20open-set%20segmentation%20method.%20It%20supports%20diverse%20prompts%5Cu2014including%20points%2C%20scribbles%2C%20boxes%2C%20and%20a%20novel%20lasso%20prompt%5Cu2014while%20leveraging%20intuitive%202D%20interactions%20to%20generate%20full%203D%20segmentations.%20Trained%20on%20120%2B%20diverse%20volumetric%203D%20datasets%20%28CT%2C%20MRI%2C%20PET%2C%203D%20Microscopy%2C%20etc.%29%2C%20nnInteractive%20sets%20a%20new%20state-of-the-art%20in%20accuracy%2C%20adaptability%2C%20and%20usability.%20Crucially%2C%20it%20is%20the%20first%20method%20integrated%20into%20widely%20used%20image%20viewers%20%28e.g.%2C%20Napari%2C%20MITK%29%2C%20ensuring%20broad%20accessibility%20for%20real-world%20clinical%20and%20research%20applications.%20Extensive%20benchmarking%20demonstrates%20that%20nnInteractive%20far%20surpasses%20existing%20methods%2C%20setting%20a%20new%20standard%20for%20AI-driven%20interactive%203D%20segmentation.%20nnInteractive%20is%20publicly%20available%3A%20Napari%20plugin%2C%20MITK%20integration%2C%20Python%20backend.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2503.08373%22%2C%22date%22%3A%222025-03-11%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2503.08373%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2503.08373%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-03-12T09%3A55%3A50Z%22%7D%7D%2C%7B%22key%22%3A%22RVZ56NDQ%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Bassi%20et%20al.%22%2C%22parsedDate%22%3A%222025-01-20%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BBassi%2C%20P.%20R.%20A.%20S.%2C%20Li%2C%20W.%2C%20Tang%2C%20Y.%2C%20Isensee%2C%20F.%2C%20Wang%2C%20Z.%2C%20Chen%2C%20J.%2C%20Chou%2C%20Y.-C.%2C%20Kirchhoff%2C%20Y.%2C%20Rokuss%2C%20M.%2C%20Huang%2C%20Z.%2C%20Ye%2C%20J.%2C%20He%2C%20J.%2C%20Wald%2C%20T.%2C%20Ulrich%2C%20C.%2C%20Baumgartner%2C%20M.%2C%20Roy%2C%20S.%2C%20Maier-Hein%2C%20K.%20H.%2C%20Jaeger%2C%20P.%2C%20Ye%2C%20Y.%2C%20%26%23x2026%3B%20Zhou%2C%20Z.%20%282025%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BTouchstone%20Benchmark%3A%20Are%20We%20on%20the%20Right%20Way%20for%20Evaluating%20AI%20Algorithms%20for%20Medical%20Segmentation%3F%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2411.03670%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2411.03670%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2411.03670%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Touchstone%20Benchmark%3A%20Are%20We%20on%20the%20Right%20Way%20for%20Evaluating%20AI%20Algorithms%20for%20Medical%20Segmentation%3F%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pedro%20R.%20A.%20S.%22%2C%22lastName%22%3A%22Bassi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Wenxuan%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yucheng%22%2C%22lastName%22%3A%22Tang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zifu%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jieneng%22%2C%22lastName%22%3A%22Chen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yu-Cheng%22%2C%22lastName%22%3A%22Chou%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yannick%22%2C%22lastName%22%3A%22Kirchhoff%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%22%2C%22lastName%22%3A%22Rokuss%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ziyan%22%2C%22lastName%22%3A%22Huang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jin%22%2C%22lastName%22%3A%22Ye%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Junjun%22%2C%22lastName%22%3A%22He%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tassilo%22%2C%22lastName%22%3A%22Wald%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Baumgartner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Saikat%22%2C%22lastName%22%3A%22Roy%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%22%2C%22lastName%22%3A%22Jaeger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yiwen%22%2C%22lastName%22%3A%22Ye%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yutong%22%2C%22lastName%22%3A%22Xie%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jianpeng%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ziyang%22%2C%22lastName%22%3A%22Chen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yong%22%2C%22lastName%22%3A%22Xia%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zhaohu%22%2C%22lastName%22%3A%22Xing%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lei%22%2C%22lastName%22%3A%22Zhu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yousef%22%2C%22lastName%22%3A%22Sadegheih%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Afshin%22%2C%22lastName%22%3A%22Bozorgpour%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pratibha%22%2C%22lastName%22%3A%22Kumari%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Reza%22%2C%22lastName%22%3A%22Azad%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dorit%22%2C%22lastName%22%3A%22Merhof%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pengcheng%22%2C%22lastName%22%3A%22Shi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ting%22%2C%22lastName%22%3A%22Ma%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yuxin%22%2C%22lastName%22%3A%22Du%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fan%22%2C%22lastName%22%3A%22Bai%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tiejun%22%2C%22lastName%22%3A%22Huang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bo%22%2C%22lastName%22%3A%22Zhao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Haonan%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiaomeng%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hanxue%22%2C%22lastName%22%3A%22Gu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Haoyu%22%2C%22lastName%22%3A%22Dong%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jichen%22%2C%22lastName%22%3A%22Yang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maciej%20A.%22%2C%22lastName%22%3A%22Mazurowski%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Saumya%22%2C%22lastName%22%3A%22Gupta%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Linshan%22%2C%22lastName%22%3A%22Wu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jiaxin%22%2C%22lastName%22%3A%22Zhuang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hao%22%2C%22lastName%22%3A%22Chen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Holger%22%2C%22lastName%22%3A%22Roth%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daguang%22%2C%22lastName%22%3A%22Xu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Matthew%20B.%22%2C%22lastName%22%3A%22Blaschko%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sergio%22%2C%22lastName%22%3A%22Decherchi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrea%22%2C%22lastName%22%3A%22Cavalli%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alan%20L.%22%2C%22lastName%22%3A%22Yuille%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zongwei%22%2C%22lastName%22%3A%22Zhou%22%7D%5D%2C%22abstractNote%22%3A%22How%20can%20we%20test%20AI%20performance%3F%20This%20question%20seems%20trivial%2C%20but%20it%20isn%26%23039%3Bt.%20Standard%20benchmarks%20often%20have%20problems%20such%20as%20in-distribution%20and%20small-size%20test%20sets%2C%20oversimplified%20metrics%2C%20unfair%20comparisons%2C%20and%20short-term%20outcome%20pressure.%20As%20a%20consequence%2C%20good%20performance%20on%20standard%20benchmarks%20does%20not%20guarantee%20success%20in%20real-world%20scenarios.%20To%20address%20these%20problems%2C%20we%20present%20Touchstone%2C%20a%20large-scale%20collaborative%20segmentation%20benchmark%20of%209%20types%20of%20abdominal%20organs.%20This%20benchmark%20is%20based%20on%205%2C195%20training%20CT%20scans%20from%2076%20hospitals%20around%20the%20world%20and%205%2C903%20testing%20CT%20scans%20from%2011%20additional%20hospitals.%20This%20diverse%20test%20set%20enhances%20the%20statistical%20significance%20of%20benchmark%20results%20and%20rigorously%20evaluates%20AI%20algorithms%20across%20various%20out-of-distribution%20scenarios.%20We%20invited%2014%20inventors%20of%2019%20AI%20algorithms%20to%20train%20their%20algorithms%2C%20while%20our%20team%2C%20as%20a%20third%20party%2C%20independently%20evaluated%20these%20algorithms%20on%20three%20test%20sets.%20In%20addition%2C%20we%20also%20evaluated%20pre-existing%20AI%20frameworks--which%2C%20differing%20from%20algorithms%2C%20are%20more%20flexible%20and%20can%20support%20different%20algorithms--including%20MONAI%20from%20NVIDIA%2C%20nnU-Net%20from%20DKFZ%2C%20and%20numerous%20other%20open-source%20frameworks.%20We%20are%20committed%20to%20expanding%20this%20benchmark%20to%20encourage%20more%20innovation%20of%20AI%20algorithms%20for%20the%20medical%20domain.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2411.03670%22%2C%22date%22%3A%222025-01-20%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2411.03670%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2411.03670%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A26%3A58Z%22%7D%7D%2C%7B%22key%22%3A%22IHDI9EVM%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Isensee%20et%20al.%22%2C%22parsedDate%22%3A%222024-12-02%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BIsensee%2C%20F.%2C%20Kirchhoff%2C%20Y.%2C%20Kraemer%2C%20L.%2C%20Rokuss%2C%20M.%2C%20Ulrich%2C%20C.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20H.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BScaling%20nnU-Net%20for%20CBCT%20Segmentation%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2411.17213%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2411.17213%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2411.17213%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Scaling%20nnU-Net%20for%20CBCT%20Segmentation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yannick%22%2C%22lastName%22%3A%22Kirchhoff%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Kraemer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%22%2C%22lastName%22%3A%22Rokuss%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20presents%20our%20approach%20to%20scaling%20the%20nnU-Net%20framework%20for%20multi-structure%20segmentation%20on%20Cone%20Beam%20Computed%20Tomography%20%28CBCT%29%20images%2C%20specifically%20in%20the%20scope%20of%20the%20ToothFairy2%20Challenge.%20We%20leveraged%20the%20nnU-Net%20ResEnc%20L%20model%2C%20introducing%20key%20modifications%20to%20patch%20size%2C%20network%20topology%2C%20and%20data%20augmentation%20strategies%20to%20address%20the%20unique%20challenges%20of%20dental%20CBCT%20imaging.%20Our%20method%20achieved%20a%20mean%20Dice%20coefficient%20of%200.9253%20and%20HD95%20of%2018.472%20on%20the%20test%20set%2C%20securing%20a%20mean%20rank%20of%204.6%20and%20with%20it%20the%20first%20place%20in%20the%20ToothFairy2%20challenge.%20The%20source%20code%20is%20publicly%20available%2C%20encouraging%20further%20research%20and%20development%20in%20the%20field.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2411.17213%22%2C%22date%22%3A%222024-12-02%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2411.17213%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2411.17213%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A32%3A15Z%22%7D%7D%2C%7B%22key%22%3A%228ZJR892J%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Yang%20et%20al.%22%2C%22parsedDate%22%3A%222024-11-27%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BYang%2C%20L.%2C%20Liu%2C%20Q.%2C%20Kumar%2C%20P.%2C%20Sengupta%2C%20A.%2C%20Farnoud%2C%20A.%2C%20Shen%2C%20R.%2C%20Trofimova%2C%20D.%2C%20Ziegler%2C%20S.%2C%20Davoudi%2C%20N.%2C%20Doryab%2C%20A.%2C%20Yildirim%2C%20A.%20%26%23xD6%3B.%2C%20Diefenbacher%2C%20M.%20E.%2C%20Schiller%2C%20H.%20B.%2C%20Razansky%2C%20D.%2C%20Piraud%2C%20M.%2C%20Burgstaller%2C%20G.%2C%20Kreyling%2C%20W.%20G.%2C%20Isensee%2C%20F.%2C%20Rehberg%2C%20M.%2C%20%26%23x2026%3B%20Schmid%2C%20O.%20%282024%29.%20%26lt%3Bb%26gt%3BLungVis%201.0%3A%20an%20automatic%20AI-powered%203D%20imaging%20ecosystem%20unveils%20spatial%20profiling%20of%20nanoparticle%20delivery%20and%20acinar%20migration%20of%20lung%20macrophages%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BNature%20Communications%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B15%26lt%3B%5C%2Fi%26gt%3B%281%29%2C%2010138.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1038%5C%2Fs41467-024-54267-1%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1038%5C%2Fs41467-024-54267-1%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22LungVis%201.0%3A%20an%20automatic%20AI-powered%203D%20imaging%20ecosystem%20unveils%20spatial%20profiling%20of%20nanoparticle%20delivery%20and%20acinar%20migration%20of%20lung%20macrophages%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lin%22%2C%22lastName%22%3A%22Yang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Qiongliang%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pramod%22%2C%22lastName%22%3A%22Kumar%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Arunima%22%2C%22lastName%22%3A%22Sengupta%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ali%22%2C%22lastName%22%3A%22Farnoud%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ruolin%22%2C%22lastName%22%3A%22Shen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Darya%22%2C%22lastName%22%3A%22Trofimova%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sebastian%22%2C%22lastName%22%3A%22Ziegler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Neda%22%2C%22lastName%22%3A%22Davoudi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ali%22%2C%22lastName%22%3A%22Doryab%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ali%20%5Cu00d6nder%22%2C%22lastName%22%3A%22Yildirim%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Markus%20E.%22%2C%22lastName%22%3A%22Diefenbacher%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Herbert%20B.%22%2C%22lastName%22%3A%22Schiller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%22%2C%22lastName%22%3A%22Razansky%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marie%22%2C%22lastName%22%3A%22Piraud%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gerald%22%2C%22lastName%22%3A%22Burgstaller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Wolfgang%20G.%22%2C%22lastName%22%3A%22Kreyling%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Markus%22%2C%22lastName%22%3A%22Rehberg%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tobias%22%2C%22lastName%22%3A%22Stoeger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Otmar%22%2C%22lastName%22%3A%22Schmid%22%7D%5D%2C%22abstractNote%22%3A%22Targeted%20%28nano-%29drug%20delivery%20is%20essential%20for%20treating%20respiratory%20diseases%2C%20which%20are%20often%20confined%20to%20distinct%20lung%20regions.%20However%2C%20spatio-temporal%20profiling%20of%20drugs%20or%20nanoparticles%20%28NPs%29%20and%20their%20interactions%20with%20lung%20macrophages%20remains%20unresolved.%20Here%2C%20we%20present%20LungVis%201.0%2C%20an%20AI-powered%20imaging%20ecosystem%20that%20integrates%20light%20sheet%20fluorescence%20microscopy%20with%20deep%20learning-based%20image%20analysis%20pipelines%20to%20map%20NP%20deposition%20and%20dosage%20holistically%20and%20quantitatively%20across%20bronchial%20and%20alveolar%20%28acinar%29%20regions%20in%20murine%20lungs%20for%20widely-used%20bulk-liquid%20and%20aerosol-based%20delivery%20methods.%20We%20demonstrate%20that%20bulk-liquid%20delivery%20results%20in%20patchy%20NP%20distribution%20with%20elevated%20bronchial%20doses%2C%20whereas%20aerosols%20achieve%20uniform%20deposition%20reaching%20distal%20alveoli.%20Furthermore%2C%20we%20reveal%20that%20lung%20tissue-resident%20macrophages%20%28TRMs%29%20are%20dynamic%2C%20actively%20patrolling%20and%20redistributing%20NPs%20within%20alveoli%2C%20contesting%20the%20conventional%20paradigm%20of%20TRMs%20as%20static%20entities.%20LungVis%201.0%20provides%20an%20advanced%20framework%20for%20exploring%20pulmonary%20delivery%20dynamics%20and%20deepening%20insights%20into%20TRM-mediated%20lung%20immunity.%22%2C%22date%22%3A%222024-11-27%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1038%5C%2Fs41467-024-54267-1%22%2C%22ISSN%22%3A%222041-1723%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.nature.com%5C%2Farticles%5C%2Fs41467-024-54267-1%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A02%3A29Z%22%7D%7D%2C%7B%22key%22%3A%22XI9Q8VBI%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Wald%20et%20al.%22%2C%22parsedDate%22%3A%222024-10-30%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BWald%2C%20T.%2C%20Ulrich%2C%20C.%2C%20K%26%23xF6%3Bhler%2C%20G.%2C%20Zimmerer%2C%20D.%2C%20Denner%2C%20S.%2C%20Baumgartner%2C%20M.%2C%20Isensee%2C%20F.%2C%20Jaini%2C%20P.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20H.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BDecoupling%20Semantic%20Similarity%20from%20Spatial%20Alignment%20for%20Neural%20Networks%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2410.23107%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2410.23107%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2410.23107%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Decoupling%20Semantic%20Similarity%20from%20Spatial%20Alignment%20for%20Neural%20Networks%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tassilo%22%2C%22lastName%22%3A%22Wald%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gregor%22%2C%22lastName%22%3A%22K%5Cu00f6hler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Zimmerer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Stefan%22%2C%22lastName%22%3A%22Denner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Baumgartner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Priyank%22%2C%22lastName%22%3A%22Jaini%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22What%20representation%20do%20deep%20neural%20networks%20learn%3F%20How%20similar%20are%20images%20to%20each%20other%20for%20neural%20networks%3F%20Despite%20the%20overwhelming%20success%20of%20deep%20learning%20methods%20key%20questions%20about%20their%20internal%20workings%20still%20remain%20largely%20unanswered%2C%20due%20to%20their%20internal%20high%20dimensionality%20and%20complexity.%20To%20address%20this%2C%20one%20approach%20is%20to%20measure%20the%20similarity%20of%20activation%20responses%20to%20various%20inputs.%20Representational%20Similarity%20Matrices%20%28RSMs%29%20distill%20this%20similarity%20into%20scalar%20values%20for%20each%20input%20pair.%20These%20matrices%20encapsulate%20the%20entire%20similarity%20structure%20of%20a%20system%2C%20indicating%20which%20input%20leads%20to%20similar%20responses.%20While%20the%20similarity%20between%20images%20is%20ambiguous%2C%20we%20argue%20that%20the%20spatial%20location%20of%20semantic%20objects%20does%20neither%20influence%20human%20perception%20nor%20deep%20learning%20classifiers.%20Thus%20this%20should%20be%20reflected%20in%20the%20definition%20of%20similarity%20between%20image%20responses%20for%20computer%20vision%20systems.%20Revisiting%20the%20established%20similarity%20calculations%20for%20RSMs%20we%20expose%20their%20sensitivity%20to%20spatial%20alignment.%20In%20this%20paper%2C%20we%20propose%20to%20solve%20this%20through%20semantic%20RSMs%2C%20which%20are%20invariant%20to%20spatial%20permutation.%20We%20measure%20semantic%20similarity%20between%20input%20responses%20by%20formulating%20it%20as%20a%20set-matching%20problem.%20Further%2C%20we%20quantify%20the%20superiority%20of%20semantic%20RSMs%20over%20spatio-semantic%20RSMs%20through%20image%20retrieval%20and%20by%20comparing%20the%20similarity%20between%20representations%20to%20the%20similarity%20between%20predicted%20class%20probabilities.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2410.23107%22%2C%22date%22%3A%222024-10-30%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2410.23107%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2410.23107%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A33%3A32Z%22%7D%7D%2C%7B%22key%22%3A%22HKUF82MH%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Klein%20et%20al.%22%2C%22parsedDate%22%3A%222024-10-23%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BKlein%2C%20L.%2C%20Ziegler%2C%20S.%2C%20Gerst%2C%20F.%2C%20Morgenroth%2C%20Y.%2C%20Gotkowski%2C%20K.%2C%20Sch%26%23xF6%3Bniger%2C%20E.%2C%20Heni%2C%20M.%2C%20Kipke%2C%20N.%2C%20Friedland%2C%20D.%2C%20Seiler%2C%20A.%2C%20Geibelt%2C%20E.%2C%20Yamazaki%2C%20H.%2C%20H%26%23xE4%3Bring%2C%20H.%20U.%2C%20Wagner%2C%20S.%2C%20Nadalin%2C%20S.%2C%20K%26%23xF6%3Bnigsrainer%2C%20A.%2C%20Mihaljevi%26%23x107%3B%2C%20A.%20L.%2C%20Hartmann%2C%20D.%2C%20Fend%2C%20F.%2C%20%26%23x2026%3B%20Wagner%2C%20R.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BExplainable%20AI-based%20analysis%20of%20human%20pancreas%20sections%20identifies%20traits%20of%20type%202%20diabetes%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B.%20medRxiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1101%5C%2F2024.10.23.24315937%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1101%5C%2F2024.10.23.24315937%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Explainable%20AI-based%20analysis%20of%20human%20pancreas%20sections%20identifies%20traits%20of%20type%202%20diabetes%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22L.%22%2C%22lastName%22%3A%22Klein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22S.%22%2C%22lastName%22%3A%22Ziegler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22F.%22%2C%22lastName%22%3A%22Gerst%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Y.%22%2C%22lastName%22%3A%22Morgenroth%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22K.%22%2C%22lastName%22%3A%22Gotkowski%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22E.%22%2C%22lastName%22%3A%22Sch%5Cu00f6niger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22M.%22%2C%22lastName%22%3A%22Heni%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22N.%22%2C%22lastName%22%3A%22Kipke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22D.%22%2C%22lastName%22%3A%22Friedland%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22A.%22%2C%22lastName%22%3A%22Seiler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22E.%22%2C%22lastName%22%3A%22Geibelt%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22H.%22%2C%22lastName%22%3A%22Yamazaki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22H.%20U.%22%2C%22lastName%22%3A%22H%5Cu00e4ring%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22S.%22%2C%22lastName%22%3A%22Wagner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22S.%22%2C%22lastName%22%3A%22Nadalin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22A.%22%2C%22lastName%22%3A%22K%5Cu00f6nigsrainer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22A.%20L.%22%2C%22lastName%22%3A%22Mihaljevi%5Cu0107%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22D.%22%2C%22lastName%22%3A%22Hartmann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22F.%22%2C%22lastName%22%3A%22Fend%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22D.%22%2C%22lastName%22%3A%22Aust%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22J.%22%2C%22lastName%22%3A%22Weitz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jumpertz-von%20Schwartzenberg%22%2C%22lastName%22%3A%22R%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22M.%22%2C%22lastName%22%3A%22Distler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22K.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22A.%20L.%22%2C%22lastName%22%3A%22Birkenfeld%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22S.%22%2C%22lastName%22%3A%22Ullrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22P.%22%2C%22lastName%22%3A%22J%5Cu00e4ger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22F.%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22M.%22%2C%22lastName%22%3A%22Solimena%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22R.%22%2C%22lastName%22%3A%22Wagner%22%7D%5D%2C%22abstractNote%22%3A%22Type%202%20diabetes%20%28T2D%29%20is%20a%20chronic%20disease%20currently%20affecting%20around%20500%20million%20people%20worldwide%20with%20often%20severe%20health%20consequences.%20Yet%2C%20histopathological%20analyses%20are%20still%20inadequate%20to%20infer%20the%20glycaemic%20state%20of%20a%20person%20based%20on%20morphological%20alterations%20linked%20to%20impaired%20insulin%20secretion%20and%20%5Cu03b2-cell%20failure%20in%20T2D.%20Giga-pixel%20microscopy%20can%20capture%20subtle%20morphological%20changes%2C%20but%20data%20complexity%20exceeds%20human%20analysis%20capabilities.%20In%20response%2C%20we%20generated%20a%20dataset%20of%20pancreas%20whole-slide%20images%20with%20multiple%20chromogenic%20and%20multiplex%20fluorescent%20stainings%20and%20trained%20deep%20learning%20models%20to%20predict%20the%20T2D%20status.%20Using%20explainable%20AI%2C%20we%20made%20the%20learned%20relationships%20interpretable%2C%20quantified%20them%20as%20biomarkers%2C%20and%20assessed%20their%20association%20with%20T2D.%20Remarkably%2C%20the%20highest%20prediction%20performance%20was%20achieved%20by%20simultaneously%20focusing%20on%20islet%20%5Cu03b1-and%20%5Cu03b4-cells%20and%20neuronal%20axons.%20Subtle%20alterations%20in%20the%20pancreatic%20tissue%20of%20T2D%20donors%20such%20as%20smaller%20islets%2C%20larger%20adipocyte%20clusters%2C%20altered%20islet-adipocyte%20proximity%2C%20and%20fibrotic%20patterns%20were%20also%20observed.%20Our%20innovative%20data-driven%20approach%20underpins%20key%20findings%20about%20pancreatic%20tissue%20alterations%20in%20T2D%20and%20provides%20novel%20targets%20for%20research.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22medRxiv%22%2C%22archiveID%22%3A%22%22%2C%22date%22%3A%222024-10-23%22%2C%22DOI%22%3A%2210.1101%5C%2F2024.10.23.24315937%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.medrxiv.org%5C%2Fcontent%5C%2F10.1101%5C%2F2024.10.23.24315937v1%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A10%3A58Z%22%7D%7D%2C%7B%22key%22%3A%22LBRF36BW%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Rokuss%20et%20al.%22%2C%22parsedDate%22%3A%222024-10-21%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BRokuss%2C%20M.%2C%20Kovacs%2C%20B.%2C%20Kirchhoff%2C%20Y.%2C%20Xiao%2C%20S.%2C%20Ulrich%2C%20C.%2C%20Maier-Hein%2C%20K.%20H.%2C%20%26amp%3B%20Isensee%2C%20F.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BFrom%20FDG%20to%20PSMA%3A%20A%20Hitchhiker%26%23x2019%3Bs%20Guide%20to%20Multitracer%2C%20Multicenter%20Lesion%20Segmentation%20in%20PET%5C%2FCT%20Imaging%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2409.09478%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2409.09478%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2409.09478%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22From%20FDG%20to%20PSMA%3A%20A%20Hitchhiker%27s%20Guide%20to%20Multitracer%2C%20Multicenter%20Lesion%20Segmentation%20in%20PET%5C%2FCT%20Imaging%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%22%2C%22lastName%22%3A%22Rokuss%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Balint%22%2C%22lastName%22%3A%22Kovacs%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yannick%22%2C%22lastName%22%3A%22Kirchhoff%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shuhan%22%2C%22lastName%22%3A%22Xiao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%5D%2C%22abstractNote%22%3A%22Automated%20lesion%20segmentation%20in%20PET%5C%2FCT%20scans%20is%20crucial%20for%20improving%20clinical%20workflows%20and%20advancing%20cancer%20diagnostics.%20However%2C%20the%20task%20is%20challenging%20due%20to%20physiological%20variability%2C%20different%20tracers%20used%20in%20PET%20imaging%2C%20and%20diverse%20imaging%20protocols%20across%20medical%20centers.%20To%20address%20this%2C%20the%20autoPET%20series%20was%20created%20to%20challenge%20researchers%20to%20develop%20algorithms%20that%20generalize%20across%20diverse%20PET%5C%2FCT%20environments.%20This%20paper%20presents%20our%20solution%20for%20the%20autoPET%20III%20challenge%2C%20targeting%20multitracer%2C%20multicenter%20generalization%20using%20the%20nnU-Net%20framework%20with%20the%20ResEncL%20architecture.%20Key%20techniques%20include%20misalignment%20data%20augmentation%20and%20multi-modal%20pretraining%20across%20CT%2C%20MR%2C%20and%20PET%20datasets%20to%20provide%20an%20initial%20anatomical%20understanding.%20We%20incorporate%20organ%20supervision%20as%20a%20multitask%20approach%2C%20enabling%20the%20model%20to%20distinguish%20between%20physiological%20uptake%20and%20tracer-specific%20patterns%2C%20which%20is%20particularly%20beneficial%20in%20cases%20where%20no%20lesions%20are%20present.%20Compared%20to%20the%20default%20nnU-Net%2C%20which%20achieved%20a%20Dice%20score%20of%2057.61%2C%20or%20the%20larger%20ResEncL%20%2865.31%29%20our%20model%20significantly%20improved%20performance%20with%20a%20Dice%20score%20of%2068.40%2C%20alongside%20a%20reduction%20in%20false%20positive%20%28FPvol%3A%207.82%29%20and%20false%20negative%20%28FNvol%3A%2010.35%29%20volumes.%20These%20results%20underscore%20the%20effectiveness%20of%20combining%20advanced%20network%20design%2C%20augmentation%2C%20pretraining%2C%20and%20multitask%20learning%20for%20PET%5C%2FCT%20lesion%20segmentation.%20After%20evaluation%20on%20the%20test%20set%2C%20our%20approach%20was%20awarded%20the%20first%20place%20in%20the%20model-centric%20category%20%28Team%20LesionTracer%29.%20Code%20is%20publicly%20available%20at%20https%3A%5C%2F%5C%2Fgithub.com%5C%2FMIC-DKFZ%5C%2Fautopet-3-submission.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2409.09478%22%2C%22date%22%3A%222024-10-21%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2409.09478%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2409.09478%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-05-02T08%3A46%3A07Z%22%7D%7D%2C%7B%22key%22%3A%223GB98SWN%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Rokuss%20et%20al.%22%2C%22parsedDate%22%3A%222024-09-20%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BRokuss%2C%20M.%2C%20Kirchhoff%2C%20Y.%2C%20Roy%2C%20S.%2C%20Kovacs%2C%20B.%2C%20Ulrich%2C%20C.%2C%20Wald%2C%20T.%2C%20Zenk%2C%20M.%2C%20Denner%2C%20S.%2C%20Isensee%2C%20F.%2C%20Vollmuth%2C%20P.%2C%20Kleesiek%2C%20J.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BLongitudinal%20Segmentation%20of%20MS%20Lesions%20via%20Temporal%20Difference%20Weighting%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2409.13416%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2409.13416%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2409.13416%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Longitudinal%20Segmentation%20of%20MS%20Lesions%20via%20Temporal%20Difference%20Weighting%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%22%2C%22lastName%22%3A%22Rokuss%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yannick%22%2C%22lastName%22%3A%22Kirchhoff%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Saikat%22%2C%22lastName%22%3A%22Roy%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Balint%22%2C%22lastName%22%3A%22Kovacs%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tassilo%22%2C%22lastName%22%3A%22Wald%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%22%2C%22lastName%22%3A%22Zenk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Stefan%22%2C%22lastName%22%3A%22Denner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Philipp%22%2C%22lastName%22%3A%22Vollmuth%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jens%22%2C%22lastName%22%3A%22Kleesiek%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22Accurate%20segmentation%20of%20Multiple%20Sclerosis%20%28MS%29%20lesions%20in%20longitudinal%20MRI%20scans%20is%20crucial%20for%20monitoring%20disease%20progression%20and%20treatment%20efficacy.%20Although%20changes%20across%20time%20are%20taken%20into%20account%20when%20assessing%20images%20in%20clinical%20practice%2C%20most%20existing%20deep%20learning%20methods%20treat%20scans%20from%20different%20timepoints%20separately.%20Among%20studies%20utilizing%20longitudinal%20images%2C%20a%20simple%20channel-wise%20concatenation%20is%20the%20primary%20albeit%20suboptimal%20method%20employed%20to%20integrate%20timepoints.%20We%20introduce%20a%20novel%20approach%20that%20explicitly%20incorporates%20temporal%20differences%20between%20baseline%20and%20follow-up%20scans%20through%20a%20unique%20architectural%20inductive%20bias%20called%20Difference%20Weighting%20Block.%20It%20merges%20features%20from%20two%20timepoints%2C%20emphasizing%20changes%20between%20scans.%20We%20achieve%20superior%20scores%20in%20lesion%20segmentation%20%28Dice%20Score%2C%20Hausdorff%20distance%29%20as%20well%20as%20lesion%20detection%20%28lesion-level%20%24F_1%24%20score%29%20as%20compared%20to%20state-of-the-art%20longitudinal%20and%20single%20timepoint%20models%20across%20two%20datasets.%20Our%20code%20is%20made%20publicly%20available%20at%20www.github.com%5C%2FMIC-DKFZ%5C%2FLongitudinal-Difference-Weighting.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2409.13416%22%2C%22date%22%3A%222024-09-20%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2409.13416%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2409.13416%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A28%3A26Z%22%7D%7D%2C%7B%22key%22%3A%223CDJ7B43%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Kovacs%20et%20al.%22%2C%22parsedDate%22%3A%222024-09-16%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BKovacs%2C%20B.%2C%20Xiao%2C%20S.%2C%20Rokuss%2C%20M.%2C%20Ulrich%2C%20C.%2C%20Isensee%2C%20F.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20H.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BData-Centric%20Strategies%20for%20Overcoming%20PET%5C%2FCT%20Heterogeneity%3A%20Insights%20from%20the%20AutoPET%20III%20Lesion%20Segmentation%20Challenge%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2409.10120%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2409.10120%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2409.10120%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Data-Centric%20Strategies%20for%20Overcoming%20PET%5C%2FCT%20Heterogeneity%3A%20Insights%20from%20the%20AutoPET%20III%20Lesion%20Segmentation%20Challenge%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Balint%22%2C%22lastName%22%3A%22Kovacs%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shuhan%22%2C%22lastName%22%3A%22Xiao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%22%2C%22lastName%22%3A%22Rokuss%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22The%20third%20autoPET%20challenge%20introduced%20a%20new%20data-centric%20task%20this%20year%2C%20shifting%20the%20focus%20from%20model%20development%20to%20improving%20metastatic%20lesion%20segmentation%20on%20PET%5C%2FCT%20images%20through%20data%20quality%20and%20handling%20strategies.%20In%20response%2C%20we%20developed%20targeted%20methods%20to%20enhance%20segmentation%20performance%20tailored%20to%20the%20characteristics%20of%20PET%5C%2FCT%20imaging.%20Our%20approach%20encompasses%20two%20key%20elements.%20First%2C%20to%20address%20potential%20alignment%20errors%20between%20CT%20and%20PET%20modalities%20as%20well%20as%20the%20prevalence%20of%20punctate%20lesions%2C%20we%20modified%20the%20baseline%20data%20augmentation%20scheme%20and%20extended%20it%20with%20misalignment%20augmentation.%20This%20adaptation%20aims%20to%20improve%20segmentation%20accuracy%2C%20particularly%20for%20tiny%20metastatic%20lesions.%20Second%2C%20to%20tackle%20the%20variability%20in%20image%20dimensions%20significantly%20affecting%20the%20prediction%20time%2C%20we%20implemented%20a%20dynamic%20ensembling%20and%20test-time%20augmentation%20%28TTA%29%20strategy.%20This%20method%20optimizes%20the%20use%20of%20ensembling%20and%20TTA%20within%20a%205-minute%20prediction%20time%20limit%2C%20effectively%20leveraging%20the%20generalization%20potential%20for%20both%20small%20and%20large%20images.%20Both%20of%20our%20solutions%20are%20designed%20to%20be%20robust%20across%20different%20tracers%20and%20institutional%20settings%2C%20offering%20a%20general%2C%20yet%20imaging-specific%20approach%20to%20the%20multi-tracer%20and%20multi-institutional%20challenges%20of%20the%20competition.%20We%20made%20the%20challenge%20repository%20with%20our%20modifications%20publicly%20available%20at%20%5C%5Curl%7Bhttps%3A%5C%2F%5C%2Fgithub.com%5C%2FMIC-DKFZ%5C%2Fmiccai2024_autopet3_datacentric%7D.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2409.10120%22%2C%22date%22%3A%222024-09-16%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2409.10120%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2409.10120%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A36%3A23Z%22%7D%7D%2C%7B%22key%22%3A%22YMWVH5AM%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22R%5Cu00e4dsch%20et%20al.%22%2C%22parsedDate%22%3A%222024-07-26%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BR%26%23xE4%3Bdsch%2C%20T.%2C%20Reinke%2C%20A.%2C%20Weru%2C%20V.%2C%20Tizabi%2C%20M.%20D.%2C%20Heller%2C%20N.%2C%20Isensee%2C%20F.%2C%20Kopp-Schneider%2C%20A.%2C%20%26amp%3B%20Maier-Hein%2C%20L.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BQuality%20Assured%3A%20Rethinking%20Annotation%20Strategies%20in%20Imaging%20AI%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2407.17596%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2407.17596%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2407.17596%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Quality%20Assured%3A%20Rethinking%20Annotation%20Strategies%20in%20Imaging%20AI%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tim%22%2C%22lastName%22%3A%22R%5Cu00e4dsch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Annika%22%2C%22lastName%22%3A%22Reinke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Vivienn%22%2C%22lastName%22%3A%22Weru%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Minu%20D.%22%2C%22lastName%22%3A%22Tizabi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nicholas%22%2C%22lastName%22%3A%22Heller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Annette%22%2C%22lastName%22%3A%22Kopp-Schneider%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lena%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20does%20not%20describe%20a%20novel%20method.%20Instead%2C%20it%20studies%20an%20essential%20foundation%20for%20reliable%20benchmarking%20and%20ultimately%20real-world%20application%20of%20AI-based%20image%20analysis%3A%20generating%20high-quality%20reference%20annotations.%20Previous%20research%20has%20focused%20on%20crowdsourcing%20as%20a%20means%20of%20outsourcing%20annotations.%20However%2C%20little%20attention%20has%20so%20far%20been%20given%20to%20annotation%20companies%2C%20specifically%20regarding%20their%20internal%20quality%20assurance%20%28QA%29%20processes.%20Therefore%2C%20our%20aim%20is%20to%20evaluate%20the%20influence%20of%20QA%20employed%20by%20annotation%20companies%20on%20annotation%20quality%20and%20devise%20methodologies%20for%20maximizing%20data%20annotation%20efficacy.%20Based%20on%20a%20total%20of%2057%2C648%20instance%20segmented%20images%20obtained%20from%20a%20total%20of%20924%20annotators%20and%2034%20QA%20workers%20from%20four%20annotation%20companies%20and%20Amazon%20Mechanical%20Turk%20%28MTurk%29%2C%20we%20derived%20the%20following%20insights%3A%20%281%29%20Annotation%20companies%20perform%20better%20both%20in%20terms%20of%20quantity%20and%20quality%20compared%20to%20the%20widely%20used%20platform%20MTurk.%20%282%29%20Annotation%20companies%26%23039%3B%20internal%20QA%20only%20provides%20marginal%20improvements%2C%20if%20any.%20However%2C%20improving%20labeling%20instructions%20instead%20of%20investing%20in%20QA%20can%20substantially%20boost%20annotation%20performance.%20%283%29%20The%20benefit%20of%20internal%20QA%20depends%20on%20specific%20image%20characteristics.%20Our%20work%20could%20enable%20researchers%20to%20derive%20substantially%20more%20value%20from%20a%20fixed%20annotation%20budget%20and%20change%20the%20way%20annotation%20companies%20conduct%20internal%20QA.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2407.17596%22%2C%22date%22%3A%222024-07-26%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2407.17596%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2407.17596%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T13%3A07%3A10Z%22%7D%7D%2C%7B%22key%22%3A%22H4A828IZ%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Isensee%20et%20al.%22%2C%22parsedDate%22%3A%222024-07-25%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BIsensee%2C%20F.%2C%20Wald%2C%20T.%2C%20Ulrich%2C%20C.%2C%20Baumgartner%2C%20M.%2C%20Roy%2C%20S.%2C%20Maier-Hein%2C%20K.%2C%20%26amp%3B%20Jaeger%2C%20P.%20F.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BnnU-Net%20Revisited%3A%20A%20Call%20for%20Rigorous%20Validation%20in%203D%20Medical%20Image%20Segmentation%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2404.09556%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2404.09556%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2404.09556%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22nnU-Net%20Revisited%3A%20A%20Call%20for%20Rigorous%20Validation%20in%203D%20Medical%20Image%20Segmentation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tassilo%22%2C%22lastName%22%3A%22Wald%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Baumgartner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Saikat%22%2C%22lastName%22%3A%22Roy%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%20F.%22%2C%22lastName%22%3A%22Jaeger%22%7D%5D%2C%22abstractNote%22%3A%22The%20release%20of%20nnU-Net%20marked%20a%20paradigm%20shift%20in%203D%20medical%20image%20segmentation%2C%20demonstrating%20that%20a%20properly%20configured%20U-Net%20architecture%20could%20still%20achieve%20state-of-the-art%20results.%20Despite%20this%2C%20the%20pursuit%20of%20novel%20architectures%2C%20and%20the%20respective%20claims%20of%20superior%20performance%20over%20the%20U-Net%20baseline%2C%20continued.%20In%20this%20study%2C%20we%20demonstrate%20that%20many%20of%20these%20recent%20claims%20fail%20to%20hold%20up%20when%20scrutinized%20for%20common%20validation%20shortcomings%2C%20such%20as%20the%20use%20of%20inadequate%20baselines%2C%20insufficient%20datasets%2C%20and%20neglected%20computational%20resources.%20By%20meticulously%20avoiding%20these%20pitfalls%2C%20we%20conduct%20a%20thorough%20and%20comprehensive%20benchmarking%20of%20current%20segmentation%20methods%20including%20CNN-based%2C%20Transformer-based%2C%20and%20Mamba-based%20approaches.%20In%20contrast%20to%20current%20beliefs%2C%20we%20find%20that%20the%20recipe%20for%20state-of-the-art%20performance%20is%201%29%20employing%20CNN-based%20U-Net%20models%2C%20including%20ResNet%20and%20ConvNeXt%20variants%2C%202%29%20using%20the%20nnU-Net%20framework%2C%20and%203%29%20scaling%20models%20to%20modern%20hardware%20resources.%20These%20results%20indicate%20an%20ongoing%20innovation%20bias%20towards%20novel%20architectures%20in%20the%20field%20and%20underscore%20the%20need%20for%20more%20stringent%20validation%20standards%20in%20the%20quest%20for%20scientific%20progress.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2404.09556%22%2C%22date%22%3A%222024-07-25%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2404.09556%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2404.09556%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A22%3A19Z%22%7D%7D%2C%7B%22key%22%3A%222GABP5CD%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Kirchhoff%20et%20al.%22%2C%22parsedDate%22%3A%222024-07-17%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BKirchhoff%2C%20Y.%2C%20Rokuss%2C%20M.%20R.%2C%20Roy%2C%20S.%2C%20Kovacs%2C%20B.%2C%20Ulrich%2C%20C.%2C%20Wald%2C%20T.%2C%20Zenk%2C%20M.%2C%20Vollmuth%2C%20P.%2C%20Kleesiek%2C%20J.%2C%20Isensee%2C%20F.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BSkeleton%20Recall%20Loss%20for%20Connectivity%20Conserving%20and%20Resource%20Efficient%20Segmentation%20of%20Thin%20Tubular%20Structures%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2404.03010%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2404.03010%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2404.03010%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Skeleton%20Recall%20Loss%20for%20Connectivity%20Conserving%20and%20Resource%20Efficient%20Segmentation%20of%20Thin%20Tubular%20Structures%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yannick%22%2C%22lastName%22%3A%22Kirchhoff%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%20R.%22%2C%22lastName%22%3A%22Rokuss%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Saikat%22%2C%22lastName%22%3A%22Roy%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Balint%22%2C%22lastName%22%3A%22Kovacs%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tassilo%22%2C%22lastName%22%3A%22Wald%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%22%2C%22lastName%22%3A%22Zenk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Philipp%22%2C%22lastName%22%3A%22Vollmuth%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jens%22%2C%22lastName%22%3A%22Kleesiek%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22Accurately%20segmenting%20thin%20tubular%20structures%2C%20such%20as%20vessels%2C%20nerves%2C%20roads%20or%20concrete%20cracks%2C%20is%20a%20crucial%20task%20in%20computer%20vision.%20Standard%20deep%20learning-based%20segmentation%20loss%20functions%2C%20such%20as%20Dice%20or%20Cross-Entropy%2C%20focus%20on%20volumetric%20overlap%2C%20often%20at%20the%20expense%20of%20preserving%20structural%20connectivity%20or%20topology.%20This%20can%20lead%20to%20segmentation%20errors%20that%20adversely%20affect%20downstream%20tasks%2C%20including%20flow%20calculation%2C%20navigation%2C%20and%20structural%20inspection.%20Although%20current%20topology-focused%20losses%20mark%20an%20improvement%2C%20they%20introduce%20significant%20computational%20and%20memory%20overheads.%20This%20is%20particularly%20relevant%20for%203D%20data%2C%20rendering%20these%20losses%20infeasible%20for%20larger%20volumes%20as%20well%20as%20increasingly%20important%20multi-class%20segmentation%20problems.%20To%20mitigate%20this%2C%20we%20propose%20a%20novel%20Skeleton%20Recall%20Loss%2C%20which%20effectively%20addresses%20these%20challenges%20by%20circumventing%20intensive%20GPU-based%20calculations%20with%20inexpensive%20CPU%20operations.%20It%20demonstrates%20overall%20superior%20performance%20to%20current%20state-of-the-art%20approaches%20on%20five%20public%20datasets%20for%20topology-preserving%20segmentation%2C%20while%20substantially%20reducing%20computational%20overheads%20by%20more%20than%2090%25.%20In%20doing%20so%2C%20we%20introduce%20the%20first%20multi-class%20capable%20loss%20function%20for%20thin%20structure%20segmentation%2C%20excelling%20in%20both%20efficiency%20and%20efficacy%20for%20topology-preservation.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2404.03010%22%2C%22date%22%3A%222024-07-17%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2404.03010%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2404.03010%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A23%3A20Z%22%7D%7D%2C%7B%22key%22%3A%22ZWLISCQA%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Wood%20et%20al.%22%2C%22parsedDate%22%3A%222024-06%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BWood%2C%20A.%20M.%2C%20Abdallah%2C%20N.%2C%20Heller%2C%20N.%2C%20Benidir%2C%20T.%2C%20Isensee%2C%20F.%2C%20Tejpaul%2C%20R.%2C%20Suk-Ouichai%2C%20C.%2C%20Curry%2C%20C.%2C%20You%2C%20A.%2C%20Remer%2C%20E.%2C%20Haywood%2C%20S.%2C%20Campbell%2C%20S.%2C%20Papanikolopoulos%2C%20N.%2C%20%26amp%3B%20Weight%2C%20C.%20%282024%29.%20%26lt%3Bb%26gt%3BFully%20Automated%20Versions%20of%20Clinically%20Validated%20Nephrometry%20Scores%20Demonstrate%20Superior%20Predictive%20Utility%20versus%20Human%20Scores%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BBJU%20International%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B133%26lt%3B%5C%2Fi%26gt%3B%286%29%2C%20690%26%23x2013%3B698.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1111%5C%2Fbju.16276%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1111%5C%2Fbju.16276%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Fully%20Automated%20Versions%20of%20Clinically%20Validated%20Nephrometry%20Scores%20Demonstrate%20Superior%20Predictive%20Utility%20versus%20Human%20Scores%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrew%20M.%22%2C%22lastName%22%3A%22Wood%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nour%22%2C%22lastName%22%3A%22Abdallah%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nicholas%22%2C%22lastName%22%3A%22Heller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tarik%22%2C%22lastName%22%3A%22Benidir%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Resha%22%2C%22lastName%22%3A%22Tejpaul%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chalairat%22%2C%22lastName%22%3A%22Suk-Ouichai%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Caleb%22%2C%22lastName%22%3A%22Curry%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alex%22%2C%22lastName%22%3A%22You%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Erick%22%2C%22lastName%22%3A%22Remer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Samuel%22%2C%22lastName%22%3A%22Haywood%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Steven%22%2C%22lastName%22%3A%22Campbell%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nikolaos%22%2C%22lastName%22%3A%22Papanikolopoulos%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christopher%22%2C%22lastName%22%3A%22Weight%22%7D%5D%2C%22abstractNote%22%3A%22OBJECTIVE%3A%20To%20automate%20the%20generation%20of%20three%20validated%20nephrometry%20scoring%20systems%20on%20preoperative%20computerised%20tomography%20%28CT%29%20scans%20by%20developing%20artificial%20intelligence%20%28AI%29-based%20image%20processing%20methods.%20Subsequently%2C%20we%20aimed%20to%20evaluate%20the%20ability%20of%20these%20scores%20to%20predict%20meaningful%20pathological%20and%20perioperative%20outcomes.%5CnPATIENTS%20AND%20METHODS%3A%20A%20total%20of%20300%20patients%20with%20preoperative%20CT%20with%20early%20arterial%20contrast%20phase%20were%20identified%20from%20a%20cohort%20of%20544%20consecutive%20patients%20undergoing%20surgical%20extirpation%20for%20suspected%20renal%20cancer.%20A%20deep%20neural%20network%20approach%20was%20used%20to%20automatically%20segment%20kidneys%20and%20tumours%2C%20and%20then%20geometric%20algorithms%20were%20used%20to%20measure%20the%20components%20of%20the%20concordance%20index%20%28C-Index%29%2C%20Preoperative%20Aspects%20and%20Dimensions%20Used%20for%20an%20Anatomical%20classification%20of%20renal%20tumours%20%28PADUA%29%2C%20and%20tumour%20contact%20surface%20area%20%28CSA%29%20nephrometry%20scores.%20Human%20scores%20were%20independently%20calculated%20by%20medical%20personnel%20blinded%20to%20the%20AI%20scores.%20AI%20and%20human%20score%20agreement%20was%20assessed%20using%20linear%20regression%20and%20predictive%20abilities%20for%20meaningful%20outcomes%20were%20assessed%20using%20logistic%20regression%20and%20receiver%20operating%20characteristic%20curve%20analyses.%5CnRESULTS%3A%20The%20median%20%28interquartile%20range%29%20age%20was%2060%5Cu2009%2851-68%29%5Cu2009years%2C%20and%2040%25%20were%20female.%20The%20median%20tumour%20size%20was%204.2%5Cu2009cm%20and%2091.3%25%20had%20malignant%20tumours.%20In%20all%2C%2027%25%20of%20the%20tumours%20were%20high%20stage%2C%2037%25%20high%20grade%2C%20and%2063%25%20of%20the%20patients%20underwent%20partial%20nephrectomy.%20There%20was%20significant%20agreement%20between%20human%20and%20AI%20scores%20on%20linear%20regression%20analyses%20%28R%20ranged%20from%200.574%20to%200.828%2C%20all%20P%5Cu2009%26lt%3B%5Cu20090.001%29.%20The%20AI-generated%20scores%20were%20equivalent%20or%20superior%20to%20human-generated%20scores%20for%20all%20examined%20outcomes%20including%20high-grade%20histology%2C%20high-stage%20tumour%2C%20indolent%20tumour%2C%20pathological%20tumour%20necrosis%2C%20and%20radical%20nephrectomy%20%28vs%20partial%20nephrectomy%29%20surgical%20approach.%5CnCONCLUSIONS%3A%20Fully%20automated%20AI-generated%20C-Index%2C%20PADUA%2C%20and%20tumour%20CSA%20nephrometry%20scores%20are%20similar%20to%20human-generated%20scores%20and%20predict%20a%20wide%20variety%20of%20meaningful%20outcomes.%20Once%20validated%2C%20our%20results%20suggest%20that%20AI-generated%20nephrometry%20scores%20could%20be%20delivered%20automatically%20from%20a%20preoperative%20CT%20scan%20to%20a%20clinician%20and%20patient%20at%20the%20point%20of%20care%20to%20aid%20in%20decision%20making.%22%2C%22date%22%3A%222024-06%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1111%5C%2Fbju.16276%22%2C%22ISSN%22%3A%221464-410X%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A41%3A53Z%22%7D%7D%2C%7B%22key%22%3A%22AHEH655Q%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Yang%20et%20al.%22%2C%22parsedDate%22%3A%222024-04-30%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BYang%2C%20L.%2C%20Kumar%2C%20P.%2C%20Liu%2C%20Q.%2C%20Chen%2C%20P.%2C%20Li%2C%20C.%2C%20L%26%23xFC%3Bth%2C%20C.%2C%20Kr%26%23xE4%3Bmer%2C%20L.%2C%20Gabriel%2C%20C.%2C%20Jeridi%2C%20A.%2C%20Piraud%2C%20M.%2C%20Stoeger%2C%20T.%2C%20Staab-Weijnitz%2C%20C.%20a.%2C%20J%26%23xE4%3Bger%2C%20P.%2C%20Rehberg%2C%20M.%2C%20Isensee%2C%20F.%2C%20%26amp%3B%20Schmid%2C%20O.%20%282024%29.%20%26lt%3Bb%26gt%3BFresh%20Perspectives%20on%20Lung%20Morphometry%20and%20Pulmonary%20Drug%20Delivery%3A%20AI-powered%203D%20Imaging%20in%20Healthy%20and%20Fibrotic%20Murine%20Lungs%26lt%3B%5C%2Fb%26gt%3B.%20In%20%26lt%3Bi%26gt%3BB30.%20SCARRED%20FOR%20LIFE%3A%20TRANSLATIONAL%20RESEARCH%20IN%20INTERSTITIAL%20ABNORMALITIES%20AND%20LUNG%20FIBROSIS%26lt%3B%5C%2Fi%26gt%3B%20%28Vol.%201%26%23x2013%3B299%2C%20pp.%20A3242%26%23x2013%3BA3242%29.%20American%20Thoracic%20Society.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1164%5C%2Fajrccm-conference.2024.209.1_MeetingAbstracts.A3242%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22bookSection%22%2C%22title%22%3A%22Fresh%20Perspectives%20on%20Lung%20Morphometry%20and%20Pulmonary%20Drug%20Delivery%3A%20AI-powered%203D%20Imaging%20in%20Healthy%20and%20Fibrotic%20Murine%20Lungs%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22L.%22%2C%22lastName%22%3A%22Yang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22P.%22%2C%22lastName%22%3A%22Kumar%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Q.%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22P.%22%2C%22lastName%22%3A%22Chen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22C.%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22C.%22%2C%22lastName%22%3A%22L%5Cu00fcth%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22L.%22%2C%22lastName%22%3A%22Kr%5Cu00e4mer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22C.%22%2C%22lastName%22%3A%22Gabriel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22A.%22%2C%22lastName%22%3A%22Jeridi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22M.%22%2C%22lastName%22%3A%22Piraud%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22T.%22%2C%22lastName%22%3A%22Stoeger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22C.a.%22%2C%22lastName%22%3A%22Staab-Weijnitz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22P.%22%2C%22lastName%22%3A%22J%5Cu00e4ger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22M.%22%2C%22lastName%22%3A%22Rehberg%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22F.%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22O.%22%2C%22lastName%22%3A%22Schmid%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22bookTitle%22%3A%22B30.%20SCARRED%20FOR%20LIFE%3A%20TRANSLATIONAL%20RESEARCH%20IN%20INTERSTITIAL%20ABNORMALITIES%20AND%20LUNG%20FIBROSIS%22%2C%22date%22%3A%222024-04-30%22%2C%22language%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.atsjournals.org%5C%2Fdoi%5C%2F10.1164%5C%2Fajrccm-conference.2024.209.1_MeetingAbstracts.A3242%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A07%3A19Z%22%7D%7D%2C%7B%22key%22%3A%22R4QKKUQH%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Yang%20et%20al.%22%2C%22parsedDate%22%3A%222024-04-29%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BYang%2C%20K.%2C%20Musio%2C%20F.%2C%20Ma%2C%20Y.%2C%20Juchler%2C%20N.%2C%20Paetzold%2C%20J.%20C.%2C%20Al-Maskari%2C%20R.%2C%20H%26%23xF6%3Bher%2C%20L.%2C%20Li%2C%20H.%20B.%2C%20Hamamci%2C%20I.%20E.%2C%20Sekuboyina%2C%20A.%2C%20Shit%2C%20S.%2C%20Huang%2C%20H.%2C%20Prabhakar%2C%20C.%2C%20Rosa%2C%20E.%20de%20la%2C%20Waldmannstetter%2C%20D.%2C%20Kofler%2C%20F.%2C%20Navarro%2C%20F.%2C%20Menten%2C%20M.%2C%20Ezhov%2C%20I.%2C%20%26%23x2026%3B%20Menze%2C%20B.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BBenchmarking%20the%20CoW%20with%20the%20TopCoW%20Challenge%3A%20Topology-Aware%20Anatomical%20Segmentation%20of%20the%20Circle%20of%20Willis%20for%20CTA%20and%20MRA%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2312.17670%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2312.17670%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2312.17670%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Benchmarking%20the%20CoW%20with%20the%20TopCoW%20Challenge%3A%20Topology-Aware%20Anatomical%20Segmentation%20of%20the%20Circle%20of%20Willis%20for%20CTA%20and%20MRA%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kaiyuan%22%2C%22lastName%22%3A%22Yang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabio%22%2C%22lastName%22%3A%22Musio%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yihui%22%2C%22lastName%22%3A%22Ma%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Norman%22%2C%22lastName%22%3A%22Juchler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Johannes%20C.%22%2C%22lastName%22%3A%22Paetzold%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rami%22%2C%22lastName%22%3A%22Al-Maskari%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Luciano%22%2C%22lastName%22%3A%22H%5Cu00f6her%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hongwei%20Bran%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ibrahim%20Ethem%22%2C%22lastName%22%3A%22Hamamci%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anjany%22%2C%22lastName%22%3A%22Sekuboyina%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suprosanna%22%2C%22lastName%22%3A%22Shit%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Houjing%22%2C%22lastName%22%3A%22Huang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chinmay%22%2C%22lastName%22%3A%22Prabhakar%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ezequiel%20de%20la%22%2C%22lastName%22%3A%22Rosa%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Diana%22%2C%22lastName%22%3A%22Waldmannstetter%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Kofler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fernando%22%2C%22lastName%22%3A%22Navarro%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Menten%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ivan%22%2C%22lastName%22%3A%22Ezhov%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%22%2C%22lastName%22%3A%22Rueckert%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Iris%22%2C%22lastName%22%3A%22Vos%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ynte%22%2C%22lastName%22%3A%22Ruigrok%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Birgitta%22%2C%22lastName%22%3A%22Velthuis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hugo%22%2C%22lastName%22%3A%22Kuijf%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Julien%22%2C%22lastName%22%3A%22H%5Cu00e4mmerli%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Catherine%22%2C%22lastName%22%3A%22Wurster%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Philippe%22%2C%22lastName%22%3A%22Bijlenga%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Laura%22%2C%22lastName%22%3A%22Westphal%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jeroen%22%2C%22lastName%22%3A%22Bisschop%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Elisa%22%2C%22lastName%22%3A%22Colombo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hakim%22%2C%22lastName%22%3A%22Baazaoui%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrew%22%2C%22lastName%22%3A%22Makmur%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22James%22%2C%22lastName%22%3A%22Hallinan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bene%22%2C%22lastName%22%3A%22Wiestler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jan%20S.%22%2C%22lastName%22%3A%22Kirschke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Roland%22%2C%22lastName%22%3A%22Wiest%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Emmanuel%22%2C%22lastName%22%3A%22Montagnon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Laurent%22%2C%22lastName%22%3A%22Letourneau-Guillon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adrian%22%2C%22lastName%22%3A%22Galdran%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Francesco%22%2C%22lastName%22%3A%22Galati%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniele%22%2C%22lastName%22%3A%22Falcetta%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maria%20A.%22%2C%22lastName%22%3A%22Zuluaga%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chaolong%22%2C%22lastName%22%3A%22Lin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Haoran%22%2C%22lastName%22%3A%22Zhao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zehan%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sinyoung%22%2C%22lastName%22%3A%22Ra%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jongyun%22%2C%22lastName%22%3A%22Hwang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hyunjin%22%2C%22lastName%22%3A%22Park%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Junqiang%22%2C%22lastName%22%3A%22Chen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marek%22%2C%22lastName%22%3A%22Wodzinski%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Henning%22%2C%22lastName%22%3A%22M%5Cu00fcller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pengcheng%22%2C%22lastName%22%3A%22Shi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Wei%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ting%22%2C%22lastName%22%3A%22Ma%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Cansu%22%2C%22lastName%22%3A%22Yal%5Cu00e7in%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rachika%20E.%22%2C%22lastName%22%3A%22Hamadache%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Joaquim%22%2C%22lastName%22%3A%22Salvi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xavier%22%2C%22lastName%22%3A%22Llado%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Uma%20Maria%20Lal-Trehan%22%2C%22lastName%22%3A%22Estrada%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Valeriia%22%2C%22lastName%22%3A%22Abramova%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Luca%22%2C%22lastName%22%3A%22Giancardo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Arnau%22%2C%22lastName%22%3A%22Oliver%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jialu%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Haibin%22%2C%22lastName%22%3A%22Huang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yue%22%2C%22lastName%22%3A%22Cui%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zehang%22%2C%22lastName%22%3A%22Lin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yusheng%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shunzhi%22%2C%22lastName%22%3A%22Zhu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tatsat%20R.%22%2C%22lastName%22%3A%22Patel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Vincent%20M.%22%2C%22lastName%22%3A%22Tutino%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maysam%22%2C%22lastName%22%3A%22Orouskhani%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Huayu%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mahmud%22%2C%22lastName%22%3A%22Mossa-Basha%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chengcheng%22%2C%22lastName%22%3A%22Zhu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%20R.%22%2C%22lastName%22%3A%22Rokuss%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yannick%22%2C%22lastName%22%3A%22Kirchhoff%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nico%22%2C%22lastName%22%3A%22Disch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Julius%22%2C%22lastName%22%3A%22Holzschuh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yuki%22%2C%22lastName%22%3A%22Sato%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sven%22%2C%22lastName%22%3A%22Hirsch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Susanne%22%2C%22lastName%22%3A%22Wegener%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bjoern%22%2C%22lastName%22%3A%22Menze%22%7D%5D%2C%22abstractNote%22%3A%22The%20Circle%20of%20Willis%20%28CoW%29%20is%20an%20important%20network%20of%20arteries%20connecting%20major%20circulations%20of%20the%20brain.%20Its%20vascular%20architecture%20is%20believed%20to%20affect%20the%20risk%2C%20severity%2C%20and%20clinical%20outcome%20of%20serious%20neuro-vascular%20diseases.%20However%2C%20characterizing%20the%20highly%20variable%20CoW%20anatomy%20is%20still%20a%20manual%20and%20time-consuming%20expert%20task.%20The%20CoW%20is%20usually%20imaged%20by%20two%20angiographic%20imaging%20modalities%2C%20magnetic%20resonance%20angiography%20%28MRA%29%20and%20computed%20tomography%20angiography%20%28CTA%29%2C%20but%20there%20exist%20limited%20public%20datasets%20with%20annotations%20on%20CoW%20anatomy%2C%20especially%20for%20CTA.%20Therefore%20we%20organized%20the%20TopCoW%20Challenge%20in%202023%20with%20the%20release%20of%20an%20annotated%20CoW%20dataset.%20The%20TopCoW%20dataset%20was%20the%20first%20public%20dataset%20with%20voxel-level%20annotations%20for%20thirteen%20possible%20CoW%20vessel%20components%2C%20enabled%20by%20virtual-reality%20%28VR%29%20technology.%20It%20was%20also%20the%20first%20large%20dataset%20with%20paired%20MRA%20and%20CTA%20from%20the%20same%20patients.%20TopCoW%20challenge%20formalized%20the%20CoW%20characterization%20problem%20as%20a%20multiclass%20anatomical%20segmentation%20task%20with%20an%20emphasis%20on%20topological%20metrics.%20We%20invited%20submissions%20worldwide%20for%20the%20CoW%20segmentation%20task%2C%20which%20attracted%20over%20140%20registered%20participants%20from%20four%20continents.%20The%20top%20performing%20teams%20managed%20to%20segment%20many%20CoW%20components%20to%20Dice%20scores%20around%2090%25%2C%20but%20with%20lower%20scores%20for%20communicating%20arteries%20and%20rare%20variants.%20There%20were%20also%20topological%20mistakes%20for%20predictions%20with%20high%20Dice%20scores.%20Additional%20topological%20analysis%20revealed%20further%20areas%20for%20improvement%20in%20detecting%20certain%20CoW%20components%20and%20matching%20CoW%20variant%20topology%20accurately.%20TopCoW%20represented%20a%20first%20attempt%20at%20benchmarking%20the%20CoW%20anatomical%20segmentation%20task%20for%20MRA%20and%20CTA%2C%20both%20morphologically%20and%20topologically.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2312.17670%22%2C%22date%22%3A%222024-04-29%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2312.17670%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2312.17670%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T11%3A59%3A00Z%22%7D%7D%2C%7B%22key%22%3A%22QGTWSLMM%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Ulrich%20et%20al.%22%2C%22parsedDate%22%3A%222024-04-24%22%2C%22numChildren%22%3A2%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BUlrich%2C%20C.%2C%20Knobloch%2C%20C.%2C%20Holzschuh%2C%20J.%20C.%2C%20Wald%2C%20T.%2C%20Rokuss%2C%20M.%20R.%2C%20Zenk%2C%20M.%2C%20Fischer%2C%20M.%2C%20Baumgartner%2C%20M.%2C%20Isensee%2C%20F.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20H.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BMitigating%20False%20Predictions%20In%20Unreasonable%20Body%20Regions%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2404.15718%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2404.15718%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2404.15718%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Mitigating%20False%20Predictions%20In%20Unreasonable%20Body%20Regions%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Catherine%22%2C%22lastName%22%3A%22Knobloch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Julius%20C.%22%2C%22lastName%22%3A%22Holzschuh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tassilo%22%2C%22lastName%22%3A%22Wald%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%20R.%22%2C%22lastName%22%3A%22Rokuss%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%22%2C%22lastName%22%3A%22Zenk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%22%2C%22lastName%22%3A%22Fischer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Baumgartner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22Despite%20considerable%20strides%20in%20developing%20deep%20learning%20models%20for%203D%20medical%20image%20segmentation%2C%20the%20challenge%20of%20effectively%20generalizing%20across%20diverse%20image%20distributions%20persists.%20While%20domain%20generalization%20is%20acknowledged%20as%20vital%20for%20robust%20application%20in%20clinical%20settings%2C%20the%20challenges%20stemming%20from%20training%20with%20a%20limited%20Field%20of%20View%20%28FOV%29%20remain%20unaddressed.%20This%20limitation%20leads%20to%20false%20predictions%20when%20applied%20to%20body%20regions%20beyond%20the%20FOV%20of%20the%20training%20data.%20In%20response%20to%20this%20problem%2C%20we%20propose%20a%20novel%20loss%20function%20that%20penalizes%20predictions%20in%20implausible%20body%20regions%2C%20applicable%20in%20both%20single-dataset%20and%20multi-dataset%20training%20schemes.%20It%20is%20realized%20with%20a%20Body%20Part%20Regression%20model%20that%20generates%20axial%20slice%20positional%20scores.%20Through%20comprehensive%20evaluation%20using%20a%20test%20set%20featuring%20varying%20FOVs%2C%20our%20approach%20demonstrates%20remarkable%20improvements%20in%20generalization%20capabilities.%20It%20effectively%20mitigates%20false%20positive%20tumor%20predictions%20up%20to%2085%25%20and%20significantly%20enhances%20overall%20segmentation%20performance.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2404.15718%22%2C%22date%22%3A%222024-04-24%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2404.15718%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2404.15718%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A38%3A30Z%22%7D%7D%2C%7B%22key%22%3A%22BK5Y7FRV%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Gutsche%20et%20al.%22%2C%22parsedDate%22%3A%222024-04%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGutsche%2C%20R.%2C%20Lowis%2C%20C.%2C%20Ziemons%2C%20K.%2C%20Kocher%2C%20M.%2C%20Ceccon%2C%20G.%2C%20Brambilla%2C%20C.%20R.%2C%20Shah%2C%20N.%20J.%2C%20Langen%2C%20K.%2C%20Galldiks%2C%20N.%2C%20Isensee%2C%20F.%2C%20%26amp%3B%20Lohmann%2C%20P.%20%282024%29.%20%26lt%3Bb%26gt%3BDeep%20learning-based%20amino%20acid%20PET%20brain%20tumor%20segmentation%20for%20automated%20response%20assessment%20in%20patients%20with%20brain%20tumors%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BNuklearmedizin%20-%20NuclearMedicine%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B63%26lt%3B%5C%2Fi%26gt%3B%2C%20L53.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1055%5C%2Fs-0044-1782321%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1055%5C%2Fs-0044-1782321%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Deep%20learning-based%20amino%20acid%20PET%20brain%20tumor%20segmentation%20for%20automated%20response%20assessment%20in%20patients%20with%20brain%20tumors%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22R.%22%2C%22lastName%22%3A%22Gutsche%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22C.%22%2C%22lastName%22%3A%22Lowis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22K.%22%2C%22lastName%22%3A%22Ziemons%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22M.%22%2C%22lastName%22%3A%22Kocher%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22G.%22%2C%22lastName%22%3A%22Ceccon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22C.%20R%5Cu00e9gio%22%2C%22lastName%22%3A%22Brambilla%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22N.%20J.%22%2C%22lastName%22%3A%22Shah%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22K.%22%2C%22lastName%22%3A%22Langen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22N.%22%2C%22lastName%22%3A%22Galldiks%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22F.%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22P.%22%2C%22lastName%22%3A%22Lohmann%22%7D%5D%2C%22abstractNote%22%3A%22Thieme%20E-Books%20%26amp%3B%20E-Journals%22%2C%22date%22%3A%222024%5C%2F04%22%2C%22proceedingsTitle%22%3A%22Nuklearmedizin%20-%20NuclearMedicine%22%2C%22conferenceName%22%3A%2262.%20Jahrestagung%20der%20Deutschen%20Gesellschaft%20f%5Cu00fcr%20Nuklearmedizin%22%2C%22language%22%3A%22de%22%2C%22DOI%22%3A%2210.1055%5C%2Fs-0044-1782321%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fwww.thieme-connect.de%5C%2FDOI%5C%2FDOI%3F10.1055%5C%2Fs-0044-1782321%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A09%3A28Z%22%7D%7D%2C%7B%22key%22%3A%225B4AA934%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Gotkowski%20et%20al.%22%2C%22parsedDate%22%3A%222024-03-19%22%2C%22numChildren%22%3A2%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGotkowski%2C%20K.%2C%20L%26%23xFC%3Bth%2C%20C.%2C%20J%26%23xE4%3Bger%2C%20P.%20F.%2C%20Ziegler%2C%20S.%2C%20Kr%26%23xE4%3Bmer%2C%20L.%2C%20Denner%2C%20S.%2C%20Xiao%2C%20S.%2C%20Disch%2C%20N.%2C%20Maier-Hein%2C%20K.%20H.%2C%20%26amp%3B%20Isensee%2C%20F.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BEmbarrassingly%20Simple%20Scribble%20Supervision%20for%203D%20Medical%20Segmentation%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2403.12834%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2403.12834%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2403.12834%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Embarrassingly%20Simple%20Scribble%20Supervision%20for%203D%20Medical%20Segmentation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karol%22%2C%22lastName%22%3A%22Gotkowski%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Carsten%22%2C%22lastName%22%3A%22L%5Cu00fcth%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%20F.%22%2C%22lastName%22%3A%22J%5Cu00e4ger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sebastian%22%2C%22lastName%22%3A%22Ziegler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Kr%5Cu00e4mer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Stefan%22%2C%22lastName%22%3A%22Denner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shuhan%22%2C%22lastName%22%3A%22Xiao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nico%22%2C%22lastName%22%3A%22Disch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%5D%2C%22abstractNote%22%3A%22Traditionally%2C%20segmentation%20algorithms%20require%20dense%20annotations%20for%20training%2C%20demanding%20significant%20annotation%20efforts%2C%20particularly%20within%20the%203D%20medical%20imaging%20field.%20Scribble-supervised%20learning%20emerges%20as%20a%20possible%20solution%20to%20this%20challenge%2C%20promising%20a%20reduction%20in%20annotation%20efforts%20when%20creating%20large-scale%20datasets.%20Recently%2C%20a%20plethora%20of%20methods%20for%20optimized%20learning%20from%20scribbles%20have%20been%20proposed%2C%20but%20have%20so%20far%20failed%20to%20position%20scribble%20annotation%20as%20a%20beneficial%20alternative.%20We%20relate%20this%20shortcoming%20to%20two%20major%20issues%3A%201%29%20the%20complex%20nature%20of%20many%20methods%20which%20deeply%20ties%20them%20to%20the%20underlying%20segmentation%20model%2C%20thus%20preventing%20a%20migration%20to%20more%20powerful%20state-of-the-art%20models%20as%20the%20field%20progresses%20and%202%29%20the%20lack%20of%20a%20systematic%20evaluation%20to%20validate%20consistent%20performance%20across%20the%20broader%20medical%20domain%2C%20resulting%20in%20a%20lack%20of%20trust%20when%20applying%20these%20methods%20to%20new%20segmentation%20problems.%20To%20address%20these%20issues%2C%20we%20propose%20a%20comprehensive%20scribble%20supervision%20benchmark%20consisting%20of%20seven%20datasets%20covering%20a%20diverse%20set%20of%20anatomies%20and%20pathologies%20imaged%20with%20varying%20modalities.%20We%20furthermore%20propose%20the%20systematic%20use%20of%20partial%20losses%2C%20i.e.%20losses%20that%20are%20only%20computed%20on%20annotated%20voxels.%20Contrary%20to%20most%20existing%20methods%2C%20these%20losses%20can%20be%20seamlessly%20integrated%20into%20state-of-the-art%20segmentation%20methods%2C%20enabling%20them%20to%20learn%20from%20scribble%20annotations%20while%20preserving%20their%20original%20loss%20formulations.%20Our%20evaluation%20using%20nnU-Net%20reveals%20that%20while%20most%20existing%20methods%20suffer%20from%20a%20lack%20of%20generalization%2C%20the%20proposed%20approach%20consistently%20delivers%20state-of-the-art%20performance.%20Thanks%20to%20its%20simplicity%2C%20our%20approach%20presents%20an%20embarrassingly%20simple%20yet%20effective%20solution%20to%20the%20challenges%20of%20scribble%20supervision.%20Source%20code%20as%20well%20as%20our%20extensive%20scribble%20benchmarking%20suite%20will%20be%20made%20publicly%20available%20upon%20publication.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2403.12834%22%2C%22date%22%3A%222024-03-19%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2403.12834%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2403.12834%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A25%3A39Z%22%7D%7D%2C%7B%22key%22%3A%225ZQ8WVJ8%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Reinke%20et%20al.%22%2C%22parsedDate%22%3A%222024-02-12%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BReinke%2C%20A.%2C%20Tizabi%2C%20M.%20D.%2C%20Baumgartner%2C%20M.%2C%20Eisenmann%2C%20M.%2C%20Heckmann-N%26%23xF6%3Btzel%2C%20D.%2C%20Kavur%2C%20A.%20E.%2C%20R%26%23xE4%3Bdsch%2C%20T.%2C%20Sudre%2C%20C.%20H.%2C%20Acion%2C%20L.%2C%20Antonelli%2C%20M.%2C%20Arbel%2C%20T.%2C%20Bakas%2C%20S.%2C%20Benis%2C%20A.%2C%20Buettner%2C%20F.%2C%20Cardoso%2C%20M.%20J.%2C%20Cheplygina%2C%20V.%2C%20Chen%2C%20J.%2C%20Christodoulou%2C%20E.%2C%20Cimini%2C%20B.%20A.%2C%20%26%23x2026%3B%20Maier-Hein%2C%20L.%20%282024%29.%20%26lt%3Bb%26gt%3BUnderstanding%20metric-related%20pitfalls%20in%20image%20analysis%20validation%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BNature%20Methods%26lt%3B%5C%2Fi%26gt%3B%2C%201%26%23x2013%3B13.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1038%5C%2Fs41592-023-02150-0%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1038%5C%2Fs41592-023-02150-0%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Understanding%20metric-related%20pitfalls%20in%20image%20analysis%20validation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Annika%22%2C%22lastName%22%3A%22Reinke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Minu%20D.%22%2C%22lastName%22%3A%22Tizabi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Baumgartner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Matthias%22%2C%22lastName%22%3A%22Eisenmann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Doreen%22%2C%22lastName%22%3A%22Heckmann-N%5Cu00f6tzel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22A.%20Emre%22%2C%22lastName%22%3A%22Kavur%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tim%22%2C%22lastName%22%3A%22R%5Cu00e4dsch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Carole%20H.%22%2C%22lastName%22%3A%22Sudre%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Laura%22%2C%22lastName%22%3A%22Acion%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michela%22%2C%22lastName%22%3A%22Antonelli%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tal%22%2C%22lastName%22%3A%22Arbel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Spyridon%22%2C%22lastName%22%3A%22Bakas%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Arriel%22%2C%22lastName%22%3A%22Benis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Buettner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22M.%20Jorge%22%2C%22lastName%22%3A%22Cardoso%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Veronika%22%2C%22lastName%22%3A%22Cheplygina%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jianxu%22%2C%22lastName%22%3A%22Chen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Evangelia%22%2C%22lastName%22%3A%22Christodoulou%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Beth%20A.%22%2C%22lastName%22%3A%22Cimini%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Keyvan%22%2C%22lastName%22%3A%22Farahani%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Luciana%22%2C%22lastName%22%3A%22Ferrer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adrian%22%2C%22lastName%22%3A%22Galdran%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bram%22%2C%22lastName%22%3A%22van%20Ginneken%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ben%22%2C%22lastName%22%3A%22Glocker%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Patrick%22%2C%22lastName%22%3A%22Godau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%20A.%22%2C%22lastName%22%3A%22Hashimoto%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%20M.%22%2C%22lastName%22%3A%22Hoffman%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Merel%22%2C%22lastName%22%3A%22Huisman%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pierre%22%2C%22lastName%22%3A%22Jannin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Charles%20E.%22%2C%22lastName%22%3A%22Kahn%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dagmar%22%2C%22lastName%22%3A%22Kainmueller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bernhard%22%2C%22lastName%22%3A%22Kainz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alexandros%22%2C%22lastName%22%3A%22Karargyris%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jens%22%2C%22lastName%22%3A%22Kleesiek%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Kofler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Thijs%22%2C%22lastName%22%3A%22Kooi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Annette%22%2C%22lastName%22%3A%22Kopp-Schneider%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michal%22%2C%22lastName%22%3A%22Kozubek%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anna%22%2C%22lastName%22%3A%22Kreshuk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tahsin%22%2C%22lastName%22%3A%22Kurc%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bennett%20A.%22%2C%22lastName%22%3A%22Landman%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Geert%22%2C%22lastName%22%3A%22Litjens%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Amin%22%2C%22lastName%22%3A%22Madani%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anne%20L.%22%2C%22lastName%22%3A%22Martel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Erik%22%2C%22lastName%22%3A%22Meijering%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bjoern%22%2C%22lastName%22%3A%22Menze%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karel%20G.%20M.%22%2C%22lastName%22%3A%22Moons%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Henning%22%2C%22lastName%22%3A%22M%5Cu00fcller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Brennan%22%2C%22lastName%22%3A%22Nichyporuk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Felix%22%2C%22lastName%22%3A%22Nickel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jens%22%2C%22lastName%22%3A%22Petersen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Susanne%20M.%22%2C%22lastName%22%3A%22Rafelski%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nasir%22%2C%22lastName%22%3A%22Rajpoot%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mauricio%22%2C%22lastName%22%3A%22Reyes%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%20A.%22%2C%22lastName%22%3A%22Riegler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nicola%22%2C%22lastName%22%3A%22Rieke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Julio%22%2C%22lastName%22%3A%22Saez-Rodriguez%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Clara%20I.%22%2C%22lastName%22%3A%22S%5Cu00e1nchez%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shravya%22%2C%22lastName%22%3A%22Shetty%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ronald%20M.%22%2C%22lastName%22%3A%22Summers%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Abdel%20A.%22%2C%22lastName%22%3A%22Taha%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Aleksei%22%2C%22lastName%22%3A%22Tiulpin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sotirios%20A.%22%2C%22lastName%22%3A%22Tsaftaris%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ben%22%2C%22lastName%22%3A%22Van%20Calster%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ga%5Cu00ebl%22%2C%22lastName%22%3A%22Varoquaux%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ziv%20R.%22%2C%22lastName%22%3A%22Yaniv%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%20F.%22%2C%22lastName%22%3A%22J%5Cu00e4ger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lena%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22Validation%20metrics%20are%20key%20for%20tracking%20scientific%20progress%20and%20bridging%20the%20current%20chasm%20between%20artificial%20intelligence%20research%20and%20its%20translation%20into%20practice.%20However%2C%20increasing%20evidence%20shows%20that%2C%20particularly%20in%20image%20analysis%2C%20metrics%20are%20often%20chosen%20inadequately.%20Although%20taking%20into%20account%20the%20individual%20strengths%2C%20weaknesses%20and%20limitations%20of%20validation%20metrics%20is%20a%20critical%20prerequisite%20to%20making%20educated%20choices%2C%20the%20relevant%20knowledge%20is%20currently%20scattered%20and%20poorly%20accessible%20to%20individual%20researchers.%20Based%20on%20a%20multistage%20Delphi%20process%20conducted%20by%20a%20multidisciplinary%20expert%20consortium%20as%20well%20as%20extensive%20community%20feedback%2C%20the%20present%20work%20provides%20a%20reliable%20and%20comprehensive%20common%20point%20of%20access%20to%20information%20on%20pitfalls%20related%20to%20validation%20metrics%20in%20image%20analysis.%20Although%20focused%20on%20biomedical%20image%20analysis%2C%20the%20addressed%20pitfalls%20generalize%20across%20application%20domains%20and%20are%20categorized%20according%20to%20a%20newly%20created%2C%20domain-agnostic%20taxonomy.%20The%20work%20serves%20to%20enhance%20global%20comprehension%20of%20a%20key%20topic%20in%20image%20analysis%20validation.%22%2C%22date%22%3A%222024-02-12%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1038%5C%2Fs41592-023-02150-0%22%2C%22ISSN%22%3A%221548-7105%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.nature.com%5C%2Farticles%5C%2Fs41592-023-02150-0%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T08%3A36%3A30Z%22%7D%7D%2C%7B%22key%22%3A%22CAUD4GCC%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Maier-Hein%20et%20al.%22%2C%22parsedDate%22%3A%222024-02%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BMaier-Hein%2C%20L.%2C%20Reinke%2C%20A.%2C%20Godau%2C%20P.%2C%20Tizabi%2C%20M.%20D.%2C%20Buettner%2C%20F.%2C%20Christodoulou%2C%20E.%2C%20Glocker%2C%20B.%2C%20Isensee%2C%20F.%2C%20Kleesiek%2C%20J.%2C%20Kozubek%2C%20M.%2C%20Reyes%2C%20M.%2C%20Riegler%2C%20M.%20A.%2C%20Wiesenfarth%2C%20M.%2C%20Kavur%2C%20A.%20E.%2C%20Sudre%2C%20C.%20H.%2C%20Baumgartner%2C%20M.%2C%20Eisenmann%2C%20M.%2C%20Heckmann-N%26%23xF6%3Btzel%2C%20D.%2C%20R%26%23xE4%3Bdsch%2C%20T.%2C%20%26%23x2026%3B%20J%26%23xE4%3Bger%2C%20P.%20F.%20%282024%29.%20%26lt%3Bb%26gt%3BMetrics%20reloaded%3A%20recommendations%20for%20image%20analysis%20validation%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BNature%20Methods%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B21%26lt%3B%5C%2Fi%26gt%3B%282%29%2C%20195%26%23x2013%3B212.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1038%5C%2Fs41592-023-02151-z%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1038%5C%2Fs41592-023-02151-z%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Metrics%20reloaded%3A%20recommendations%20for%20image%20analysis%20validation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lena%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Annika%22%2C%22lastName%22%3A%22Reinke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Patrick%22%2C%22lastName%22%3A%22Godau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Minu%20D.%22%2C%22lastName%22%3A%22Tizabi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Buettner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Evangelia%22%2C%22lastName%22%3A%22Christodoulou%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ben%22%2C%22lastName%22%3A%22Glocker%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jens%22%2C%22lastName%22%3A%22Kleesiek%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michal%22%2C%22lastName%22%3A%22Kozubek%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mauricio%22%2C%22lastName%22%3A%22Reyes%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%20A.%22%2C%22lastName%22%3A%22Riegler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Manuel%22%2C%22lastName%22%3A%22Wiesenfarth%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22A.%20Emre%22%2C%22lastName%22%3A%22Kavur%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Carole%20H.%22%2C%22lastName%22%3A%22Sudre%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Baumgartner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Matthias%22%2C%22lastName%22%3A%22Eisenmann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Doreen%22%2C%22lastName%22%3A%22Heckmann-N%5Cu00f6tzel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tim%22%2C%22lastName%22%3A%22R%5Cu00e4dsch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Laura%22%2C%22lastName%22%3A%22Acion%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michela%22%2C%22lastName%22%3A%22Antonelli%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tal%22%2C%22lastName%22%3A%22Arbel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Spyridon%22%2C%22lastName%22%3A%22Bakas%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Arriel%22%2C%22lastName%22%3A%22Benis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Matthew%20B.%22%2C%22lastName%22%3A%22Blaschko%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22M.%20Jorge%22%2C%22lastName%22%3A%22Cardoso%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Veronika%22%2C%22lastName%22%3A%22Cheplygina%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Beth%20A.%22%2C%22lastName%22%3A%22Cimini%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gary%20S.%22%2C%22lastName%22%3A%22Collins%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Keyvan%22%2C%22lastName%22%3A%22Farahani%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Luciana%22%2C%22lastName%22%3A%22Ferrer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adrian%22%2C%22lastName%22%3A%22Galdran%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bram%22%2C%22lastName%22%3A%22van%20Ginneken%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Robert%22%2C%22lastName%22%3A%22Haase%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%20A.%22%2C%22lastName%22%3A%22Hashimoto%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%20M.%22%2C%22lastName%22%3A%22Hoffman%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Merel%22%2C%22lastName%22%3A%22Huisman%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pierre%22%2C%22lastName%22%3A%22Jannin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Charles%20E.%22%2C%22lastName%22%3A%22Kahn%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dagmar%22%2C%22lastName%22%3A%22Kainmueller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bernhard%22%2C%22lastName%22%3A%22Kainz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alexandros%22%2C%22lastName%22%3A%22Karargyris%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alan%22%2C%22lastName%22%3A%22Karthikesalingam%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Kofler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Annette%22%2C%22lastName%22%3A%22Kopp-Schneider%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anna%22%2C%22lastName%22%3A%22Kreshuk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tahsin%22%2C%22lastName%22%3A%22Kurc%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bennett%20A.%22%2C%22lastName%22%3A%22Landman%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Geert%22%2C%22lastName%22%3A%22Litjens%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Amin%22%2C%22lastName%22%3A%22Madani%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anne%20L.%22%2C%22lastName%22%3A%22Martel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Peter%22%2C%22lastName%22%3A%22Mattson%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Erik%22%2C%22lastName%22%3A%22Meijering%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bjoern%22%2C%22lastName%22%3A%22Menze%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karel%20G.%20M.%22%2C%22lastName%22%3A%22Moons%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Henning%22%2C%22lastName%22%3A%22M%5Cu00fcller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Brennan%22%2C%22lastName%22%3A%22Nichyporuk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Felix%22%2C%22lastName%22%3A%22Nickel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jens%22%2C%22lastName%22%3A%22Petersen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nasir%22%2C%22lastName%22%3A%22Rajpoot%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nicola%22%2C%22lastName%22%3A%22Rieke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Julio%22%2C%22lastName%22%3A%22Saez-Rodriguez%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Clara%20I.%22%2C%22lastName%22%3A%22S%5Cu00e1nchez%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shravya%22%2C%22lastName%22%3A%22Shetty%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maarten%22%2C%22lastName%22%3A%22van%20Smeden%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ronald%20M.%22%2C%22lastName%22%3A%22Summers%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Abdel%20A.%22%2C%22lastName%22%3A%22Taha%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Aleksei%22%2C%22lastName%22%3A%22Tiulpin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sotirios%20A.%22%2C%22lastName%22%3A%22Tsaftaris%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ben%22%2C%22lastName%22%3A%22Van%20Calster%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ga%5Cu00ebl%22%2C%22lastName%22%3A%22Varoquaux%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%20F.%22%2C%22lastName%22%3A%22J%5Cu00e4ger%22%7D%5D%2C%22abstractNote%22%3A%22Increasing%20evidence%20shows%20that%20flaws%20in%20machine%20learning%20%28ML%29%20algorithm%20validation%20are%20an%20underestimated%20global%20problem.%20In%20biomedical%20image%20analysis%2C%20chosen%20performance%20metrics%20often%20do%20not%20reflect%20the%20domain%20interest%2C%20and%20thus%20fail%20to%20adequately%20measure%20scientific%20progress%20and%20hinder%20translation%20of%20ML%20techniques%20into%20practice.%20To%20overcome%20this%2C%20we%20created%20Metrics%20Reloaded%2C%20a%20comprehensive%20framework%20guiding%20researchers%20in%20the%20problem-aware%20selection%20of%20metrics.%20Developed%20by%20a%20large%20international%20consortium%20in%20a%20multistage%20Delphi%20process%2C%20it%20is%20based%20on%20the%20novel%20concept%20of%20a%20problem%20fingerprint%5Cu2014a%20structured%20representation%20of%20the%20given%20problem%20that%20captures%20all%20aspects%20that%20are%20relevant%20for%20metric%20selection%2C%20from%20the%20domain%20interest%20to%20the%20properties%20of%20the%20target%20structure%28s%29%2C%20dataset%20and%20algorithm%20output.%20On%20the%20basis%20of%20the%20problem%20fingerprint%2C%20users%20are%20guided%20through%20the%20process%20of%20choosing%20and%20applying%20appropriate%20validation%20metrics%20while%20being%20made%20aware%20of%20potential%20pitfalls.%20Metrics%20Reloaded%20targets%20image%20analysis%20problems%20that%20can%20be%20interpreted%20as%20classification%20tasks%20at%20image%2C%20object%20or%20pixel%20level%2C%20namely%20image-level%20classification%2C%20object%20detection%2C%20semantic%20segmentation%20and%20instance%20segmentation%20tasks.%20To%20improve%20the%20user%20experience%2C%20we%20implemented%20the%20framework%20in%20the%20Metrics%20Reloaded%20online%20tool.%20Following%20the%20convergence%20of%20ML%20methodology%20across%20application%20domains%2C%20Metrics%20Reloaded%20fosters%20the%20convergence%20of%20validation%20methodology.%20Its%20applicability%20is%20demonstrated%20for%20various%20biomedical%20use%20cases.%22%2C%22date%22%3A%222024-02%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1038%5C%2Fs41592-023-02151-z%22%2C%22ISSN%22%3A%221548-7105%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.nature.com%5C%2Farticles%5C%2Fs41592-023-02151-z%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T08%3A34%3A55Z%22%7D%7D%2C%7B%22key%22%3A%22A9H8X2LP%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Yang%20et%20al.%22%2C%22parsedDate%22%3A%222024-01-18%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BYang%2C%20K.%2C%20Musio%2C%20F.%2C%20Ma%2C%20Y.%2C%20Juchler%2C%20N.%2C%20Paetzold%2C%20J.%20C.%2C%20Al-Maskari%2C%20R.%2C%20H%26%23xF6%3Bher%2C%20L.%2C%20Li%2C%20H.%20B.%2C%20Hamamci%2C%20I.%20E.%2C%20Sekuboyina%2C%20A.%2C%20Shit%2C%20S.%2C%20Huang%2C%20H.%2C%20Waldmannstetter%2C%20D.%2C%20Kofler%2C%20F.%2C%20Navarro%2C%20F.%2C%20Menten%2C%20M.%2C%20Ezhov%2C%20I.%2C%20Rueckert%2C%20D.%2C%20Vos%2C%20I.%2C%20%26%23x2026%3B%20Menze%2C%20B.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BTopCoW%3A%20Benchmarking%20Topology-Aware%20Anatomical%20Segmentation%20of%20the%20Circle%20of%20Willis%20%28CoW%29%20for%20CTA%20and%20MRA%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2312.17670%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2312.17670%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2312.17670%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22TopCoW%3A%20Benchmarking%20Topology-Aware%20Anatomical%20Segmentation%20of%20the%20Circle%20of%20Willis%20%28CoW%29%20for%20CTA%20and%20MRA%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kaiyuan%22%2C%22lastName%22%3A%22Yang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabio%22%2C%22lastName%22%3A%22Musio%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yihui%22%2C%22lastName%22%3A%22Ma%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Norman%22%2C%22lastName%22%3A%22Juchler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Johannes%20C.%22%2C%22lastName%22%3A%22Paetzold%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rami%22%2C%22lastName%22%3A%22Al-Maskari%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Luciano%22%2C%22lastName%22%3A%22H%5Cu00f6her%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hongwei%20Bran%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ibrahim%20Ethem%22%2C%22lastName%22%3A%22Hamamci%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anjany%22%2C%22lastName%22%3A%22Sekuboyina%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suprosanna%22%2C%22lastName%22%3A%22Shit%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Houjing%22%2C%22lastName%22%3A%22Huang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Diana%22%2C%22lastName%22%3A%22Waldmannstetter%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Kofler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fernando%22%2C%22lastName%22%3A%22Navarro%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Menten%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ivan%22%2C%22lastName%22%3A%22Ezhov%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%22%2C%22lastName%22%3A%22Rueckert%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Iris%22%2C%22lastName%22%3A%22Vos%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ynte%22%2C%22lastName%22%3A%22Ruigrok%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Birgitta%22%2C%22lastName%22%3A%22Velthuis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hugo%22%2C%22lastName%22%3A%22Kuijf%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Julien%22%2C%22lastName%22%3A%22H%5Cu00e4mmerli%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Catherine%22%2C%22lastName%22%3A%22Wurster%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Philippe%22%2C%22lastName%22%3A%22Bijlenga%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Laura%22%2C%22lastName%22%3A%22Westphal%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jeroen%22%2C%22lastName%22%3A%22Bisschop%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Elisa%22%2C%22lastName%22%3A%22Colombo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hakim%22%2C%22lastName%22%3A%22Baazaoui%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrew%22%2C%22lastName%22%3A%22Makmur%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22James%22%2C%22lastName%22%3A%22Hallinan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bene%22%2C%22lastName%22%3A%22Wiestler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jan%20S.%22%2C%22lastName%22%3A%22Kirschke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Roland%22%2C%22lastName%22%3A%22Wiest%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Emmanuel%22%2C%22lastName%22%3A%22Montagnon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Laurent%22%2C%22lastName%22%3A%22Letourneau-Guillon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adrian%22%2C%22lastName%22%3A%22Galdran%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Francesco%22%2C%22lastName%22%3A%22Galati%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniele%22%2C%22lastName%22%3A%22Falcetta%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maria%20A.%22%2C%22lastName%22%3A%22Zuluaga%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chaolong%22%2C%22lastName%22%3A%22Lin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Haoran%22%2C%22lastName%22%3A%22Zhao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zehan%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sinyoung%22%2C%22lastName%22%3A%22Ra%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jongyun%22%2C%22lastName%22%3A%22Hwang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hyunjin%22%2C%22lastName%22%3A%22Park%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Junqiang%22%2C%22lastName%22%3A%22Chen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marek%22%2C%22lastName%22%3A%22Wodzinski%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Henning%22%2C%22lastName%22%3A%22M%5Cu00fcller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pengcheng%22%2C%22lastName%22%3A%22Shi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Wei%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ting%22%2C%22lastName%22%3A%22Ma%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Cansu%22%2C%22lastName%22%3A%22Yal%5Cu00e7in%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rachika%20E.%22%2C%22lastName%22%3A%22Hamadache%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Joaquim%22%2C%22lastName%22%3A%22Salvi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xavier%22%2C%22lastName%22%3A%22Llado%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Uma%20Maria%20Lal-Trehan%22%2C%22lastName%22%3A%22Estrada%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Valeriia%22%2C%22lastName%22%3A%22Abramova%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Luca%22%2C%22lastName%22%3A%22Giancardo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Arnau%22%2C%22lastName%22%3A%22Oliver%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jialu%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Haibin%22%2C%22lastName%22%3A%22Huang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yue%22%2C%22lastName%22%3A%22Cui%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zehang%22%2C%22lastName%22%3A%22Lin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yusheng%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shunzhi%22%2C%22lastName%22%3A%22Zhu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tatsat%20R.%22%2C%22lastName%22%3A%22Patel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Vincent%20M.%22%2C%22lastName%22%3A%22Tutino%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maysam%22%2C%22lastName%22%3A%22Orouskhani%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Huayu%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mahmud%22%2C%22lastName%22%3A%22Mossa-Basha%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chengcheng%22%2C%22lastName%22%3A%22Zhu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%20R.%22%2C%22lastName%22%3A%22Rokuss%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yannick%22%2C%22lastName%22%3A%22Kirchhoff%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nico%22%2C%22lastName%22%3A%22Disch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Julius%22%2C%22lastName%22%3A%22Holzschuh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yuki%22%2C%22lastName%22%3A%22Sato%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sven%22%2C%22lastName%22%3A%22Hirsch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Susanne%22%2C%22lastName%22%3A%22Wegener%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bjoern%22%2C%22lastName%22%3A%22Menze%22%7D%5D%2C%22abstractNote%22%3A%22The%20Circle%20of%20Willis%20%28CoW%29%20is%20an%20important%20network%20of%20arteries%20connecting%20major%20circulations%20of%20the%20brain.%20Its%20vascular%20architecture%20is%20believed%20to%20affect%20the%20risk%2C%20severity%2C%20and%20clinical%20outcome%20of%20serious%20neuro-vascular%20diseases.%20However%2C%20characterizing%20the%20highly%20variable%20CoW%20anatomy%20is%20still%20a%20manual%20and%20time-consuming%20expert%20task.%20The%20CoW%20is%20usually%20imaged%20by%20two%20angiographic%20imaging%20modalities%2C%20magnetic%20resonance%20angiography%20%28MRA%29%20and%20computed%20tomography%20angiography%20%28CTA%29%2C%20but%20there%20exist%20limited%20public%20datasets%20with%20annotations%20on%20CoW%20anatomy%2C%20especially%20for%20CTA.%20Therefore%20we%20organized%20the%20TopCoW%20Challenge%20in%202023%20with%20the%20release%20of%20an%20annotated%20CoW%20dataset.%20The%20TopCoW%20dataset%20was%20the%20first%20public%20dataset%20with%20voxel-level%20annotations%20for%20thirteen%20possible%20CoW%20vessel%20components%2C%20enabled%20by%20virtual-reality%20%28VR%29%20technology.%20It%20was%20also%20the%20first%20large%20dataset%20with%20paired%20MRA%20and%20CTA%20from%20the%20same%20patients.%20TopCoW%20challenge%20formalized%20the%20CoW%20characterization%20problem%20as%20a%20multiclass%20anatomical%20segmentation%20task%20with%20an%20emphasis%20on%20topological%20metrics.%20We%20invited%20submissions%20worldwide%20for%20the%20CoW%20segmentation%20task%2C%20which%20attracted%20over%20140%20registered%20participants%20from%20four%20continents.%20The%20top%20performing%20teams%20managed%20to%20segment%20many%20CoW%20components%20to%20Dice%20scores%20around%2090%25%2C%20but%20with%20lower%20scores%20for%20communicating%20arteries%20and%20rare%20variants.%20There%20were%20also%20topological%20mistakes%20for%20predictions%20with%20high%20Dice%20scores.%20Additional%20topological%20analysis%20revealed%20further%20areas%20for%20improvement%20in%20detecting%20certain%20CoW%20components%20and%20matching%20CoW%20variant%20topology%20accurately.%20TopCoW%20represented%20a%20first%20attempt%20at%20benchmarking%20the%20CoW%20anatomical%20segmentation%20task%20for%20MRA%20and%20CTA%2C%20both%20morphologically%20and%20topologically.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2312.17670%22%2C%22date%22%3A%222024-01-18%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2312.17670%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2312.17670%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-02-15T10%3A30%3A42Z%22%7D%7D%2C%7B%22key%22%3A%22GYCLTYZ6%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Gupta%20et%20al.%22%2C%22parsedDate%22%3A%222024-01-15%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGupta%2C%20S.%2C%20da%20Assuncao%20Godinho%2C%20J.%20R.%2C%20Gotkowski%2C%20K.%2C%20%26amp%3B%20Isensee%2C%20F.%20%282024%29.%20%26lt%3Bb%26gt%3BStandardized%20and%20semiautomated%20workflow%20for%203D%20characterization%20of%20liberated%20particles%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BPowder%20Technology%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B433%26lt%3B%5C%2Fi%26gt%3B%2C%20119159.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.powtec.2023.119159%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.powtec.2023.119159%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Standardized%20and%20semiautomated%20workflow%20for%203D%20characterization%20of%20liberated%20particles%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shuvam%22%2C%22lastName%22%3A%22Gupta%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jose%20Ricardo%22%2C%22lastName%22%3A%22da%20Assuncao%20Godinho%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karol%22%2C%22lastName%22%3A%22Gotkowski%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%5D%2C%22abstractNote%22%3A%22MSPaCMAn%20is%20the%20recently%20developed%20workflow%20that%20does%20the%20mineralogical%20quantification%20of%20individual%20particles%20using%20its%20histograms%20while%20considering%20the%20effects%20of%20partial%20volume%20artefacts%20in%20interphases%20at%20particle%20level%20detail.%20This%20paper%20demonstrates%20and%20validates%20the%20new%20developments%20in%20the%20MSPaCMAn%20workflow%2C%20aiming%20to%20minimize%20user%20bias%20and%20enhance%20the%20accuracy%20of%20MSPaCMAn.%20Here%2C%20in%20the%20new%20developments%20of%20MSPaCMAn%20workflow%2C%20firstly%2C%20the%20recently%20developed%20deep%20learning%20method%2C%20namely%20ParticleSeg3D%2C%20is%20employed%20to%20distinguish%20particles%20from%20the%20background.%20Secondly%2C%20the%20particle%26%23039%3Bs%20size%20and%20shape%20information%20are%20considered%20along%20with%20its%20histogram%20to%20classify%20and%20quantify%20the%20mineral%20phases%20in%20liberated%20particles.%20After%20the%20new%20developments%2C%20the%20detection%20limit%20of%20MSPaCMAn%20to%20characterize%20small%20and%20thin%20liberated%20particles%20is%20enhanced.%20Experimental%20results%20demonstrate%20the%20effectiveness%20of%20the%20MSPaCMAn%26%23039%3Bs%20updated%20workflow.%20It%20was%20found%20that%20the%20mineralogical%20composition%20calculated%20by%20the%20MSPaCMAn%26%23039%3Bs%20updated%20workflow%20was%20precise%2C%20with%20the%20highest%20coefficient%20of%20variance%20of%206.56%25.%20Moreover%2C%20the%20mineralogical%20composition%20determined%20by%20MSPaCMAn%26%23039%3Bs%20updated%20workflow%20had%20low%20variance%20across%20three%20different%20reconstruction%20parameters%20and%20two%20different%20voxel%20sizes%20%285.5%5Cu00a0%5Cu03bcm%20and%2010%5Cu00a0%5Cu03bcm%29.%20Comparisons%20with%20other%20quantification%20methods%20highlight%20the%20accuracy%20of%20MSPaCMAn%26%23039%3Bs%20updated%20workflow%20to%20determine%20the%20mineralogical%20compositions.%20When%20analyzing%20a%20test%20sample%20consisting%20of%20quartz%2C%20calcite%2C%20fluorite%2C%20and%20lepidolite%2C%20MSPaCMAn%26%23039%3Bs%20updated%20workflow%20achieved%20the%20highest%20mineralogical%20deviation%20of%20only%207.73%25%20from%20the%20reference%20mineralogy.%20In%20contrast%2C%20the%20random%20forest%20algorithm%20resulted%20in%20a%20deviation%20of%2051.47%25%2C%20while%20the%20manual%20thresholding%20method%20yielded%20a%20deviation%20of%2041.46%25.%20Overall%2C%20these%20findings%20emphasize%20the%20reliability%20and%20accuracy%20of%20MSPaCMAn%26%23039%3Bs%20updated%20workflow%20in%20quantifying%20mineralogical%20composition.%22%2C%22date%22%3A%222024-01-15%22%2C%22language%22%3A%22%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.powtec.2023.119159%22%2C%22ISSN%22%3A%220032-5910%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.sciencedirect.com%5C%2Fscience%5C%2Farticle%5C%2Fpii%5C%2FS0032591023009427%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-11-15T11%3A52%3A30Z%22%7D%7D%2C%7B%22key%22%3A%22XG53EIDF%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Lamm%20et%20al.%22%2C%22parsedDate%22%3A%222024-01-05%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BLamm%2C%20L.%2C%20Zufferey%2C%20S.%2C%20Righetto%2C%20R.%20D.%2C%20Wietrzynski%2C%20W.%2C%20Yamauchi%2C%20K.%20A.%2C%20Burt%2C%20A.%2C%20Liu%2C%20Y.%2C%20Zhang%2C%20H.%2C%20Martinez-Sanchez%2C%20A.%2C%20Ziegler%2C%20S.%2C%20Isensee%2C%20F.%2C%20Schnabel%2C%20J.%20A.%2C%20Engel%2C%20B.%20D.%2C%20%26amp%3B%20Peng%2C%20T.%20%282024%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BMemBrain%20v2%3A%20an%20end-to-end%20tool%20for%20the%20analysis%20of%20membranes%20in%20cryo-electron%20tomography%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B.%20bioRxiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1101%5C%2F2024.01.05.574336%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1101%5C%2F2024.01.05.574336%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22MemBrain%20v2%3A%20an%20end-to-end%20tool%20for%20the%20analysis%20of%20membranes%20in%20cryo-electron%20tomography%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lorenz%22%2C%22lastName%22%3A%22Lamm%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Simon%22%2C%22lastName%22%3A%22Zufferey%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ricardo%20D.%22%2C%22lastName%22%3A%22Righetto%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Wojciech%22%2C%22lastName%22%3A%22Wietrzynski%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kevin%20A.%22%2C%22lastName%22%3A%22Yamauchi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alister%22%2C%22lastName%22%3A%22Burt%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ye%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hanyi%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Antonio%22%2C%22lastName%22%3A%22Martinez-Sanchez%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sebastian%22%2C%22lastName%22%3A%22Ziegler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Julia%20A.%22%2C%22lastName%22%3A%22Schnabel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Benjamin%20D.%22%2C%22lastName%22%3A%22Engel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tingying%22%2C%22lastName%22%3A%22Peng%22%7D%5D%2C%22abstractNote%22%3A%22MemBrain%20v2%20is%20a%20deep%20learning-enabled%20program%20aimed%20at%20the%20efficient%20analysis%20of%20membranes%20in%20cryo-electron%20tomography%20%28cryo-ET%29.%20The%20final%20v2%20release%20of%20MemBrain%20will%20comprise%20three%20main%20modules%3A%201%29%20MemBrain-seg%2C%20which%20provides%20automated%20membrane%20segmentation%2C%202%29%20MemBrain-pick%2C%20which%20provides%20automated%20picking%20of%20particles%20along%20segmented%20membranes%2C%20and%203%29%20MemBrain-stats%2C%20which%20provides%20quantitative%20statistics%20of%20particle%20distributions%20and%20membrane%20morphometrics.%5CnThis%20initial%20version%20of%20the%20manuscript%20is%20focused%20on%20the%20beta%20release%20of%20MemBrain-seg%2C%20which%20combines%20iterative%20training%20with%20diverse%20data%20and%20specialized%20Fourier-based%20data%20augmentations.%20These%20augmentations%20are%20specifically%20designed%20to%20enhance%20the%20tool%5Cu2019s%20adaptability%20to%20a%20variety%20of%20tomographic%20data%20and%20address%20common%20challenges%20in%20cryo-ET%20analysis.%20A%20key%20feature%20of%20MemBrain-seg%20is%20the%20implementation%20of%20the%20Surface-Dice%20loss%20function%2C%20which%20improves%20the%20network%5Cu2019s%20focus%20on%20membrane%20connectivity%20and%20allows%20for%20the%20effective%20incorporation%20of%20manual%20annotations%20from%20different%20sources.%20This%20function%20is%20beneficial%20in%20handling%20the%20variability%20inherent%20in%20membrane%20structures%20and%20annotations.%20Our%20ongoing%20collaboration%20with%20the%20cryo-ET%20community%20plays%20an%20important%20role%20in%20continually%20improving%20MemBrain%20v2%20with%20a%20wide%20array%20of%20training%20data.%20This%20collaborative%20approach%20ensures%20that%20MemBrain%20v2%20remains%20attuned%20to%20the%20field%5Cu2019s%20needs%2C%20enhancing%20its%20robustness%20and%20generalizability%20across%20different%20types%20of%20tomographic%20data.%5CnThe%20current%20version%20of%20MemBrain-seg%20is%20available%20at%20https%3A%5C%2F%5C%2Fgithub.com%5C%2Fteamtomo%5C%2Fmembrainseg%2C%20and%20the%20predecessor%20of%20MemBrain-pick%20%28also%20called%20MemBrain%20v1%29%20is%20deposited%20at%20https%3A%5C%2F%5C%2Fgithub.com%5C%2FCellArchLab%5C%2FMemBrain.%20This%20preprint%20will%20be%20updated%20concomitantly%20with%20the%20code%20until%20the%20three%20integrated%20modules%20of%20MemBrain%20v2%20are%20complete.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22bioRxiv%22%2C%22archiveID%22%3A%22%22%2C%22date%22%3A%222024-01-05%22%2C%22DOI%22%3A%2210.1101%5C%2F2024.01.05.574336%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.biorxiv.org%5C%2Fcontent%5C%2F10.1101%5C%2F2024.01.05.574336v1%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-02-15T10%3A23%3A29Z%22%7D%7D%2C%7B%22key%22%3A%229RDRBGBX%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Gotkowski%20et%20al.%22%2C%22parsedDate%22%3A%222024%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGotkowski%2C%20K.%2C%20Gupta%2C%20S.%2C%20Godinho%2C%20J.%20R.%20A.%2C%20Tochtrop%2C%20C.%20G.%20S.%2C%20Maier-Hein%2C%20K.%20H.%2C%20%26amp%3B%20Isensee%2C%20F.%20%282024%29.%20%26lt%3Bb%26gt%3BParticleSeg3D%3A%20A%20scalable%20out-of-the-box%20deep%20learning%20segmentation%20solution%20for%20individual%20particle%20characterization%20from%20micro%20CT%20images%20in%20mineral%20processing%20and%20recycling%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BPowder%20Technology%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B434%26lt%3B%5C%2Fi%26gt%3B%2C%20119286.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.powtec.2023.119286%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.powtec.2023.119286%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22ParticleSeg3D%3A%20A%20scalable%20out-of-the-box%20deep%20learning%20segmentation%20solution%20for%20individual%20particle%20characterization%20from%20micro%20CT%20images%20in%20mineral%20processing%20and%20recycling%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karol%22%2C%22lastName%22%3A%22Gotkowski%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shuvam%22%2C%22lastName%22%3A%22Gupta%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jose%20R.A.%22%2C%22lastName%22%3A%22Godinho%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Camila%20G.S.%22%2C%22lastName%22%3A%22Tochtrop%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%2202%5C%2F2024%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.powtec.2023.119286%22%2C%22ISSN%22%3A%2200325910%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Flinkinghub.elsevier.com%5C%2Fretrieve%5C%2Fpii%5C%2FS0032591023010690%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-11-15T11%3A48%3A17Z%22%7D%7D%2C%7B%22key%22%3A%22PZU8TGVH%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Roy%20et%20al.%22%2C%22parsedDate%22%3A%222024%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BRoy%2C%20S.%2C%20Koehler%2C%20G.%2C%20Baumgartner%2C%20M.%2C%20Ulrich%2C%20C.%2C%20Isensee%2C%20F.%2C%20Jaeger%2C%20P.%20F.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20%282024%29.%20%26lt%3Bb%26gt%3BAbstract%3A%203D%20Medical%20Image%20Segmentation%20with%20Transformer-based%20Scaling%20of%20ConvNets%26lt%3B%5C%2Fb%26gt%3B.%20In%20A.%20Maier%2C%20T.%20M.%20Deserno%2C%20H.%20Handels%2C%20K.%20Maier-Hein%2C%20C.%20Palm%2C%20%26amp%3B%20T.%20Tolxdorff%20%28Eds.%29%2C%20%26lt%3Bi%26gt%3BBildverarbeitung%20f%26%23xFC%3Br%20die%20Medizin%202024%26lt%3B%5C%2Fi%26gt%3B%20%28pp.%2079%26%23x2013%3B79%29.%20Springer%20Fachmedien.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-658-44037-4_23%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-658-44037-4_23%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Abstract%3A%203D%20Medical%20Image%20Segmentation%20with%20Transformer-based%20Scaling%20of%20ConvNets%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Saikat%22%2C%22lastName%22%3A%22Roy%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gregor%22%2C%22lastName%22%3A%22Koehler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Baumgartner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%20F.%22%2C%22lastName%22%3A%22Jaeger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Andreas%22%2C%22lastName%22%3A%22Maier%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Thomas%20M.%22%2C%22lastName%22%3A%22Deserno%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Heinz%22%2C%22lastName%22%3A%22Handels%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Christoph%22%2C%22lastName%22%3A%22Palm%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Thomas%22%2C%22lastName%22%3A%22Tolxdorff%22%7D%5D%2C%22abstractNote%22%3A%22Transformer-based%20architectures%20have%20seen%20widespread%20adoption%20recently%20for%20medical%20image%20segmentation.%20However%2C%20achieving%20performances%20equivalent%20to%20those%20in%20natural%20images%20are%20challenging%20due%20to%20the%20absence%20of%20large-scale%20annotated%20datasets.%20In%20contrast%2C%20convolutional%20networks%20have%20higher%20inductive%20biases%20and%20consequently%2C%20are%20easier%20to%20train%20to%20high%20performance.%20Recently%2C%20the%20ConvNeXt%20architecture%20attempted%20to%20improve%20the%20standard%20ConvNet%20by%20upgrading%20the%20popular%20ResNet%20blocks%20to%20mirror%20Transformer%20blocks.%20In%20this%20work%2C%20we%20extend%20upon%20this%20to%20design%20a%20modernized%20and%20scalable%20convolutional%20architecture%20customized%20to%20challenges%20of%20dense%20segmentation%20tasks%20in%20data-scarce%20medical%20settings.%20In%20this%20work%2C%20we%20introduce%20the%20MedNeXt%20architecture%20which%20is%20a%20Transformer-inspired%2C%20scalable%20large-kernel%20network%20for%20medical%20image%20segmentation%20with%204%20key%20features%20%5Cu2013%201%29%20Fully%20ConvNeXt%203D%20Encoder-Decoder%20architecture%20to%20leverage%20network-wide%20benefits%20of%20the%20block%20design%2C%202%29%20Residual%20ConvNeXt%20blocks%20for%20up%20and%20downsampling%20to%20preserve%20semantic%20richness%20across%20scales%2C%203%29%20Upkern%2C%20an%20algorithm%20to%20iteratively%20increase%20kernel%20size%20by%20upsampling%20small%20kernel%20networks%2C%20thus%20preventing%20performance%20saturation%20on%20limited%20data%2C%204%29%20Compound%20scaling%20of%20depth%2C%20width%20and%20kernel%20size%20to%20leverage%20the%20benefits%20of%20large-scale%20variants%20of%20the%20MedNeXt%20architecture.%20With%20state-of-the-art%20performance%20on%204%20popular%20segmentation%20tasks%2C%20across%20variations%20in%20imaging%20modalities%20%28CT%2C%20MRI%29%20and%20dataset%20sizes%2C%20MedNeXt%20represents%20a%20modernized%20deep%20architecture%20for%20medical%20image%20segmentation.%20This%20work%20was%20originally%20published%20in%20%5B1%5D.%20Our%20code%20is%20made%20publicly%20available%20at%3A%20https%3A%5C%2F%5C%2Fgithub.com%5C%2FMIC-DKFZ%5C%2FMedNeXt.%22%2C%22date%22%3A%222024%22%2C%22proceedingsTitle%22%3A%22Bildverarbeitung%20f%5Cu00fcr%20die%20Medizin%202024%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22de%22%2C%22DOI%22%3A%2210.1007%5C%2F978-3-658-44037-4_23%22%2C%22ISBN%22%3A%22978-3-658-44037-4%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A44%3A27Z%22%7D%7D%2C%7B%22key%22%3A%22K935T6J9%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Koehler%20et%20al.%22%2C%22parsedDate%22%3A%222024%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BKoehler%2C%20G.%2C%20Wald%2C%20T.%2C%20Ulrich%2C%20C.%2C%20Zimmerer%2C%20D.%2C%20Jaeger%2C%20P.%20F.%2C%20Franke%2C%20J.%20K.%2C%20Kohl%2C%20S.%2C%20Isensee%2C%20F.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20H.%20%282024%29.%20%26lt%3Bb%26gt%3BRecycleNet%3A%20Latent%20Feature%20Recycling%20Leads%20to%20Iterative%20Decision%20Refinement%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BProceedings%20of%20the%20IEEE%5C%2FCVF%20Winter%20Conference%20on%20Applications%20of%20Computer%20Vision%26lt%3B%5C%2Fi%26gt%3B%2C%20810%26%23x2013%3B818.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fopenaccess.thecvf.com%5C%2Fcontent%5C%2FWACV2024%5C%2Fhtml%5C%2FKohler_RecycleNet_Latent_Feature_Recycling_Leads_to_Iterative_Decision_Refinement_WACV_2024_paper.html%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fopenaccess.thecvf.com%5C%2Fcontent%5C%2FWACV2024%5C%2Fhtml%5C%2FKohler_RecycleNet_Latent_Feature_Recycling_Leads_to_Iterative_Decision_Refinement_WACV_2024_paper.html%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22RecycleNet%3A%20Latent%20Feature%20Recycling%20Leads%20to%20Iterative%20Decision%20Refinement%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gregor%22%2C%22lastName%22%3A%22Koehler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tassilo%22%2C%22lastName%22%3A%22Wald%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Zimmerer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%20F.%22%2C%22lastName%22%3A%22Jaeger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22J%5Cu00f6rg%20KH%22%2C%22lastName%22%3A%22Franke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Simon%22%2C%22lastName%22%3A%22Kohl%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222024%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%20IEEE%5C%2FCVF%20Winter%20Conference%20on%20Applications%20of%20Computer%20Vision%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fopenaccess.thecvf.com%5C%2Fcontent%5C%2FWACV2024%5C%2Fhtml%5C%2FKohler_RecycleNet_Latent_Feature_Recycling_Leads_to_Iterative_Decision_Refinement_WACV_2024_paper.html%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-02-15T10%3A22%3A13Z%22%7D%7D%2C%7B%22key%22%3A%22MRCY4K4W%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Isensee%20and%20Maier-Hein%22%2C%22parsedDate%22%3A%222023-12-12%22%2C%22numChildren%22%3A2%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BIsensee%2C%20F.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20H.%20%282023%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BLook%20Ma%2C%20no%20code%3A%20fine%20tuning%20nnU-Net%20for%20the%20AutoPET%20II%20challenge%20by%20only%20adjusting%20its%20JSON%20plans%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2309.13747%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2309.13747%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2309.13747%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Look%20Ma%2C%20no%20code%3A%20fine%20tuning%20nnU-Net%20for%20the%20AutoPET%20II%20challenge%20by%20only%20adjusting%20its%20JSON%20plans%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22We%20participate%20in%20the%20AutoPET%20II%20challenge%20by%20modifying%20nnU-Net%20only%20through%20its%20easy%20to%20understand%20and%20modify%20%26%23039%3BnnUNetPlans.json%26%23039%3B%20file.%20By%20switching%20to%20a%20UNet%20with%20residual%20encoder%2C%20increasing%20the%20batch%20size%20and%20increasing%20the%20patch%20size%20we%20obtain%20a%20configuration%20that%20substantially%20outperforms%20the%20automatically%20configured%20nnU-Net%20baseline%20%285-fold%20cross-validation%20Dice%20score%20of%2065.14%20vs%2033.28%29%20at%20the%20expense%20of%20increased%20compute%20requirements%20for%20model%20training.%20Our%20final%20submission%20ensembles%20the%20two%20most%20promising%20configurations.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2309.13747%22%2C%22date%22%3A%222023-12-12%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2309.13747%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2309.13747%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T14%3A01%3A20Z%22%7D%7D%2C%7B%22key%22%3A%22HB3HLARY%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Kofler%20et%20al.%22%2C%22parsedDate%22%3A%222023-12-05%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BKofler%2C%20F.%2C%20M%26%23xF6%3Bller%2C%20H.%2C%20Buchner%2C%20J.%20A.%2C%20de%20la%20Rosa%2C%20E.%2C%20Ezhov%2C%20I.%2C%20Rosier%2C%20M.%2C%20Mekki%2C%20I.%2C%20Shit%2C%20S.%2C%20Negwer%2C%20M.%2C%20Al-Maskari%2C%20R.%2C%20Ert%26%23xFC%3Brk%2C%20A.%2C%20Vinayahalingam%2C%20S.%2C%20Isensee%2C%20F.%2C%20Pati%2C%20S.%2C%20Rueckert%2C%20D.%2C%20Kirschke%2C%20J.%20S.%2C%20Ehrlich%2C%20S.%20K.%2C%20Reinke%2C%20A.%2C%20Menze%2C%20B.%2C%20%26%23x2026%3B%20Piraud%2C%20M.%20%282023%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BPanoptica%20--%20instance-wise%20evaluation%20of%203D%20semantic%20and%20instance%20segmentation%20maps%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2312.02608%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2312.02608%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2312.02608%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Panoptica%20--%20instance-wise%20evaluation%20of%203D%20semantic%20and%20instance%20segmentation%20maps%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Kofler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hendrik%22%2C%22lastName%22%3A%22M%5Cu00f6ller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Josef%20A.%22%2C%22lastName%22%3A%22Buchner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ezequiel%22%2C%22lastName%22%3A%22de%20la%20Rosa%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ivan%22%2C%22lastName%22%3A%22Ezhov%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marcel%22%2C%22lastName%22%3A%22Rosier%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Isra%22%2C%22lastName%22%3A%22Mekki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suprosanna%22%2C%22lastName%22%3A%22Shit%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Moritz%22%2C%22lastName%22%3A%22Negwer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rami%22%2C%22lastName%22%3A%22Al-Maskari%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ali%22%2C%22lastName%22%3A%22Ert%5Cu00fcrk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shankeeth%22%2C%22lastName%22%3A%22Vinayahalingam%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sarthak%22%2C%22lastName%22%3A%22Pati%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%22%2C%22lastName%22%3A%22Rueckert%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jan%20S.%22%2C%22lastName%22%3A%22Kirschke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Stefan%20K.%22%2C%22lastName%22%3A%22Ehrlich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Annika%22%2C%22lastName%22%3A%22Reinke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bjoern%22%2C%22lastName%22%3A%22Menze%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Benedikt%22%2C%22lastName%22%3A%22Wiestler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marie%22%2C%22lastName%22%3A%22Piraud%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20introduces%20panoptica%2C%20a%20versatile%20and%20performance-optimized%20package%20designed%20for%20computing%20instance-wise%20segmentation%20quality%20metrics%20from%202D%20and%203D%20segmentation%20maps.%20panoptica%20addresses%20the%20limitations%20of%20existing%20metrics%20and%20provides%20a%20modular%20framework%20that%20complements%20the%20original%20intersection%20over%20union-based%20panoptic%20quality%20with%20other%20metrics%2C%20such%20as%20the%20distance%20metric%20Average%20Symmetric%20Surface%20Distance.%20The%20package%20is%20open-source%2C%20implemented%20in%20Python%2C%20and%20accompanied%20by%20comprehensive%20documentation%20and%20tutorials.%20panoptica%20employs%20a%20three-step%20metrics%20computation%20process%20to%20cover%20diverse%20use%20cases.%20The%20efficacy%20of%20panoptica%20is%20demonstrated%20on%20various%20real-world%20biomedical%20datasets%2C%20where%20an%20instance-wise%20evaluation%20is%20instrumental%20for%20an%20accurate%20representation%20of%20the%20underlying%20clinical%20task.%20Overall%2C%20we%20envision%20panoptica%20as%20a%20valuable%20tool%20facilitating%20in-depth%20evaluation%20of%20segmentation%20methods.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2312.02608%22%2C%22date%22%3A%222023-12-05%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2312.02608%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2312.02608%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T12%3A33%3A54Z%22%7D%7D%2C%7B%22key%22%3A%22BQBFAW36%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Kovacs%20et%20al.%22%2C%22parsedDate%22%3A%222023-11-13%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BKovacs%2C%20B.%2C%20Netzer%2C%20N.%2C%20Baumgartner%2C%20M.%2C%20Schrader%2C%20A.%2C%20Isensee%2C%20F.%2C%20Wei%26%23xDF%3Ber%2C%20C.%2C%20Wolf%2C%20I.%2C%20G%26%23xF6%3Brtz%2C%20M.%2C%20Jaeger%2C%20P.%20F.%2C%20Sch%26%23xFC%3Btz%2C%20V.%2C%20Floca%2C%20R.%2C%20Gnirs%2C%20R.%2C%20Stenzinger%2C%20A.%2C%20Hohenfellner%2C%20M.%2C%20Schlemmer%2C%20H.-P.%2C%20Bonekamp%2C%20D.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20H.%20%282023%29.%20%26lt%3Bb%26gt%3BAddressing%20image%20misalignments%20in%20multi-parametric%20prostate%20MRI%20for%20enhanced%20computer-aided%20diagnosis%20of%20prostate%20cancer%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BScientific%20Reports%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B13%26lt%3B%5C%2Fi%26gt%3B%281%29%2C%2019805.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1038%5C%2Fs41598-023-46747-z%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1038%5C%2Fs41598-023-46747-z%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Addressing%20image%20misalignments%20in%20multi-parametric%20prostate%20MRI%20for%20enhanced%20computer-aided%20diagnosis%20of%20prostate%20cancer%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Balint%22%2C%22lastName%22%3A%22Kovacs%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nils%22%2C%22lastName%22%3A%22Netzer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Baumgartner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adrian%22%2C%22lastName%22%3A%22Schrader%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Cedric%22%2C%22lastName%22%3A%22Wei%5Cu00dfer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ivo%22%2C%22lastName%22%3A%22Wolf%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Magdalena%22%2C%22lastName%22%3A%22G%5Cu00f6rtz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%20F.%22%2C%22lastName%22%3A%22Jaeger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Victoria%22%2C%22lastName%22%3A%22Sch%5Cu00fctz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ralf%22%2C%22lastName%22%3A%22Floca%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Regula%22%2C%22lastName%22%3A%22Gnirs%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Albrecht%22%2C%22lastName%22%3A%22Stenzinger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Markus%22%2C%22lastName%22%3A%22Hohenfellner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Heinz-Peter%22%2C%22lastName%22%3A%22Schlemmer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Bonekamp%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22Prostate%20cancer%20%28PCa%29%20diagnosis%20on%20multi-parametric%20magnetic%20resonance%20images%20%28MRI%29%20requires%20radiologists%20with%20a%20high%20level%20of%20expertise.%20Misalignments%20between%20the%20MRI%20sequences%20can%20be%20caused%20by%20patient%20movement%2C%20elastic%20soft-tissue%20deformations%2C%20and%20imaging%20artifacts.%20They%20further%20increase%20the%20complexity%20of%20the%20task%20prompting%20radiologists%20to%20interpret%20the%20images.%20Recently%2C%20computer-aided%20diagnosis%20%28CAD%29%20tools%20have%20demonstrated%20potential%20for%20PCa%20diagnosis%20typically%20relying%20on%20complex%20co-registration%20of%20the%20input%20modalities.%20However%2C%20there%20is%20no%20consensus%20among%20research%20groups%20on%20whether%20CAD%20systems%20profit%20from%20using%20registration.%20Furthermore%2C%20alternative%20strategies%20to%20handle%20multi-modal%20misalignments%20have%20not%20been%20explored%20so%20far.%20Our%20study%20introduces%20and%20compares%20different%20strategies%20to%20cope%20with%20image%20misalignments%20and%20evaluates%20them%20regarding%20to%20their%20direct%20effect%20on%20diagnostic%20accuracy%20of%20PCa.%20In%20addition%20to%20established%20registration%20algorithms%2C%20we%20propose%20%5Cu2018misalignment%20augmentation%5Cu2019%20as%20a%20concept%20to%20increase%20CAD%20robustness.%20As%20the%20results%20demonstrate%2C%20misalignment%20augmentations%20can%20not%20only%20compensate%20for%20a%20complete%20lack%20of%20registration%2C%20but%20if%20used%20in%20conjunction%20with%20registration%2C%20also%20improve%20the%20overall%20performance%20on%20an%20independent%20test%20set.%22%2C%22date%22%3A%222023-11-13%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1038%5C%2Fs41598-023-46747-z%22%2C%22ISSN%22%3A%222045-2322%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.nature.com%5C%2Farticles%5C%2Fs41598-023-46747-z%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T14%3A11%3A49Z%22%7D%7D%2C%7B%22key%22%3A%226JKKIDVQ%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Klein%20et%20al.%22%2C%22parsedDate%22%3A%222023-10-30%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BKlein%2C%20L.%2C%20Ziegler%2C%20S.%2C%20Laufer%2C%20F.%2C%20Debus%2C%20C.%2C%20G%26%23xF6%3Btz%2C%20M.%2C%20Maier%26%23x2010%3BHein%2C%20K.%2C%20Paetzold%2C%20U.%20W.%2C%20Isensee%2C%20F.%2C%20%26amp%3B%20J%26%23xE4%3Bger%2C%20P.%20F.%20%282023%29.%20%26lt%3Bb%26gt%3BDiscovering%20Process%20Dynamics%20for%20Scalable%20Perovskite%20Solar%20Cell%20Manufacturing%20with%20Explainable%20AI%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BAdvanced%20Materials%26lt%3B%5C%2Fi%26gt%3B%2C%202307160.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1002%5C%2Fadma.202307160%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1002%5C%2Fadma.202307160%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Discovering%20Process%20Dynamics%20for%20Scalable%20Perovskite%20Solar%20Cell%20Manufacturing%20with%20Explainable%20AI%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lukas%22%2C%22lastName%22%3A%22Klein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sebastian%22%2C%22lastName%22%3A%22Ziegler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Felix%22%2C%22lastName%22%3A%22Laufer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Charlotte%22%2C%22lastName%22%3A%22Debus%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Markus%22%2C%22lastName%22%3A%22G%5Cu00f6tz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier%5Cu2010Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ulrich%20W.%22%2C%22lastName%22%3A%22Paetzold%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%20F.%22%2C%22lastName%22%3A%22J%5Cu00e4ger%22%7D%5D%2C%22abstractNote%22%3A%22Abstract%5Cn%20%20%20%20%20%20%20%20%20%20%20%20Large%5Cu2010area%20processing%20of%20perovskite%20semiconductor%20thin%5Cu2010films%20is%20complex%20and%20evokes%20unexplained%20variance%20in%20quality%2C%20posing%20a%20major%20hurdle%20for%20the%20commercialization%20of%20perovskite%20photovoltaics.%20Advances%20in%20scalable%20fabrication%20processes%20are%20currently%20limited%20to%20gradual%20and%20arbitrary%20trial%5Cu2010and%5Cu2010error%20procedures.%20While%20the%20in%5Cu2010situ%20acquisition%20of%20photoluminescence%20videos%20has%20the%20potential%20to%20reveal%20important%20variations%20in%20the%20thin%5Cu2010film%20formation%20process%2C%20the%20high%20dimensionality%20of%20the%20data%20quickly%20surpasses%20the%20limits%20of%20human%20analysis.%20In%20response%2C%20this%20study%20leverages%20deep%20learning%20and%20explainable%20artificial%20intelligence%20%28XAI%29%20to%20discover%20relationships%20between%20sensor%20information%20acquired%20during%20the%20perovskite%20thin%5Cu2010film%20formation%20process%20and%20the%20resulting%20solar%20cell%20performance%20indicators%2C%20while%20rendering%20these%20relationships%20humanly%20understandable.%20We%5Cu00a0further%20show%20how%20gained%20insights%20can%20be%20distilled%20into%20actionable%20recommendations%20for%20perovskite%20thin%5Cu2010film%20processing%2C%20advancing%20towards%20industrial%5Cu2010scale%20solar%20cell%20manufacturing.%20Our%5Cu00a0study%20demonstrates%20that%20XAI%20methods%20will%20play%20a%20critical%20role%20in%20accelerating%20energy%20materials%20science.%5Cn%20%20%20%20%20%20%20%20%20%20%20%20This%20article%20is%20protected%20by%20copyright.%20All%20rights%20reserved%22%2C%22date%22%3A%222023-10-30%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1002%5C%2Fadma.202307160%22%2C%22ISSN%22%3A%220935-9648%2C%201521-4095%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fonlinelibrary.wiley.com%5C%2Fdoi%5C%2F10.1002%5C%2Fadma.202307160%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-11-15T11%3A44%3A15Z%22%7D%7D%2C%7B%22key%22%3A%226JS57HEF%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Abdallah%20et%20al.%22%2C%22parsedDate%22%3A%222023-10%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BAbdallah%2C%20N.%2C%20Wood%2C%20A.%2C%20Benidir%2C%20T.%2C%20Heller%2C%20N.%2C%20Isensee%2C%20F.%2C%20Tejpaul%2C%20R.%2C%20Corrigan%2C%20D.%2C%20Suk-Ouichai%2C%20C.%2C%20Struyk%2C%20G.%2C%20Moore%2C%20K.%2C%20Venkatesh%2C%20N.%2C%20Ergun%2C%20O.%2C%20You%2C%20A.%2C%20Campbell%2C%20R.%2C%20Remer%2C%20E.%20M.%2C%20Haywood%2C%20S.%2C%20Krishnamurthi%2C%20V.%2C%20Abouassaly%2C%20R.%2C%20Campbell%2C%20S.%2C%20%26%23x2026%3B%20Weight%2C%20C.%20J.%20%282023%29.%20%26lt%3Bb%26gt%3BAI-generated%20R.E.N.A.L.%2B%20Score%20Surpasses%20Human-generated%20Score%20in%20Predicting%20Renal%20Oncologic%20Outcomes%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BUrology%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B180%26lt%3B%5C%2Fi%26gt%3B%2C%20160%26%23x2013%3B167.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.urology.2023.07.017%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.urology.2023.07.017%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22AI-generated%20R.E.N.A.L.%2B%20Score%20Surpasses%20Human-generated%20Score%20in%20Predicting%20Renal%20Oncologic%20Outcomes%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nour%22%2C%22lastName%22%3A%22Abdallah%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrew%22%2C%22lastName%22%3A%22Wood%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tarik%22%2C%22lastName%22%3A%22Benidir%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nicholas%22%2C%22lastName%22%3A%22Heller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Resha%22%2C%22lastName%22%3A%22Tejpaul%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dillon%22%2C%22lastName%22%3A%22Corrigan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chalairat%22%2C%22lastName%22%3A%22Suk-Ouichai%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Griffin%22%2C%22lastName%22%3A%22Struyk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Keenan%22%2C%22lastName%22%3A%22Moore%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nitin%22%2C%22lastName%22%3A%22Venkatesh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Onuralp%22%2C%22lastName%22%3A%22Ergun%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alex%22%2C%22lastName%22%3A%22You%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rebecca%22%2C%22lastName%22%3A%22Campbell%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Erick%20M.%22%2C%22lastName%22%3A%22Remer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Samuel%22%2C%22lastName%22%3A%22Haywood%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Venkatesh%22%2C%22lastName%22%3A%22Krishnamurthi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Robert%22%2C%22lastName%22%3A%22Abouassaly%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Steven%22%2C%22lastName%22%3A%22Campbell%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nikolaos%22%2C%22lastName%22%3A%22Papanikolopoulos%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christopher%20J.%22%2C%22lastName%22%3A%22Weight%22%7D%5D%2C%22abstractNote%22%3A%22OBJECTIVE%3A%20To%20determine%20whether%20we%20can%20surpass%20the%20traditional%20R.E.N.A.L.%20nephrometry%20score%20%28H-score%29%20prediction%20ability%20of%20pathologic%20outcomes%20by%20creating%20artificial%20intelligence%20%28AI%29-generated%20R.E.N.A.L.%2B%5Cu00a0score%20%28AI%2B%20score%29%20with%20continuous%20rather%20than%20ordinal%20components.%20We%20also%20assessed%20the%20AI%2B%20score%20components%26%23039%3B%20relative%20importance%20with%20respect%20to%20outcome%20odds.%5CnMETHODS%3A%20This%20is%20a%20retrospective%20study%20of%20300%20consecutive%20patients%20with%20preoperative%20computed%20tomography%20scans%20showing%20suspected%20renal%20cancer%20at%20a%20single%20institution%20from%202010%20to%202018.%20H-score%20was%20tabulated%20by%20three%20trained%20medical%20personnel.%20Deep%20neural%20network%20approach%20automatically%20generated%20kidney%20segmentation%20masks%20of%20parenchyma%20and%20tumor.%20Geometric%20algorithms%20were%20used%20to%20automatically%20estimate%20score%20components%20as%20ordinal%20and%20continuous%20variables.%20Multivariate%20logistic%20regression%20of%20continuous%20R.E.N.A.L.%20components%20was%20used%20to%20generate%20AI%2B%20score.%20Predictive%20utility%20was%20compared%20between%20AI%2B%2C%20AI%2C%20and%20H-scores%20for%20variables%20of%20interest%2C%20and%20AI%2B%20score%20components%26%23039%3B%20relative%20importance%20was%20assessed.%5CnRESULTS%3A%20Median%20age%20was%2060years%20%28interquartile%20range%2051-68%29%2C%20and%2040%25%20were%20female.%20Median%20tumor%20size%20was%204.2%5Cu00a0cm%20%282.6-6.12%29%2C%20and%2092%25%20were%20malignant%2C%20including%2027%25%2C%2037%25%2C%20and%2023%25%20with%20high-stage%2C%20high-grade%2C%20and%20necrosis%2C%20respectively.%20AI%2B%20score%20demonstrated%20superior%20predictive%20ability%20over%20AI%20and%20H-scores%20for%20predicting%20malignancy%20%28area%20under%20the%20curve%20%5BAUC%5D%200.69%20vs%200.67%20vs%200.64%2C%20respectively%29%2C%20high%5Cu00a0stage%20%28AUC%200.82%20vs%200.65%20vs%200.71%2C%20respectively%29%2C%20high%5Cu00a0grade%20%28AUC%200.78%20vs%200.65%20vs%200.65%2C%20respectively%29%2C%20pathologic%20tumor%20necrosis%20%28AUC%200.81%20vs%200.72%20vs%200.74%2C%20respectively%29%2C%20and%20partial%20nephrectomy%20approach%20%28AUC%200.88%20vs%200.74%20vs%200.79%2C%20respectively%29.%20Of%20AI%2B%20score%20components%2C%20the%20maximal%20tumor%20diameter%20%28%26quot%3BR%26quot%3B%29%20was%20the%20most%20important%20outcomes%20predictor.%5CnCONCLUSION%3A%20AI%2B%20score%20was%20superior%20to%20AI-score%20and%20H-score%20in%20predicting%20oncologic%20outcomes.%20Time-efficient%20AI%2B%20score%20can%20be%20used%20at%20the%20point%20of%20care%2C%20surpassing%20validated%20clinical%20scoring%20systems.%22%2C%22date%22%3A%222023-10%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.urology.2023.07.017%22%2C%22ISSN%22%3A%221527-9995%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T13%3A04%3A16Z%22%7D%7D%2C%7B%22key%22%3A%22CZNLCBEY%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Kovacs%20et%20al.%22%2C%22parsedDate%22%3A%222023-09-07%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BKovacs%2C%20B.%2C%20Netzer%2C%20N.%2C%20Baumgartner%2C%20M.%2C%20Eith%2C%20C.%2C%20Bounias%2C%20D.%2C%20Meinzer%2C%20C.%2C%20Jaeger%2C%20P.%20F.%2C%20Zhang%2C%20K.%20S.%2C%20Floca%2C%20R.%2C%20Schrader%2C%20A.%2C%20Isensee%2C%20F.%2C%20Gnirs%2C%20R.%2C%20Goertz%2C%20M.%2C%20Schuetz%2C%20V.%2C%20Stenzinger%2C%20A.%2C%20Hohenfellner%2C%20M.%2C%20Schlemmer%2C%20H.-P.%2C%20Wolf%2C%20I.%2C%20Bonekamp%2C%20D.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20H.%20%282023%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BAnatomy-informed%20Data%20Augmentation%20for%20Enhanced%20Prostate%20Cancer%20Detection%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2309.03652%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2309.03652%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2309.03652%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Anatomy-informed%20Data%20Augmentation%20for%20Enhanced%20Prostate%20Cancer%20Detection%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Balint%22%2C%22lastName%22%3A%22Kovacs%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nils%22%2C%22lastName%22%3A%22Netzer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Baumgartner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Carolin%22%2C%22lastName%22%3A%22Eith%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dimitrios%22%2C%22lastName%22%3A%22Bounias%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Clara%22%2C%22lastName%22%3A%22Meinzer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%20F.%22%2C%22lastName%22%3A%22Jaeger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kevin%20S.%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ralf%22%2C%22lastName%22%3A%22Floca%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adrian%22%2C%22lastName%22%3A%22Schrader%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Regula%22%2C%22lastName%22%3A%22Gnirs%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Magdalena%22%2C%22lastName%22%3A%22Goertz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Viktoria%22%2C%22lastName%22%3A%22Schuetz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Albrecht%22%2C%22lastName%22%3A%22Stenzinger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Markus%22%2C%22lastName%22%3A%22Hohenfellner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Heinz-Peter%22%2C%22lastName%22%3A%22Schlemmer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ivo%22%2C%22lastName%22%3A%22Wolf%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Bonekamp%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22Data%20augmentation%20%28DA%29%20is%20a%20key%20factor%20in%20medical%20image%20analysis%2C%20such%20as%20in%20prostate%20cancer%20%28PCa%29%20detection%20on%20magnetic%20resonance%20images.%20State-of-the-art%20computer-aided%20diagnosis%20systems%20still%20rely%20on%20simplistic%20spatial%20transformations%20to%20preserve%20the%20pathological%20label%20post%20transformation.%20However%2C%20such%20augmentations%20do%20not%20substantially%20increase%20the%20organ%20as%20well%20as%20tumor%20shape%20variability%20in%20the%20training%20set%2C%20limiting%20the%20model%26%23039%3Bs%20ability%20to%20generalize%20to%20unseen%20cases%20with%20more%20diverse%20localized%20soft-tissue%20deformations.%20We%20propose%20a%20new%20anatomy-informed%20transformation%20that%20leverages%20information%20from%20adjacent%20organs%20to%20simulate%20typical%20physiological%20deformations%20of%20the%20prostate%20and%20generates%20unique%20lesion%20shapes%20without%20altering%20their%20label.%20Due%20to%20its%20lightweight%20computational%20requirements%2C%20it%20can%20be%20easily%20integrated%20into%20common%20DA%20frameworks.%20We%20demonstrate%20the%20effectiveness%20of%20our%20augmentation%20on%20a%20dataset%20of%20774%20biopsy-confirmed%20examinations%2C%20by%20evaluating%20a%20state-of-the-art%20method%20for%20PCa%20detection%20with%20different%20augmentation%20settings.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2309.03652%22%2C%22date%22%3A%222023-09-07%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2309.03652%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2309.03652%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T14%3A09%3A22Z%22%7D%7D%2C%7B%22key%22%3A%22GC58WGKK%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Gutsche%20et%20al.%22%2C%22parsedDate%22%3A%222023-08-10%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGutsche%2C%20R.%2C%20Lowis%2C%20C.%2C%20Ziemons%2C%20K.%2C%20Kocher%2C%20M.%2C%20Ceccon%2C%20G.%2C%20Brambilla%2C%20C.%20R.%2C%20Shah%2C%20N.%20J.%2C%20Langen%2C%20K.-J.%2C%20Galldiks%2C%20N.%2C%20Isensee%2C%20F.%2C%20%26amp%3B%20Lohmann%2C%20P.%20%282023%29.%20%26lt%3Bb%26gt%3BAutomated%20Brain%20Tumor%20Detection%20and%20Segmentation%20for%20Treatment%20Response%20Assessment%20Using%20Amino%20Acid%20PET%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BJournal%20of%20Nuclear%20Medicine%3A%20Official%20Publication%2C%20Society%20of%20Nuclear%20Medicine%26lt%3B%5C%2Fi%26gt%3B%2C%20jnumed.123.265725.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2967%5C%2Fjnumed.123.265725%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2967%5C%2Fjnumed.123.265725%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Automated%20Brain%20Tumor%20Detection%20and%20Segmentation%20for%20Treatment%20Response%20Assessment%20Using%20Amino%20Acid%20PET%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Robin%22%2C%22lastName%22%3A%22Gutsche%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Carsten%22%2C%22lastName%22%3A%22Lowis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karl%22%2C%22lastName%22%3A%22Ziemons%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Kocher%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Garry%22%2C%22lastName%22%3A%22Ceccon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Cl%5Cu00e1udia%20R%5Cu00e9gio%22%2C%22lastName%22%3A%22Brambilla%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nadim%20J.%22%2C%22lastName%22%3A%22Shah%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karl-Josef%22%2C%22lastName%22%3A%22Langen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Norbert%22%2C%22lastName%22%3A%22Galldiks%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Philipp%22%2C%22lastName%22%3A%22Lohmann%22%7D%5D%2C%22abstractNote%22%3A%22Evaluation%20of%20metabolic%20tumor%20volume%20%28MTV%29%20changes%20using%20amino%20acid%20PET%20has%20become%20an%20important%20tool%20for%20response%20assessment%20in%20brain%20tumor%20patients.%20MTV%20is%20usually%20determined%20by%20manual%20or%20semiautomatic%20delineation%2C%20which%20is%20laborious%20and%20may%20be%20prone%20to%20intra-%20and%20interobserver%20variability.%20The%20goal%20of%20our%20study%20was%20to%20develop%20a%20method%20for%20automated%20MTV%20segmentation%20and%20to%20evaluate%20its%20performance%20for%20response%20assessment%20in%20patients%20with%20gliomas.%20Methods%3A%20In%20total%2C%20699%20amino%20acid%20PET%20scans%20using%20the%20tracer%20O-%282-%5B18F%5Dfluoroethyl%29-l-tyrosine%20%2818F-FET%29%20from%20555%20brain%20tumor%20patients%20at%20initial%20diagnosis%20or%20during%20follow-up%20were%20retrospectively%20evaluated%20%28mainly%20glioma%20patients%2C%2076%25%29.%2018F-FET%20PET%20MTVs%20were%20segmented%20semiautomatically%20by%20experienced%20readers.%20An%20artificial%20neural%20network%20%28no%20new%20U-Net%29%20was%20configured%20on%20476%20scans%20from%20399%20patients%2C%20and%20the%20network%20performance%20was%20evaluated%20on%20a%20test%20dataset%20including%20223%20scans%20from%20156%20patients.%20Surface%20and%20volumetric%20Dice%20similarity%20coefficients%20%28DSCs%29%20were%20used%20to%20evaluate%20segmentation%20quality.%20Finally%2C%20the%20network%20was%20applied%20to%20a%20recently%20published%2018F-FET%20PET%20study%20on%20response%20assessment%20in%20glioblastoma%20patients%20treated%20with%20adjuvant%20temozolomide%20chemotherapy%20for%20a%20fully%20automated%20response%20assessment%20in%20comparison%20to%20an%20experienced%20physician.%20Results%3A%20In%20the%20test%20dataset%2C%2092%25%20of%20lesions%20with%20increased%20uptake%20%28n%20%3D%20189%29%20and%2085%25%20of%20lesions%20with%20iso-%20or%20hypometabolic%20uptake%20%28n%20%3D%2033%29%20were%20correctly%20identified%20%28F1%20score%2C%2092%25%29.%20Single%20lesions%20with%20a%20contiguous%20uptake%20had%20the%20highest%20DSC%2C%20followed%20by%20lesions%20with%20heterogeneous%2C%20noncontiguous%20uptake%20and%20multifocal%20lesions%20%28surface%20DSC%3A%200.96%2C%200.93%2C%20and%200.81%20respectively%3B%20volume%20DSC%3A%200.83%2C%200.77%2C%20and%200.67%2C%20respectively%29.%20Change%20in%20MTV%2C%20as%20detected%20by%20the%20automated%20segmentation%2C%20was%20a%20significant%20determinant%20of%20disease-free%20and%20overall%20survival%2C%20in%20agreement%20with%20the%20physician%26%23039%3Bs%20assessment.%20Conclusion%3A%20Our%20deep%20learning-based%2018F-FET%20PET%20segmentation%20allows%20reliable%2C%20robust%2C%20and%20fully%20automated%20evaluation%20of%20MTV%20in%20brain%20tumor%20patients%20and%20demonstrates%20clinical%20value%20for%20automated%20response%20assessment.%22%2C%22date%22%3A%222023-08-10%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.2967%5C%2Fjnumed.123.265725%22%2C%22ISSN%22%3A%221535-5667%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-05-02T07%3A44%3A37Z%22%7D%7D%2C%7B%22key%22%3A%2256Q6KQS8%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Wald%20et%20al.%22%2C%22parsedDate%22%3A%222023-07-05%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BWald%2C%20T.%2C%20Ulrich%2C%20C.%2C%20Isensee%2C%20F.%2C%20Zimmerer%2C%20D.%2C%20Koehler%2C%20G.%2C%20Baumgartner%2C%20M.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20H.%20%282023%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BExploring%20new%20ways%3A%20Enforcing%20representational%20dissimilarity%20to%20learn%20new%20features%20and%20reduce%20error%20consistency%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2307.02516%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2307.02516%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2307.02516%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Exploring%20new%20ways%3A%20Enforcing%20representational%20dissimilarity%20to%20learn%20new%20features%20and%20reduce%20error%20consistency%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tassilo%22%2C%22lastName%22%3A%22Wald%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Zimmerer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gregor%22%2C%22lastName%22%3A%22Koehler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Baumgartner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22Independently%20trained%20machine%20learning%20models%20tend%20to%20learn%20similar%20features.%20Given%20an%20ensemble%20of%20independently%20trained%20models%2C%20this%20results%20in%20correlated%20predictions%20and%20common%20failure%20modes.%20Previous%20attempts%20focusing%20on%20decorrelation%20of%20output%20predictions%20or%20logits%20yielded%20mixed%20results%2C%20particularly%20due%20to%20their%20reduction%20in%20model%20accuracy%20caused%20by%20conflicting%20optimization%20objectives.%20In%20this%20paper%2C%20we%20propose%20the%20novel%20idea%20of%20utilizing%20methods%20of%20the%20representational%20similarity%20field%20to%20promote%20dissimilarity%20during%20training%20instead%20of%20measuring%20similarity%20of%20trained%20models.%20To%20this%20end%2C%20we%20promote%20intermediate%20representations%20to%20be%20dissimilar%20at%20different%20depths%20between%20architectures%2C%20with%20the%20goal%20of%20learning%20robust%20ensembles%20with%20disjoint%20failure%20modes.%20We%20show%20that%20highly%20dissimilar%20intermediate%20representations%20result%20in%20less%20correlated%20output%20predictions%20and%20slightly%20lower%20error%20consistency%2C%20resulting%20in%20higher%20ensemble%20accuracy.%20With%20this%2C%20we%20shine%20first%20light%20on%20the%20connection%20between%20intermediate%20representations%20and%20their%20impact%20on%20the%20output%20predictions.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2307.02516%22%2C%22date%22%3A%222023-07-05%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2307.02516%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2307.02516%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222023-07-21T07%3A16%3A21Z%22%7D%7D%2C%7B%22key%22%3A%224EF5UIDE%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Heller%20et%20al.%22%2C%22parsedDate%22%3A%222023-07-04%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHeller%2C%20N.%2C%20Isensee%2C%20F.%2C%20Trofimova%2C%20D.%2C%20Tejpaul%2C%20R.%2C%20Zhao%2C%20Z.%2C%20Chen%2C%20H.%2C%20Wang%2C%20L.%2C%20Golts%2C%20A.%2C%20Khapun%2C%20D.%2C%20Shats%2C%20D.%2C%20Shoshan%2C%20Y.%2C%20Gilboa-Solomon%2C%20F.%2C%20George%2C%20Y.%2C%20Yang%2C%20X.%2C%20Zhang%2C%20J.%2C%20Zhang%2C%20J.%2C%20Xia%2C%20Y.%2C%20Wu%2C%20M.%2C%20Liu%2C%20Z.%2C%20%26%23x2026%3B%20Weight%2C%20C.%20%282023%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BThe%20KiTS21%20Challenge%3A%20Automatic%20segmentation%20of%20kidneys%2C%20renal%20tumors%2C%20and%20renal%20cysts%20in%20corticomedullary-phase%20CT%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2307.01984%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2307.01984%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2307.01984%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22The%20KiTS21%20Challenge%3A%20Automatic%20segmentation%20of%20kidneys%2C%20renal%20tumors%2C%20and%20renal%20cysts%20in%20corticomedullary-phase%20CT%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nicholas%22%2C%22lastName%22%3A%22Heller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dasha%22%2C%22lastName%22%3A%22Trofimova%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Resha%22%2C%22lastName%22%3A%22Tejpaul%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zhongchen%22%2C%22lastName%22%3A%22Zhao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Huai%22%2C%22lastName%22%3A%22Chen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lisheng%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alex%22%2C%22lastName%22%3A%22Golts%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%22%2C%22lastName%22%3A%22Khapun%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%22%2C%22lastName%22%3A%22Shats%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yoel%22%2C%22lastName%22%3A%22Shoshan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Flora%22%2C%22lastName%22%3A%22Gilboa-Solomon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yasmeen%22%2C%22lastName%22%3A%22George%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xi%22%2C%22lastName%22%3A%22Yang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jianpeng%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jing%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yong%22%2C%22lastName%22%3A%22Xia%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mengran%22%2C%22lastName%22%3A%22Wu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zhiyang%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ed%22%2C%22lastName%22%3A%22Walczak%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sean%22%2C%22lastName%22%3A%22McSweeney%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ranveer%22%2C%22lastName%22%3A%22Vasdev%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chris%22%2C%22lastName%22%3A%22Hornung%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rafat%22%2C%22lastName%22%3A%22Solaiman%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jamee%22%2C%22lastName%22%3A%22Schoephoerster%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bailey%22%2C%22lastName%22%3A%22Abernathy%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Wu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Safa%22%2C%22lastName%22%3A%22Abdulkadir%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ben%22%2C%22lastName%22%3A%22Byun%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Justice%22%2C%22lastName%22%3A%22Spriggs%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Griffin%22%2C%22lastName%22%3A%22Struyk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alexandra%22%2C%22lastName%22%3A%22Austin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ben%22%2C%22lastName%22%3A%22Simpson%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Hagstrom%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sierra%22%2C%22lastName%22%3A%22Virnig%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22John%22%2C%22lastName%22%3A%22French%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nitin%22%2C%22lastName%22%3A%22Venkatesh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sarah%22%2C%22lastName%22%3A%22Chan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Keenan%22%2C%22lastName%22%3A%22Moore%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anna%22%2C%22lastName%22%3A%22Jacobsen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Susan%22%2C%22lastName%22%3A%22Austin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mark%22%2C%22lastName%22%3A%22Austin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Subodh%22%2C%22lastName%22%3A%22Regmi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nikolaos%22%2C%22lastName%22%3A%22Papanikolopoulos%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christopher%22%2C%22lastName%22%3A%22Weight%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20presents%20the%20challenge%20report%20for%20the%202021%20Kidney%20and%20Kidney%20Tumor%20Segmentation%20Challenge%20%28KiTS21%29%20held%20in%20conjunction%20with%20the%202021%20international%20conference%20on%20Medical%20Image%20Computing%20and%20Computer%20Assisted%20Interventions%20%28MICCAI%29.%20KiTS21%20is%20a%20sequel%20to%20its%20first%20edition%20in%202019%2C%20and%20it%20features%20a%20variety%20of%20innovations%20in%20how%20the%20challenge%20was%20designed%2C%20in%20addition%20to%20a%20larger%20dataset.%20A%20novel%20annotation%20method%20was%20used%20to%20collect%20three%20separate%20annotations%20for%20each%20region%20of%20interest%2C%20and%20these%20annotations%20were%20performed%20in%20a%20fully%20transparent%20setting%20using%20a%20web-based%20annotation%20tool.%20Further%2C%20the%20KiTS21%20test%20set%20was%20collected%20from%20an%20outside%20institution%2C%20challenging%20participants%20to%20develop%20methods%20that%20generalize%20well%20to%20new%20populations.%20Nonetheless%2C%20the%20top-performing%20teams%20achieved%20a%20significant%20improvement%20over%20the%20state%20of%20the%20art%20set%20in%202019%2C%20and%20this%20performance%20is%20shown%20to%20inch%20ever%20closer%20to%20human-level%20performance.%20An%20in-depth%20meta-analysis%20is%20presented%20describing%20which%20methods%20were%20used%20and%20how%20they%20faired%20on%20the%20leaderboard%2C%20as%20well%20as%20the%20characteristics%20of%20which%20cases%20generally%20saw%20good%20performance%2C%20and%20which%20did%20not.%20Overall%20KiTS21%20facilitated%20a%20significant%20advancement%20in%20the%20state%20of%20the%20art%20in%20kidney%20tumor%20segmentation%2C%20and%20provides%20useful%20insights%20that%20are%20applicable%20to%20the%20field%20of%20semantic%20segmentation%20as%20a%20whole.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2307.01984%22%2C%22date%22%3A%222023-07-04%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2307.01984%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2307.01984%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T13%3A58%3A39Z%22%7D%7D%2C%7B%22key%22%3A%22QXMGIF8J%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Yang%20et%20al.%22%2C%22parsedDate%22%3A%222023-05-10%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BYang%2C%20L.%2C%20Liu%2C%20Q.%2C%20Kumar%2C%20P.%2C%20Sengupta%2C%20A.%2C%20Farnoud%2C%20A.%2C%20Shen%2C%20R.%2C%20Trofimova%2C%20D.%2C%20Ziegler%2C%20S.%2C%20Kutschke%2C%20D.%2C%20Kreyling%2C%20W.%2C%20Piraud%2C%20M.%2C%20Isensee%2C%20F.%2C%20Burgstaller%2C%20G.%2C%20Rehberg%2C%20M.%2C%20St%26%23xF6%3Bger%2C%20T.%2C%20%26amp%3B%20Schmid%2C%20O.%20%282023%29.%20%26lt%3Bb%26gt%3B60%20Multimodal%20Imaging%20and%20Artificial%20Intelligence%20Unveil%20Hot-Spot%20Deposition%2C%20Bronchial%5C%2FAlveolar%20Dose%20and%20Cellular%20Fate%20of%20Biopersistent%20Nanoparticles%20in%20the%20Lung%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BAnnals%20of%20Work%20Exposures%20and%20Health%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B67%26lt%3B%5C%2Fi%26gt%3B%2C%20i53%26%23x2013%3Bi53.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1093%5C%2Fannweh%5C%2Fwxac087.129%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1093%5C%2Fannweh%5C%2Fwxac087.129%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%2260%20Multimodal%20Imaging%20and%20Artificial%20Intelligence%20Unveil%20Hot-Spot%20Deposition%2C%20Bronchial%5C%2FAlveolar%20Dose%20and%20Cellular%20Fate%20of%20Biopersistent%20Nanoparticles%20in%20the%20Lung%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lin%22%2C%22lastName%22%3A%22Yang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Qiongliang%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pramod%22%2C%22lastName%22%3A%22Kumar%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Arunima%22%2C%22lastName%22%3A%22Sengupta%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ali%22%2C%22lastName%22%3A%22Farnoud%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ruolin%22%2C%22lastName%22%3A%22Shen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Darya%22%2C%22lastName%22%3A%22Trofimova%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sebastian%22%2C%22lastName%22%3A%22Ziegler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Kutschke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Wolfgang%22%2C%22lastName%22%3A%22Kreyling%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marie%22%2C%22lastName%22%3A%22Piraud%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gerald%22%2C%22lastName%22%3A%22Burgstaller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Markus%22%2C%22lastName%22%3A%22Rehberg%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tobias%22%2C%22lastName%22%3A%22St%5Cu00f6ger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Otmar%22%2C%22lastName%22%3A%22Schmid%22%7D%5D%2C%22abstractNote%22%3A%22Pulmonary%20delivery%20is%20not%20only%20of%20increasing%20importance%20to%20exploit%20local%20therapy%20for%20lung%20diseases%20like%20COVID-19%2C%20but%20also%20plays%20an%20essential%20role%20in%20interpreting%20health%20impact%20of%20inhaled%20hazardous%20%28nano-%29materials.%20Deciphering%20of%20biodistribution%2C%20biokinetics%2C%20and%20cell-mediated%20immunity%20of%20pulmonary%20delivered%20nanoparticles%20%28NPs%29%20remains%20insufficient.%20We%20applied%20state-of-the-art%20multimodal%20imaging%20and%20deep%20learning%20pipelines%20to%20elucidate%20the%20intricate%20deposition%20profiles%20and%20the%20fate%20of%20biopersistent%20NPs%20in%20the%20lung%20within%20cellular%20resolution.%20Spatially%20resolved%20delivery%20characteristics%20like%20inter-%20and%20intra-acinar%20distribution%20pattern%20and%20regional%20NP%20dosage%20were%20revealed%20by%20tissue-clearing%20light-sheet%20fluorescence%20microscopy%20for%20six%20common%20routes%20of%20pulmonary%20delivery%2C%20i.e.%2C%20intranasal%20%26amp%3B%20oropharyngeal%20aspiration%2C%20intubated%20instillation%2C%20microsprayer%20application%2C%20ventilator-assisted%20%26amp%3B%20nose-only%20aerosol%20inhalation.%20Artificial%20intelligence-driven%20entire%20airway%203D%20segmentation%20%28convolutional%20neural%20network%29%20enabled%20accurate%20dosimetry%20of%20bronchial%20versus%20acinar%5C%2Falveolar%20NP%20dose%20%28B%5C%2FA%3A%200.04%20to%200.18%20depending%20on%20delivery%20route%29%20rather%20than%20the%20conventionally%20simplified%202D%20central-to-peripheral%20ratio%20%28C%5C%2FP%3A%201.32%20to%203.79%29.%20Moreover%2C%20longitudinal%203D%20imaging%20revealed%20similar%20intra-acinar%20NP%20kinetics%20independent%20of%20delivery%20route.%20Inhaled%20NP%20relocation%20from%20the%20alveolar-epithelium%20to%20interstitium%20was%20traditionally%20claimed%20as%20the%20consequence%20of%20passive%20diffusion%5C%2Ftransportation%20of%20NPs.%20This%20study%2C%20however%2C%20revealed%20that%20acinar%20NP%20transport%20can%20be%20attributed%20to%20the%20phagocytosis%20and%20migration%20of%20tissue-resident%20macrophages%20%28TRMs%29%20as%20evidenced%20by%20complementary%20analytical%20approaches%20%28intravital%20microscopy%2C%20ex%20vivo%204D%20live-tissue%20microscopy%2C%20in%20situ%20immunofluorescence%2C%20ex%20vivo%20NP-lung%20interaction%20model%2C%20flow%20cytometry%29.%20Overall%2C%20this%20study%20elucidates%20holistic%20NP-lung%20delivery%20and%20biokinetics%20features%20and%20TRM%20immunity%20on%20the%20fate%20of%20biopersistent%20NPs.%22%2C%22date%22%3A%222023-05-10%22%2C%22language%22%3A%22%22%2C%22DOI%22%3A%2210.1093%5C%2Fannweh%5C%2Fwxac087.129%22%2C%22ISSN%22%3A%22%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T12%3A58%3A52Z%22%7D%7D%2C%7B%22key%22%3A%22KFRRN545%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Roy%20et%20al.%22%2C%22parsedDate%22%3A%222023-04-09%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BRoy%2C%20S.%2C%20Koehler%2C%20G.%2C%20Baumgartner%2C%20M.%2C%20Ulrich%2C%20C.%2C%20Petersen%2C%20J.%2C%20Isensee%2C%20F.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20%282023%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BTransformer%20Utilization%20in%20Medical%20Image%20Segmentation%20Networks%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2304.04225%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2304.04225%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2304.04225%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Transformer%20Utilization%20in%20Medical%20Image%20Segmentation%20Networks%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Saikat%22%2C%22lastName%22%3A%22Roy%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gregor%22%2C%22lastName%22%3A%22Koehler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Baumgartner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jens%22%2C%22lastName%22%3A%22Petersen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22Owing%20to%20success%20in%20the%20data-rich%20domain%20of%20natural%20images%2C%20Transformers%20have%20recently%20become%20popular%20in%20medical%20image%20segmentation.%20However%2C%20the%20pairing%20of%20Transformers%20with%20convolutional%20blocks%20in%20varying%20architectural%20permutations%20leaves%20their%20relative%20effectiveness%20to%20open%20interpretation.%20We%20introduce%20Transformer%20Ablations%20that%20replace%20the%20Transformer%20blocks%20with%20plain%20linear%20operators%20to%20quantify%20this%20effectiveness.%20With%20experiments%20on%208%20models%20on%202%20medical%20image%20segmentation%20tasks%2C%20we%20explore%20--%201%29%20the%20replaceable%20nature%20of%20Transformer-learnt%20representations%2C%202%29%20Transformer%20capacity%20alone%20cannot%20prevent%20representational%20replaceability%20and%20works%20in%20tandem%20with%20effective%20design%2C%203%29%20The%20mere%20existence%20of%20explicit%20feature%20hierarchies%20in%20transformer%20blocks%20is%20more%20beneficial%20than%20accompanying%20self-attention%20modules%2C%204%29%20Major%20spatial%20downsampling%20before%20Transformer%20modules%20should%20be%20used%20with%20caution.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2304.04225%22%2C%22date%22%3A%222023-04-09%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2304.04225%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2304.04225%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T14%3A33%3A23Z%22%7D%7D%2C%7B%22key%22%3A%22IATVMD87%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Eisenmann%20et%20al.%22%2C%22parsedDate%22%3A%222023-03-30%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BEisenmann%2C%20M.%2C%20Reinke%2C%20A.%2C%20Weru%2C%20V.%2C%20Tizabi%2C%20M.%20D.%2C%20Isensee%2C%20F.%2C%20Adler%2C%20T.%20J.%2C%20Ali%2C%20S.%2C%20Andrearczyk%2C%20V.%2C%20Aubreville%2C%20M.%2C%20Baid%2C%20U.%2C%20Bakas%2C%20S.%2C%20Balu%2C%20N.%2C%20Bano%2C%20S.%2C%20Bernal%2C%20J.%2C%20Bodenstedt%2C%20S.%2C%20Casella%2C%20A.%2C%20Cheplygina%2C%20V.%2C%20Daum%2C%20M.%2C%20de%20Bruijne%2C%20M.%2C%20%26%23x2026%3B%20Maier-Hein%2C%20L.%20%282023%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BWhy%20is%20the%20winner%20the%20best%3F%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2303.17719%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2303.17719%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2303.17719%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Why%20is%20the%20winner%20the%20best%3F%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Matthias%22%2C%22lastName%22%3A%22Eisenmann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Annika%22%2C%22lastName%22%3A%22Reinke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Vivienn%22%2C%22lastName%22%3A%22Weru%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Minu%20Dietlinde%22%2C%22lastName%22%3A%22Tizabi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tim%20J.%22%2C%22lastName%22%3A%22Adler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sharib%22%2C%22lastName%22%3A%22Ali%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Vincent%22%2C%22lastName%22%3A%22Andrearczyk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marc%22%2C%22lastName%22%3A%22Aubreville%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ujjwal%22%2C%22lastName%22%3A%22Baid%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Spyridon%22%2C%22lastName%22%3A%22Bakas%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Niranjan%22%2C%22lastName%22%3A%22Balu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sophia%22%2C%22lastName%22%3A%22Bano%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jorge%22%2C%22lastName%22%3A%22Bernal%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sebastian%22%2C%22lastName%22%3A%22Bodenstedt%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alessandro%22%2C%22lastName%22%3A%22Casella%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Veronika%22%2C%22lastName%22%3A%22Cheplygina%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marie%22%2C%22lastName%22%3A%22Daum%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marleen%22%2C%22lastName%22%3A%22de%20Bruijne%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adrien%22%2C%22lastName%22%3A%22Depeursinge%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Reuben%22%2C%22lastName%22%3A%22Dorent%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jan%22%2C%22lastName%22%3A%22Egger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%20G.%22%2C%22lastName%22%3A%22Ellis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sandy%22%2C%22lastName%22%3A%22Engelhardt%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Melanie%22%2C%22lastName%22%3A%22Ganz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Noha%22%2C%22lastName%22%3A%22Ghatwary%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gabriel%22%2C%22lastName%22%3A%22Girard%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Patrick%22%2C%22lastName%22%3A%22Godau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anubha%22%2C%22lastName%22%3A%22Gupta%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lasse%22%2C%22lastName%22%3A%22Hansen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kanako%22%2C%22lastName%22%3A%22Harada%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mattias%22%2C%22lastName%22%3A%22Heinrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nicholas%22%2C%22lastName%22%3A%22Heller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alessa%22%2C%22lastName%22%3A%22Hering%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Arnaud%22%2C%22lastName%22%3A%22Huaulm%5Cu00e9%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pierre%22%2C%22lastName%22%3A%22Jannin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ali%20Emre%22%2C%22lastName%22%3A%22Kavur%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Old%5Cu0159ich%22%2C%22lastName%22%3A%22Kodym%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michal%22%2C%22lastName%22%3A%22Kozubek%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jianning%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hongwei%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jun%22%2C%22lastName%22%3A%22Ma%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Carlos%22%2C%22lastName%22%3A%22Mart%5Cu00edn-Isla%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bjoern%22%2C%22lastName%22%3A%22Menze%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alison%22%2C%22lastName%22%3A%22Noble%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Valentin%22%2C%22lastName%22%3A%22Oreiller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nicolas%22%2C%22lastName%22%3A%22Padoy%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sarthak%22%2C%22lastName%22%3A%22Pati%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kelly%22%2C%22lastName%22%3A%22Payette%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tim%22%2C%22lastName%22%3A%22R%5Cu00e4dsch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jonathan%22%2C%22lastName%22%3A%22Rafael-Pati%5Cu00f1o%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Vivek%20Singh%22%2C%22lastName%22%3A%22Bawa%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Stefanie%22%2C%22lastName%22%3A%22Speidel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Carole%20H.%22%2C%22lastName%22%3A%22Sudre%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kimberlin%22%2C%22lastName%22%3A%22van%20Wijnen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Wagner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Donglai%22%2C%22lastName%22%3A%22Wei%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Amine%22%2C%22lastName%22%3A%22Yamlahi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Moi%20Hoon%22%2C%22lastName%22%3A%22Yap%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chun%22%2C%22lastName%22%3A%22Yuan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%22%2C%22lastName%22%3A%22Zenk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Aneeq%22%2C%22lastName%22%3A%22Zia%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Zimmerer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dogu%20Baran%22%2C%22lastName%22%3A%22Aydogan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Binod%22%2C%22lastName%22%3A%22Bhattarai%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Louise%22%2C%22lastName%22%3A%22Bloch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Raphael%22%2C%22lastName%22%3A%22Br%5Cu00fcngel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jihoon%22%2C%22lastName%22%3A%22Cho%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chanyeol%22%2C%22lastName%22%3A%22Choi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Qi%22%2C%22lastName%22%3A%22Dou%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ivan%22%2C%22lastName%22%3A%22Ezhov%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christoph%20M.%22%2C%22lastName%22%3A%22Friedrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Clifton%22%2C%22lastName%22%3A%22Fuller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rebati%20Raman%22%2C%22lastName%22%3A%22Gaire%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adrian%22%2C%22lastName%22%3A%22Galdran%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22%5Cu00c1lvaro%20Garc%5Cu00eda%22%2C%22lastName%22%3A%22Faura%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maria%22%2C%22lastName%22%3A%22Grammatikopoulou%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22SeulGi%22%2C%22lastName%22%3A%22Hong%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mostafa%22%2C%22lastName%22%3A%22Jahanifar%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ikbeom%22%2C%22lastName%22%3A%22Jang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Abdolrahim%22%2C%22lastName%22%3A%22Kadkhodamohammadi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Inha%22%2C%22lastName%22%3A%22Kang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Kofler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Satoshi%22%2C%22lastName%22%3A%22Kondo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hugo%22%2C%22lastName%22%3A%22Kuijf%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mingxing%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Minh%20Huan%22%2C%22lastName%22%3A%22Luu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Toma%5Cu017e%22%2C%22lastName%22%3A%22Martin%5Cu010di%5Cu010d%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pedro%22%2C%22lastName%22%3A%22Morais%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mohamed%20A.%22%2C%22lastName%22%3A%22Naser%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bruno%22%2C%22lastName%22%3A%22Oliveira%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Owen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Subeen%22%2C%22lastName%22%3A%22Pang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jinah%22%2C%22lastName%22%3A%22Park%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sung-Hong%22%2C%22lastName%22%3A%22Park%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Szymon%22%2C%22lastName%22%3A%22P%5Cu0142otka%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Elodie%22%2C%22lastName%22%3A%22Puybareau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nasir%22%2C%22lastName%22%3A%22Rajpoot%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kanghyun%22%2C%22lastName%22%3A%22Ryu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Numan%22%2C%22lastName%22%3A%22Saeed%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adam%22%2C%22lastName%22%3A%22Shephard%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pengcheng%22%2C%22lastName%22%3A%22Shi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dejan%22%2C%22lastName%22%3A%22%5Cu0160tepec%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ronast%22%2C%22lastName%22%3A%22Subedi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillaume%22%2C%22lastName%22%3A%22Tochon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Helena%20R.%22%2C%22lastName%22%3A%22Torres%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Helene%22%2C%22lastName%22%3A%22Urien%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jo%5Cu00e3o%20L.%22%2C%22lastName%22%3A%22Vila%5Cu00e7a%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kareem%20Abdul%22%2C%22lastName%22%3A%22Wahid%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Haojie%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jiacheng%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Liansheng%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiyue%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Benedikt%22%2C%22lastName%22%3A%22Wiestler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marek%22%2C%22lastName%22%3A%22Wodzinski%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fangfang%22%2C%22lastName%22%3A%22Xia%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Juanying%22%2C%22lastName%22%3A%22Xie%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zhiwei%22%2C%22lastName%22%3A%22Xiong%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sen%22%2C%22lastName%22%3A%22Yang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yanwu%22%2C%22lastName%22%3A%22Yang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zixuan%22%2C%22lastName%22%3A%22Zhao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%20F.%22%2C%22lastName%22%3A%22J%5Cu00e4ger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Annette%22%2C%22lastName%22%3A%22Kopp-Schneider%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lena%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22International%20benchmarking%20competitions%20have%20become%20fundamental%20for%20the%20comparative%20performance%20assessment%20of%20image%20analysis%20methods.%20However%2C%20little%20attention%20has%20been%20given%20to%20investigating%20what%20can%20be%20learnt%20from%20these%20competitions.%20Do%20they%20really%20generate%20scientific%20progress%3F%20What%20are%20common%20and%20successful%20participation%20strategies%3F%20What%20makes%20a%20solution%20superior%20to%20a%20competing%20method%3F%20To%20address%20this%20gap%20in%20the%20literature%2C%20we%20performed%20a%20multi-center%20study%20with%20all%2080%20competitions%20that%20were%20conducted%20in%20the%20scope%20of%20IEEE%20ISBI%202021%20and%20MICCAI%202021.%20Statistical%20analyses%20performed%20based%20on%20comprehensive%20descriptions%20of%20the%20submitted%20algorithms%20linked%20to%20their%20rank%20as%20well%20as%20the%20underlying%20participation%20strategies%20revealed%20common%20characteristics%20of%20winning%20solutions.%20These%20typically%20include%20the%20use%20of%20multi-task%20learning%20%2863%25%29%20and%5C%2For%20multi-stage%20pipelines%20%2861%25%29%2C%20and%20a%20focus%20on%20augmentation%20%28100%25%29%2C%20image%20preprocessing%20%2897%25%29%2C%20data%20curation%20%2879%25%29%2C%20and%20postprocessing%20%2866%25%29.%20The%20%26quot%3Btypical%26quot%3B%20lead%20of%20a%20winning%20team%20is%20a%20computer%20scientist%20with%20a%20doctoral%20degree%2C%20five%20years%20of%20experience%20in%20biomedical%20image%20analysis%2C%20and%20four%20years%20of%20experience%20in%20deep%20learning.%20Two%20core%20general%20development%20strategies%20stood%20out%20for%20highly-ranked%20teams%3A%20the%20reflection%20of%20the%20metrics%20in%20the%20method%20design%20and%20the%20focus%20on%20analyzing%20and%20handling%20failure%20cases.%20According%20to%20the%20organizers%2C%2043%25%20of%20the%20winning%20algorithms%20exceeded%20the%20state%20of%20the%20art%20but%20only%2011%25%20completely%20solved%20the%20respective%20domain%20problem.%20The%20insights%20of%20our%20study%20could%20help%20researchers%20%281%29%20improve%20algorithm%20development%20strategies%20when%20approaching%20new%20problems%2C%20and%20%282%29%20focus%20on%20open%20research%20questions%20revealed%20by%20this%20work.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2303.17719%22%2C%22date%22%3A%222023-03-30%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2303.17719%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2303.17719%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222023-04-03T11%3A36%3A59Z%22%7D%7D%2C%7B%22key%22%3A%227N7V5BUR%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A10654427%2C%22username%22%3A%22katharinakriegel%22%2C%22name%22%3A%22%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fkatharinakriegel%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Vollmuth%20et%20al.%22%2C%22parsedDate%22%3A%222023-03-14%22%2C%22numChildren%22%3A2%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BVollmuth%2C%20P.%2C%20Foltyn%2C%20M.%2C%20Huang%2C%20R.%20Y.%2C%20Galldiks%2C%20N.%2C%20Petersen%2C%20J.%2C%20Isensee%2C%20F.%2C%20van%20den%20Bent%2C%20M.%20J.%2C%20Barkhof%2C%20F.%2C%20Park%2C%20J.%20E.%2C%20Park%2C%20Y.%20W.%2C%20Ahn%2C%20S.%20S.%2C%20Brugnara%2C%20G.%2C%20Meredig%2C%20H.%2C%20Jain%2C%20R.%2C%20Smits%2C%20M.%2C%20Pope%2C%20W.%20B.%2C%20Maier-Hein%2C%20K.%2C%20Weller%2C%20M.%2C%20Wen%2C%20P.%20Y.%2C%20%26%23x2026%3B%20Bendszus%2C%20M.%20%282023%29.%20%26lt%3Bb%26gt%3BArtificial%20intelligence%20%28AI%29-based%20decision%20support%20improves%20reproducibility%20of%20tumor%20response%20assessment%20in%20neuro-oncology%3A%20An%20international%20multi-reader%20study%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BNeuro-Oncology%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B25%26lt%3B%5C%2Fi%26gt%3B%283%29%2C%20533%26%23x2013%3B543.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1093%5C%2Fneuonc%5C%2Fnoac189%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1093%5C%2Fneuonc%5C%2Fnoac189%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Artificial%20intelligence%20%28AI%29-based%20decision%20support%20improves%20reproducibility%20of%20tumor%20response%20assessment%20in%20neuro-oncology%3A%20An%20international%20multi-reader%20study%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Philipp%22%2C%22lastName%22%3A%22Vollmuth%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martha%22%2C%22lastName%22%3A%22Foltyn%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Raymond%20Y.%22%2C%22lastName%22%3A%22Huang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Norbert%22%2C%22lastName%22%3A%22Galldiks%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jens%22%2C%22lastName%22%3A%22Petersen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%20J.%22%2C%22lastName%22%3A%22van%20den%20Bent%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Frederik%22%2C%22lastName%22%3A%22Barkhof%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ji%20Eun%22%2C%22lastName%22%3A%22Park%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yae%20Won%22%2C%22lastName%22%3A%22Park%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sung%20Soo%22%2C%22lastName%22%3A%22Ahn%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gianluca%22%2C%22lastName%22%3A%22Brugnara%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hagen%22%2C%22lastName%22%3A%22Meredig%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rajan%22%2C%22lastName%22%3A%22Jain%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marion%22%2C%22lastName%22%3A%22Smits%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Whitney%20B.%22%2C%22lastName%22%3A%22Pope%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Weller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Patrick%20Y.%22%2C%22lastName%22%3A%22Wen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Wolfgang%22%2C%22lastName%22%3A%22Wick%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Bendszus%22%7D%5D%2C%22abstractNote%22%3A%22BACKGROUND%3A%20To%20assess%20whether%20artificial%20intelligence%20%28AI%29-based%20decision%20support%20allows%20more%20reproducible%20and%20standardized%20assessment%20of%20treatment%20response%20on%20MRI%20in%20neuro-oncology%20as%20compared%20to%20manual%202-dimensional%20measurements%20of%20tumor%20burden%20using%20the%20Response%20Assessment%20in%20Neuro-Oncology%20%28RANO%29%20criteria.%5CnMETHODS%3A%20A%20series%20of%2030%20patients%20%2815%20lower-grade%20gliomas%2C%2015%20glioblastoma%29%20with%20availability%20of%20consecutive%20MRI%20scans%20was%20selected.%20The%20time%20to%20progression%20%28TTP%29%20on%20MRI%20was%20separately%20evaluated%20for%20each%20patient%20by%2015%20investigators%20over%20two%20rounds.%20In%20the%20first%20round%20the%20TTP%20was%20evaluated%20based%20on%20the%20RANO%20criteria%2C%20whereas%20in%20the%20second%20round%20the%20TTP%20was%20evaluated%20by%20incorporating%20additional%20information%20from%20AI-enhanced%20MRI%20sequences%20depicting%20the%20longitudinal%20changes%20in%20tumor%20volumes.%20The%20agreement%20of%20the%20TTP%20measurements%20between%20investigators%20was%20evaluated%20using%20concordance%20correlation%20coefficients%20%28CCC%29%20with%20confidence%20intervals%20%28CI%29%20and%20P-values%20obtained%20using%20bootstrap%20resampling.%5CnRESULTS%3A%20The%20CCC%20of%20TTP-measurements%20between%20investigators%20was%200.77%20%2895%25%20CI%5Cu00a0%3D%5Cu00a00.69%2C0.88%29%20with%20RANO%20alone%20and%20increased%20to%200.91%20%2895%25%20CI%5Cu00a0%3D%5Cu00a00.82%2C0.95%29%20with%20AI-based%20decision%20support%20%28P%5Cu00a0%3D%5Cu00a0.005%29.%20This%20effect%20was%20significantly%20greater%20%28P%5Cu00a0%3D%5Cu00a0.008%29%20for%20patients%20with%20lower-grade%20gliomas%20%28CCC%5Cu00a0%3D%5Cu00a00.70%20%5B95%25%20CI%5Cu00a0%3D%5Cu00a00.56%2C0.85%5D%20without%20vs.%200.90%20%5B95%25%20CI%5Cu00a0%3D%5Cu00a00.76%2C0.95%5D%20with%20AI-based%20decision%20support%29%20as%20compared%20to%20glioblastoma%20%28CCC%5Cu00a0%3D%5Cu00a00.83%20%5B95%25%20CI%5Cu00a0%3D%5Cu00a00.75%2C0.92%5D%20without%20vs.%200.86%20%5B95%25%20CI%5Cu00a0%3D%5Cu00a00.78%2C0.93%5D%20with%20AI-based%20decision%20support%29.%20Investigators%20with%20less%20years%20of%20experience%20judged%20the%20AI-based%20decision%20as%20more%20helpful%20%28P%5Cu00a0%3D%5Cu00a0.02%29.%5CnCONCLUSIONS%3A%20AI-based%20decision%20support%20has%20the%20potential%20to%20yield%20more%20reproducible%20and%20standardized%20assessment%20of%20treatment%20response%20in%20neuro-oncology%20as%20compared%20to%20manual%202-dimensional%20measurements%20of%20tumor%20burden%2C%20particularly%20in%20patients%20with%20lower-grade%20gliomas.%20A%5Cu00a0fully-functional%20version%20of%20this%20AI-based%20processing%20pipeline%20is%20provided%20as%20open-source%20%28https%3A%5C%2F%5C%2Fgithub.com%5C%2FNeuroAI-HD%5C%2FHD-GLIO-XNAT%29.%22%2C%22date%22%3A%222023-03-14%22%2C%22language%22%3A%22eng%22%2C%22DOI%22%3A%2210.1093%5C%2Fneuonc%5C%2Fnoac189%22%2C%22ISSN%22%3A%221523-5866%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-11-15T11%3A58%3A39Z%22%7D%7D%2C%7B%22key%22%3A%22Y7MNSG2Q%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Ro%5Cu00df%20et%20al.%22%2C%22parsedDate%22%3A%222023-03-01%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BRo%26%23xDF%3B%2C%20T.%2C%20Bruno%2C%20P.%2C%20Reinke%2C%20A.%2C%20Wiesenfarth%2C%20M.%2C%20Koeppel%2C%20L.%2C%20Full%2C%20P.%20M.%2C%20Pekdemir%2C%20B.%2C%20Godau%2C%20P.%2C%20Trofimova%2C%20D.%2C%20Isensee%2C%20F.%2C%20Adler%2C%20T.%20J.%2C%20Tran%2C%20T.%20N.%2C%20Moccia%2C%20S.%2C%20Calimeri%2C%20F.%2C%20M%26%23xFC%3Bller-Stich%2C%20B.%20P.%2C%20Kopp-Schneider%2C%20A.%2C%20%26amp%3B%20Maier-Hein%2C%20L.%20%282023%29.%20%26lt%3Bb%26gt%3BBeyond%20rankings%3A%20Learning%20%28more%29%20from%20algorithm%20validation%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BMedical%20Image%20Analysis%26lt%3B%5C%2Fi%26gt%3B%2C%20102765.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.media.2023.102765%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.media.2023.102765%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Beyond%20rankings%3A%20Learning%20%28more%29%20from%20algorithm%20validation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tobias%22%2C%22lastName%22%3A%22Ro%5Cu00df%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pierangela%22%2C%22lastName%22%3A%22Bruno%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Annika%22%2C%22lastName%22%3A%22Reinke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Manuel%22%2C%22lastName%22%3A%22Wiesenfarth%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lisa%22%2C%22lastName%22%3A%22Koeppel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Peter%20M.%22%2C%22lastName%22%3A%22Full%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22B%5Cu00fcnyamin%22%2C%22lastName%22%3A%22Pekdemir%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Patrick%22%2C%22lastName%22%3A%22Godau%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Darya%22%2C%22lastName%22%3A%22Trofimova%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tim%20J.%22%2C%22lastName%22%3A%22Adler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Thuy%20N.%22%2C%22lastName%22%3A%22Tran%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sara%22%2C%22lastName%22%3A%22Moccia%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Francesco%22%2C%22lastName%22%3A%22Calimeri%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Beat%20P.%22%2C%22lastName%22%3A%22M%5Cu00fcller-Stich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Annette%22%2C%22lastName%22%3A%22Kopp-Schneider%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lena%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22Challenges%20have%20become%20the%20state-of-the-art%20approach%20to%20benchmark%20image%20analysis%20algorithms%20in%20a%20comparative%20manner.%20While%20the%20validation%20on%20identical%20data%20sets%20was%20a%20great%20step%20forward%2C%20results%20analysis%20is%20often%20restricted%20to%20pure%20ranking%20tables%2C%20leaving%20relevant%20questions%20unanswered.%20Specifically%2C%20little%20effort%20has%20been%20put%20into%20the%20systematic%20investigation%20on%20what%20characterizes%20images%20in%20which%20state-of-the-art%20algorithms%20fail.%20To%20address%20this%20gap%20in%20the%20literature%2C%20we%20%281%29%20present%20a%20statistical%20framework%20for%20learning%20from%20challenges%20and%20%282%29%20instantiate%20it%20for%20the%20specific%20task%20of%20instrument%20instance%20segmentation%20in%20laparoscopic%20videos.%20Our%20framework%20relies%20on%20the%20semantic%20meta%20data%20annotation%20of%20images%2C%20which%20serves%20as%20foundation%20for%20a%20General%20Linear%20Mixed%20Models%20%28GLMM%29%20analysis.%20Based%20on%2051%2C542%20meta%20data%20annotations%20performed%20on%202%2C728%20images%2C%20we%20applied%20our%20approach%20to%20the%20results%20of%20the%20Robust%20Medical%20Instrument%20Segmentation%20Challenge%20%28ROBUST-MIS%29%20challenge%202019%20and%20revealed%20underexposure%2C%20motion%20and%20occlusion%20of%20instruments%20as%20well%20as%20the%20presence%20of%20smoke%20or%20other%20objects%20in%20the%20background%20as%20major%20sources%20of%20algorithm%20failure.%20Our%20subsequent%20method%20development%2C%20tailored%20to%20the%20specific%20remaining%20issues%2C%20yielded%20a%20deep%20learning%20model%20with%20state-of-the-art%20overall%20performance%20and%20specific%20strengths%20in%20the%20processing%20of%20images%20in%20which%20previous%20methods%20tended%20to%20fail.%20Due%20to%20the%20objectivity%20and%20generic%20applicability%20of%20our%20approach%2C%20it%20could%20become%20a%20valuable%20tool%20for%20validation%20in%20the%20field%20of%20medical%20image%20analysis%20and%20beyond.%22%2C%22date%22%3A%222023-03-01%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.media.2023.102765%22%2C%22ISSN%22%3A%221361-8415%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.sciencedirect.com%5C%2Fscience%5C%2Farticle%5C%2Fpii%5C%2FS1361841523000269%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222023-03-02T15%3A52%3A01Z%22%7D%7D%2C%7B%22key%22%3A%22VQMZWJPV%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Wood%20et%20al.%22%2C%22parsedDate%22%3A%222023-02-20%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BWood%2C%20A.%2C%20Benidir%2C%20T.%2C%20Abdallah%2C%20N.%2C%20Heller%2C%20N.%2C%20Isensee%2C%20F.%2C%20Tejpaul%2C%20R.%2C%20Suk-ouichai%2C%20C.%2C%20Curry%2C%20C.%2C%20You%2C%20A.%2C%20Remer%2C%20E.%20M.%2C%20Haywood%2C%20S.%2C%20Campbell%2C%20S.%2C%20Papanikolopoulos%2C%20N.%2C%20%26amp%3B%20Weight%2C%20C.%20J.%20%282023%29.%20%26lt%3Bb%26gt%3BPredictive%20accuracy%20of%20computer-generated%20C-index%20nephrometry%20scores%20compared%20with%20human-generated%20scores%20in%20predicting%20oncologic%20and%20perioperative%20outcomes.%26lt%3B%5C%2Fb%26gt%3B%20%26lt%3Bi%26gt%3BJournal%20of%20Clinical%20Oncology%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B41%26lt%3B%5C%2Fi%26gt%3B%286_suppl%29%2C%20623%26%23x2013%3B623.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1200%5C%2FJCO.2023.41.6_suppl.623%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1200%5C%2FJCO.2023.41.6_suppl.623%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Predictive%20accuracy%20of%20computer-generated%20C-index%20nephrometry%20scores%20compared%20with%20human-generated%20scores%20in%20predicting%20oncologic%20and%20perioperative%20outcomes.%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrew%22%2C%22lastName%22%3A%22Wood%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tarik%22%2C%22lastName%22%3A%22Benidir%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nour%22%2C%22lastName%22%3A%22Abdallah%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nicholas%22%2C%22lastName%22%3A%22Heller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Resha%22%2C%22lastName%22%3A%22Tejpaul%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chalairat%22%2C%22lastName%22%3A%22Suk-ouichai%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Caleb%22%2C%22lastName%22%3A%22Curry%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alex%22%2C%22lastName%22%3A%22You%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Erick%20M.%22%2C%22lastName%22%3A%22Remer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Samuel%22%2C%22lastName%22%3A%22Haywood%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Steven%22%2C%22lastName%22%3A%22Campbell%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Nikolaos%22%2C%22lastName%22%3A%22Papanikolopoulos%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christopher%20J.%22%2C%22lastName%22%3A%22Weight%22%7D%5D%2C%22abstractNote%22%3A%22623%5CnBackground%3A%20The%20Centrality%20index%20%28C-index%29%20score%20is%20a%20validated%20nephrometry%20scoring%20system%20that%20requires%20precise%20measurements%20and%20mathematical%20calculations%20of%20cross%20sectional%20imaging.%20Like%20other%20nephrometry%20scores%2C%20its%20implementation%20has%20been%20slowed%20by%20required%20time%20investment%20and%20interobserver%20variability.%20We%20sought%20to%20automate%20this%20score%20on%20preoperative%20computerized%20tomography%20scans%20by%20developing%20an%20artificial%20intelligence-generated%20C-index%20score.%20We%20then%20aimed%20to%20evaluate%20its%20ability%20to%20predict%20meaningful%20oncologic%20and%20perioperative%20outcomes%20as%20compared%20to%20human-generated%20C-index%20nephrometry%20scores.%20Methods%3A%20300%20patients%20with%20preoperative%20computerized%20tomography%20with%20early%20arterial%20contrast%20phase%20were%20identified%20from%20a%20cohort%20of%20544%20consecutive%20patients%20undergoing%20surgical%20extirpation%20for%20suspected%20renal%20cancer.%20A%20deep%20neural%20network%20approach%20was%20used%20to%20automatically%20segment%20kidneys%20and%20tumors%2C%20and%20then%20programed%20to%20generate%20the%20measurements%20and%20calculate%20C-index%20score.%20Human%20C-index%20scores%20were%20independently%20calculated%20by%20medical%20personnel%20blinded%20to%20AI-scores.%20AI-%20and%20Human%20score%20agreement%20was%20assessed%20using%20bivariate%20linear%20regression%20correlation%20and%20their%20predictive%20abilities%20for%20both%20oncologic%20and%20perioperative%20outcomes%20were%20assessed%20using%20logistic%20regression%20and%20compared%20with%20receiver%20operating%20characteristic%20%28ROC%29%20curve%20analyses%20with%20measurements%20of%20areas%20under%20the%20curve%20%28AUC%29.%20Results%3A%20Median%20age%20was%2060%20years%20%28IQE%2051%5Cu201368%29%2C%20and%2040%25%20were%20female.%20Median%20tumor%20size%20was%204.2%20cm%20and%2091.3%25%20had%20malignant%20tumors.%2027%25%20were%20high%20stage%2C%2037%25%20high%20grade%2C%20and%2063%25%20underwent%20partial%20nephrectomy.%20There%20was%20significant%20agreement%20between%20Human%20scores%20and%20AI-scores%20on%20linear%20regression%20analysis%20%28R2%20%3D%200.738%2C%20p%20%26lt%3B0.0001%29.%20Both%20AI-%20and%20Human%20generated%20C-index%20scores%20similarly%20predicted%20meaningful%20oncologic%20outcomes%2C%20with%20lower%20levels%20of%20either%20C-index%20score%20associated%20with%20increased%20risk%20of%20malignant%20histology%20%28H-score%20p%20%3D%200.018%2C%20AI%20score%20p%20%3D0.014%29%20high-grade%20disease%20%28both%20p%20%26lt%3B0.0001%29%2C%20and%20high%20stage%20disease%20%28both%20p%20%26lt%3B0.0001%29.%20Lower%20levels%20of%20either%20AI%20or%20human%20generated%20C-index%20scores%20also%20predicted%20a%20radical%20nephrectomy%20rather%20than%20partial%20nephrectomy%20surgical%20approach%20%28both%20p%20%26lt%3B0.0001%29.%20AUC%20measurements%20%28Table%29%20were%20similar%20but%20consistently%20superior%20for%20AI%20generated%20C-index%20scores.%20Conclusions%3A%20Fully%20automated%20AI-generated%20C-index%20scores%20are%20comparable%20to%20human-generated%20C-index%20scores%20and%20predict%20a%20wide%20variety%20of%20meaningful%20patient-centered%20outcomes.%20Once%20validated%20in%20additional%20populations%2C%20our%20results%20suggest%20that%20our%20AI%20generated%20C-index%20could%20be%20delivered%20automatically%20from%20a%20preoperative%20CT%20scan%20to%20a%20clinician%20and%20patient%20at%20the%20point%20of%20care%20to%20aid%20in%20decision%20making.%5Cn%5Cu00a0%5CtAI%20AUC%5CtHuman%20AUC%5CnHigh%20Grade%5Ct0.750%5Ct0.708%5CnHigh%20Stage%5Ct0.786%5Ct0.760%5CnMalignant%20Histology%5Ct0.639%5Ct0.630%5CnSurgical%20Approach%5Ct0.870%5Ct0.843%5CnOPEN%20IN%20VIEWER%22%2C%22date%22%3A%222023-02-20%22%2C%22language%22%3A%22%22%2C%22DOI%22%3A%2210.1200%5C%2FJCO.2023.41.6_suppl.623%22%2C%22ISSN%22%3A%220732-183X%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fascopubs.org%5C%2Fdoi%5C%2Fabs%5C%2F10.1200%5C%2FJCO.2023.41.6_suppl.623%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T15%3A01%3A16Z%22%7D%7D%2C%7B%22key%22%3A%22BG93L74P%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Bilic%20et%20al.%22%2C%22parsedDate%22%3A%222023-02-01%22%2C%22numChildren%22%3A2%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BBilic%2C%20P.%2C%20Christ%2C%20P.%2C%20Li%2C%20H.%20B.%2C%20Vorontsov%2C%20E.%2C%20Ben-Cohen%2C%20A.%2C%20Kaissis%2C%20G.%2C%20Szeskin%2C%20A.%2C%20Jacobs%2C%20C.%2C%20Mamani%2C%20G.%20E.%20H.%2C%20Chartrand%2C%20G.%2C%20Loh%26%23xF6%3Bfer%2C%20F.%2C%20Holch%2C%20J.%20W.%2C%20Sommer%2C%20W.%2C%20Hofmann%2C%20F.%2C%20Hostettler%2C%20A.%2C%20Lev-Cohain%2C%20N.%2C%20Drozdzal%2C%20M.%2C%20Amitai%2C%20M.%20M.%2C%20Vivanti%2C%20R.%2C%20%26%23x2026%3B%20Menze%2C%20B.%20%282023%29.%20%26lt%3Bb%26gt%3BThe%20Liver%20Tumor%20Segmentation%20Benchmark%20%28LiTS%29%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BMedical%20Image%20Analysis%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B84%26lt%3B%5C%2Fi%26gt%3B%2C%20102680.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.media.2022.102680%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.media.2022.102680%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22The%20Liver%20Tumor%20Segmentation%20Benchmark%20%28LiTS%29%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Patrick%22%2C%22lastName%22%3A%22Bilic%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Patrick%22%2C%22lastName%22%3A%22Christ%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hongwei%20Bran%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Eugene%22%2C%22lastName%22%3A%22Vorontsov%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Avi%22%2C%22lastName%22%3A%22Ben-Cohen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Georgios%22%2C%22lastName%22%3A%22Kaissis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adi%22%2C%22lastName%22%3A%22Szeskin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Colin%22%2C%22lastName%22%3A%22Jacobs%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gabriel%20Efrain%20Humpire%22%2C%22lastName%22%3A%22Mamani%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gabriel%22%2C%22lastName%22%3A%22Chartrand%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Loh%5Cu00f6fer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Julian%20Walter%22%2C%22lastName%22%3A%22Holch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Wieland%22%2C%22lastName%22%3A%22Sommer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Felix%22%2C%22lastName%22%3A%22Hofmann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alexandre%22%2C%22lastName%22%3A%22Hostettler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Naama%22%2C%22lastName%22%3A%22Lev-Cohain%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michal%22%2C%22lastName%22%3A%22Drozdzal%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michal%20Marianne%22%2C%22lastName%22%3A%22Amitai%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Refael%22%2C%22lastName%22%3A%22Vivanti%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jacob%22%2C%22lastName%22%3A%22Sosna%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ivan%22%2C%22lastName%22%3A%22Ezhov%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anjany%22%2C%22lastName%22%3A%22Sekuboyina%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fernando%22%2C%22lastName%22%3A%22Navarro%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Kofler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Johannes%20C.%22%2C%22lastName%22%3A%22Paetzold%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suprosanna%22%2C%22lastName%22%3A%22Shit%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiaobin%22%2C%22lastName%22%3A%22Hu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jana%22%2C%22lastName%22%3A%22Lipkov%5Cu00e1%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Markus%22%2C%22lastName%22%3A%22Rempfler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marie%22%2C%22lastName%22%3A%22Piraud%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jan%22%2C%22lastName%22%3A%22Kirschke%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Benedikt%22%2C%22lastName%22%3A%22Wiestler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zhiheng%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christian%22%2C%22lastName%22%3A%22H%5Cu00fclsemeyer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marcel%22%2C%22lastName%22%3A%22Beetz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Florian%22%2C%22lastName%22%3A%22Ettlinger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michela%22%2C%22lastName%22%3A%22Antonelli%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Woong%22%2C%22lastName%22%3A%22Bae%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22M%5Cu00edriam%22%2C%22lastName%22%3A%22Bellver%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lei%22%2C%22lastName%22%3A%22Bi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hao%22%2C%22lastName%22%3A%22Chen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Grzegorz%22%2C%22lastName%22%3A%22Chlebus%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Erik%20B.%22%2C%22lastName%22%3A%22Dam%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Qi%22%2C%22lastName%22%3A%22Dou%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chi-Wing%22%2C%22lastName%22%3A%22Fu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bogdan%22%2C%22lastName%22%3A%22Georgescu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xavier%22%2C%22lastName%22%3A%22Gir%5Cu00f3-i-Nieto%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Felix%22%2C%22lastName%22%3A%22Gruen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xu%22%2C%22lastName%22%3A%22Han%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pheng-Ann%22%2C%22lastName%22%3A%22Heng%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22J%5Cu00fcrgen%22%2C%22lastName%22%3A%22Hesser%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jan%20Hendrik%22%2C%22lastName%22%3A%22Moltz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christian%22%2C%22lastName%22%3A%22Igel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%22%2C%22lastName%22%3A%22J%5Cu00e4ger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fucang%22%2C%22lastName%22%3A%22Jia%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Krishna%20Chaitanya%22%2C%22lastName%22%3A%22Kaluva%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mahendra%22%2C%22lastName%22%3A%22Khened%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ildoo%22%2C%22lastName%22%3A%22Kim%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jae-Hun%22%2C%22lastName%22%3A%22Kim%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sungwoong%22%2C%22lastName%22%3A%22Kim%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Simon%22%2C%22lastName%22%3A%22Kohl%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tomasz%22%2C%22lastName%22%3A%22Konopczynski%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Avinash%22%2C%22lastName%22%3A%22Kori%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ganapathy%22%2C%22lastName%22%3A%22Krishnamurthi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fan%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hongchao%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Junbo%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiaomeng%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22John%22%2C%22lastName%22%3A%22Lowengrub%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jun%22%2C%22lastName%22%3A%22Ma%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kevis-Kokitsi%22%2C%22lastName%22%3A%22Maninis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hans%22%2C%22lastName%22%3A%22Meine%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dorit%22%2C%22lastName%22%3A%22Merhof%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Akshay%22%2C%22lastName%22%3A%22Pai%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mathias%22%2C%22lastName%22%3A%22Perslev%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jens%22%2C%22lastName%22%3A%22Petersen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jordi%22%2C%22lastName%22%3A%22Pont-Tuset%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jin%22%2C%22lastName%22%3A%22Qi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiaojuan%22%2C%22lastName%22%3A%22Qi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Oliver%22%2C%22lastName%22%3A%22Rippel%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Karsten%22%2C%22lastName%22%3A%22Roth%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ignacio%22%2C%22lastName%22%3A%22Sarasua%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrea%22%2C%22lastName%22%3A%22Schenk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zengming%22%2C%22lastName%22%3A%22Shen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jordi%22%2C%22lastName%22%3A%22Torres%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christian%22%2C%22lastName%22%3A%22Wachinger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chunliang%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Leon%22%2C%22lastName%22%3A%22Weninger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jianrong%22%2C%22lastName%22%3A%22Wu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daguang%22%2C%22lastName%22%3A%22Xu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiaoping%22%2C%22lastName%22%3A%22Yang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Simon%20Chun-Ho%22%2C%22lastName%22%3A%22Yu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yading%22%2C%22lastName%22%3A%22Yuan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Miao%22%2C%22lastName%22%3A%22Yue%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Liping%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jorge%22%2C%22lastName%22%3A%22Cardoso%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Spyridon%22%2C%22lastName%22%3A%22Bakas%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rickmer%22%2C%22lastName%22%3A%22Braren%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Volker%22%2C%22lastName%22%3A%22Heinemann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christopher%22%2C%22lastName%22%3A%22Pal%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22An%22%2C%22lastName%22%3A%22Tang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Samuel%22%2C%22lastName%22%3A%22Kadoury%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Luc%22%2C%22lastName%22%3A%22Soler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bram%22%2C%22lastName%22%3A%22van%20Ginneken%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hayit%22%2C%22lastName%22%3A%22Greenspan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Leo%22%2C%22lastName%22%3A%22Joskowicz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bjoern%22%2C%22lastName%22%3A%22Menze%22%7D%5D%2C%22abstractNote%22%3A%22In%20this%20work%2C%20we%20report%20the%20set-up%20and%20results%20of%20the%20Liver%20Tumor%20Segmentation%20Benchmark%20%28LiTS%29%2C%20which%20was%20organized%20in%20conjunction%20with%20the%20IEEE%20International%20Symposium%20on%20Biomedical%20Imaging%20%28ISBI%29%202017%20and%20the%20International%20Conferences%20on%20Medical%20Image%20Computing%20and%20Computer-Assisted%20Intervention%20%28MICCAI%29%202017%20and%202018.%20The%20image%20dataset%20is%20diverse%20and%20contains%20primary%20and%20secondary%20tumors%20with%20varied%20sizes%20and%20appearances%20with%20various%20lesion-to-background%20levels%20%28hyper-%5C%2Fhypo-dense%29%2C%20created%20in%20collaboration%20with%20seven%20hospitals%20and%20research%20institutions.%20Seventy-five%20submitted%20liver%20and%20liver%20tumor%20segmentation%20algorithms%20were%20trained%20on%20a%20set%20of%20131%20computed%20tomography%20%28CT%29%20volumes%20and%20were%20tested%20on%2070%20unseen%20test%20images%20acquired%20from%20different%20patients.%20We%20found%20that%20not%20a%20single%20algorithm%20performed%20best%20for%20both%20liver%20and%20liver%20tumors%20in%20the%20three%20events.%20The%20best%20liver%20segmentation%20algorithm%20achieved%20a%20Dice%20score%20of%200.963%2C%20whereas%2C%20for%20tumor%20segmentation%2C%20the%20best%20algorithms%20achieved%20Dices%20scores%20of%200.674%20%28ISBI%202017%29%2C%200.702%20%28MICCAI%202017%29%2C%20and%200.739%20%28MICCAI%202018%29.%20Retrospectively%2C%20we%20performed%20additional%20analysis%20on%20liver%20tumor%20detection%20and%20revealed%20that%20not%20all%20top-performing%20segmentation%20algorithms%20worked%20well%20for%20tumor%20detection.%20The%20best%20liver%20tumor%20detection%20method%20achieved%20a%20lesion-wise%20recall%20of%200.458%20%28ISBI%202017%29%2C%200.515%20%28MICCAI%202017%29%2C%20and%200.554%20%28MICCAI%202018%29%2C%20indicating%20the%20need%20for%20further%20research.%20LiTS%20remains%20an%20active%20benchmark%20and%20resource%20for%20research%2C%20e.g.%2C%20contributing%20the%20liver-related%20segmentation%20tasks%20in%20http%3A%5C%2F%5C%2Fmedicaldecathlon.com%5C%2F.%20In%20addition%2C%20both%20data%20and%20online%20evaluation%20are%20accessible%20via%20https%3A%5C%2F%5C%2Fcompetitions.codalab.org%5C%2Fcompetitions%5C%2F17094.%22%2C%22date%22%3A%222023-02-01%22%2C%22language%22%3A%22%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.media.2022.102680%22%2C%22ISSN%22%3A%221361-8415%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.sciencedirect.com%5C%2Fscience%5C%2Farticle%5C%2Fpii%5C%2FS1361841522003085%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T12%3A15%3A13Z%22%7D%7D%2C%7B%22key%22%3A%22C65QU6QC%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22L%5Cu00fcth%20et%20al.%22%2C%22parsedDate%22%3A%222023-01-05%22%2C%22numChildren%22%3A2%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BL%26%23xFC%3Bth%2C%20C.%20T.%2C%20Zimmerer%2C%20D.%2C%20Koehler%2C%20G.%2C%20Jaeger%2C%20P.%20F.%2C%20Isensee%2C%20F.%2C%20Petersen%2C%20J.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20H.%20%282023%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BCRADL%3A%20Contrastive%20Representations%20for%20Unsupervised%20Anomaly%20Detection%20and%20Localization%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2301.02126%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2301.02126%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2301.02126%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22CRADL%3A%20Contrastive%20Representations%20for%20Unsupervised%20Anomaly%20Detection%20and%20Localization%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Carsten%20T.%22%2C%22lastName%22%3A%22L%5Cu00fcth%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Zimmerer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gregor%22%2C%22lastName%22%3A%22Koehler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%20F.%22%2C%22lastName%22%3A%22Jaeger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jens%22%2C%22lastName%22%3A%22Petersen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22Unsupervised%20anomaly%20detection%20in%20medical%20imaging%20aims%20to%20detect%20and%20localize%20arbitrary%20anomalies%20without%20requiring%20annotated%20anomalous%20data%20during%20training.%20Often%2C%20this%20is%20achieved%20by%20learning%20a%20data%20distribution%20of%20normal%20samples%20and%20detecting%20anomalies%20as%20regions%20in%20the%20image%20which%20deviate%20from%20this%20distribution.%20Most%20current%20state-of-the-art%20methods%20use%20latent%20variable%20generative%20models%20operating%20directly%20on%20the%20images.%20However%2C%20generative%20models%20have%20been%20shown%20to%20mostly%20capture%20low-level%20features%2C%20s.a.%20pixel-intensities%2C%20instead%20of%20rich%20semantic%20features%2C%20which%20also%20applies%20to%20their%20representations.%20We%20circumvent%20this%20problem%20by%20proposing%20CRADL%20whose%20core%20idea%20is%20to%20model%20the%20distribution%20of%20normal%20samples%20directly%20in%20the%20low-dimensional%20representation%20space%20of%20an%20encoder%20trained%20with%20a%20contrastive%20pretext-task.%20By%20utilizing%20the%20representations%20of%20contrastive%20learning%2C%20we%20aim%20to%20fix%20the%20over-fixation%20on%20low-level%20features%20and%20learn%20more%20semantic-rich%20representations.%20Our%20experiments%20on%20anomaly%20detection%20and%20localization%20tasks%20using%20three%20distinct%20evaluation%20datasets%20show%20that%201%29%20contrastive%20representations%20are%20superior%20to%20representations%20of%20generative%20latent%20variable%20models%20and%202%29%20the%20CRADL%20framework%20shows%20competitive%20or%20superior%20performance%20to%20state-of-the-art.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2301.02126%22%2C%22date%22%3A%222023-01-05%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2301.02126%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2301.02126%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T14%3A18%3A29Z%22%7D%7D%2C%7B%22key%22%3A%22W2QZRU5Z%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A9737705%2C%22username%22%3A%22Niebelsa%22%2C%22name%22%3A%22%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fniebelsa%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Ma%5Cu0161ka%20et%20al.%22%2C%22parsedDate%22%3A%222023%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BMa%26%23x161%3Bka%2C%20M.%2C%20Ulman%2C%20V.%2C%20Delgado-Rodriguez%2C%20P.%2C%20G%26%23xF3%3Bmez-de-Mariscal%2C%20E.%2C%20Ne%26%23x10D%3Basov%26%23xE1%3B%2C%20T.%2C%20Guerrero%20Pe%26%23xF1%3Ba%2C%20F.%20A.%2C%20Ren%2C%20T.%20I.%2C%20Meyerowitz%2C%20E.%20M.%2C%20Scherr%2C%20T.%2C%20L%26%23xF6%3Bffler%2C%20K.%2C%20Mikut%2C%20R.%2C%20Guo%2C%20T.%2C%20Wang%2C%20Y.%2C%20Allebach%2C%20J.%20P.%2C%20Bao%2C%20R.%2C%20Al-Shakarji%2C%20N.%20M.%2C%20Rahmon%2C%20G.%2C%20Toubal%2C%20I.%20E.%2C%20Palaniappan%2C%20K.%2C%20%26%23x2026%3B%20Ortiz-de-Sol%26%23xF3%3Brzano%2C%20C.%20%282023%29.%20%26lt%3Bb%26gt%3BThe%20Cell%20Tracking%20Challenge%3A%2010%20years%20of%20objective%20benchmarking%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Bi%26gt%3BNature%20Methods%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B20%26lt%3B%5C%2Fi%26gt%3B%287%29%2C%201010%26%23x2013%3B1020.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1038%5C%2Fs41592-023-01879-y%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1038%5C%2Fs41592-023-01879-y%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22The%20Cell%20Tracking%20Challenge%3A%2010%20years%20of%20objective%20benchmarking%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Ma%5Cu0161ka%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Vladim%5Cu00edr%22%2C%22lastName%22%3A%22Ulman%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pablo%22%2C%22lastName%22%3A%22Delgado-Rodriguez%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Estibaliz%22%2C%22lastName%22%3A%22G%5Cu00f3mez-de-Mariscal%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tereza%22%2C%22lastName%22%3A%22Ne%5Cu010dasov%5Cu00e1%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fidel%20A.%22%2C%22lastName%22%3A%22Guerrero%20Pe%5Cu00f1a%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tsang%20Ing%22%2C%22lastName%22%3A%22Ren%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Elliot%20M.%22%2C%22lastName%22%3A%22Meyerowitz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tim%22%2C%22lastName%22%3A%22Scherr%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Katharina%22%2C%22lastName%22%3A%22L%5Cu00f6ffler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ralf%22%2C%22lastName%22%3A%22Mikut%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tianqi%22%2C%22lastName%22%3A%22Guo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yin%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jan%20P.%22%2C%22lastName%22%3A%22Allebach%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rina%22%2C%22lastName%22%3A%22Bao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Noor%20M.%22%2C%22lastName%22%3A%22Al-Shakarji%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gani%22%2C%22lastName%22%3A%22Rahmon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Imad%20Eddine%22%2C%22lastName%22%3A%22Toubal%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kannappan%22%2C%22lastName%22%3A%22Palaniappan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Filip%22%2C%22lastName%22%3A%22Lux%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Petr%22%2C%22lastName%22%3A%22Matula%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ko%22%2C%22lastName%22%3A%22Sugawara%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klas%20E.%20G.%22%2C%22lastName%22%3A%22Magnusson%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Layton%22%2C%22lastName%22%3A%22Aho%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrew%20R.%22%2C%22lastName%22%3A%22Cohen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Assaf%22%2C%22lastName%22%3A%22Arbelle%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tal%22%2C%22lastName%22%3A%22Ben-Haim%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tammy%20Riklin%22%2C%22lastName%22%3A%22Raviv%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%20F.%22%2C%22lastName%22%3A%22J%5Cu00e4ger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yanming%22%2C%22lastName%22%3A%22Zhu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Cristina%22%2C%22lastName%22%3A%22Ederra%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ainhoa%22%2C%22lastName%22%3A%22Urbiola%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Erik%22%2C%22lastName%22%3A%22Meijering%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alexandre%22%2C%22lastName%22%3A%22Cunha%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Arrate%22%2C%22lastName%22%3A%22Mu%5Cu00f1oz-Barrutia%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michal%22%2C%22lastName%22%3A%22Kozubek%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Carlos%22%2C%22lastName%22%3A%22Ortiz-de-Sol%5Cu00f3rzano%22%7D%5D%2C%22abstractNote%22%3A%22Abstract%5Cn%20%20%20%20%20%20%20%20%20%20%20%20The%20Cell%20Tracking%20Challenge%20is%20an%20ongoing%20benchmarking%20initiative%20that%20has%20become%20a%20reference%20in%20cell%20segmentation%20and%20tracking%20algorithm%20development.%20Here%2C%20we%20present%20a%20significant%20number%20of%20improvements%20introduced%20in%20the%20challenge%20since%20our%202017%20report.%20These%20include%20the%20creation%20of%20a%20new%20segmentation-only%20benchmark%2C%20the%20enrichment%20of%20the%20dataset%20repository%20with%20new%20datasets%20that%20increase%20its%20diversity%20and%20complexity%2C%20and%20the%20creation%20of%20a%20silver%20standard%20reference%20corpus%20based%20on%20the%20most%20competitive%20results%2C%20which%20will%20be%20of%20particular%20interest%20for%20data-hungry%20deep%20learning-based%20strategies.%20Furthermore%2C%20we%20present%20the%20up-to-date%20cell%20segmentation%20and%20tracking%20leaderboards%2C%20an%20in-depth%20analysis%20of%20the%20relationship%20between%20the%20performance%20of%20the%20state-of-the-art%20methods%20and%20the%20properties%20of%20the%20datasets%20and%20annotations%2C%20and%20two%20novel%2C%20insightful%20studies%20about%20the%20generalizability%20and%20the%20reusability%20of%20top-performing%20methods.%20These%20studies%20provide%20critical%20practical%20conclusions%20for%20both%20developers%20and%20users%20of%20traditional%20and%20machine%20learning-based%20cell%20segmentation%20and%20tracking%20algorithms.%22%2C%22date%22%3A%2207%5C%2F2023%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1038%5C%2Fs41592-023-01879-y%22%2C%22ISSN%22%3A%221548-7091%2C%201548-7105%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.nature.com%5C%2Farticles%5C%2Fs41592-023-01879-y%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T12%3A45%3A54Z%22%7D%7D%2C%7B%22key%22%3A%222M8FVBVP%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A9737705%2C%22username%22%3A%22Niebelsa%22%2C%22name%22%3A%22%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fniebelsa%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Roy%20et%20al.%22%2C%22parsedDate%22%3A%222023%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BRoy%2C%20S.%2C%20Koehler%2C%20G.%2C%20Ulrich%2C%20C.%2C%20Baumgartner%2C%20M.%2C%20Petersen%2C%20J.%2C%20Isensee%2C%20F.%2C%20Jaeger%2C%20P.%20F.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20%282023%29.%20%26lt%3Bb%26gt%3BMedNeXt%3A%20Transformer-driven%20Scaling%20of%20ConvNets%20for%20Medical%20Image%20Segmentation%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FARXIV.2303.09975%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FARXIV.2303.09975%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22MedNeXt%3A%20Transformer-driven%20Scaling%20of%20ConvNets%20for%20Medical%20Image%20Segmentation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Saikat%22%2C%22lastName%22%3A%22Roy%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gregor%22%2C%22lastName%22%3A%22Koehler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Baumgartner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jens%22%2C%22lastName%22%3A%22Petersen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%20F.%22%2C%22lastName%22%3A%22Jaeger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22There%20has%20been%20exploding%20interest%20in%20embracing%20Transformer-based%20architectures%20for%20medical%20image%20segmentation.%20However%2C%20the%20lack%20of%20large-scale%20annotated%20medical%20datasets%20make%20achieving%20performances%20equivalent%20to%20those%20in%20natural%20images%20challenging.%20Convolutional%20networks%2C%20in%20contrast%2C%20have%20higher%20inductive%20biases%20and%20consequently%2C%20are%20easily%20trainable%20to%20high%20performance.%20Recently%2C%20the%20ConvNeXt%20architecture%20attempted%20to%20modernize%20the%20standard%20ConvNet%20by%20mirroring%20Transformer%20blocks.%20In%20this%20work%2C%20we%20improve%20upon%20this%20to%20design%20a%20modernized%20and%20scalable%20convolutional%20architecture%20customized%20to%20challenges%20of%20data-scarce%20medical%20settings.%20We%20introduce%20MedNeXt%2C%20a%20Transformer-inspired%20large%20kernel%20segmentation%20network%20which%20introduces%20-%201%29%20A%20fully%20ConvNeXt%203D%20Encoder-Decoder%20Network%20for%20medical%20image%20segmentation%2C%202%29%20Residual%20ConvNeXt%20up%20and%20downsampling%20blocks%20to%20preserve%20semantic%20richness%20across%20scales%2C%203%29%20A%20novel%20technique%20to%20iteratively%20increase%20kernel%20sizes%20by%20upsampling%20small%20kernel%20networks%2C%20to%20prevent%20performance%20saturation%20on%20limited%20medical%20data%2C%204%29%20Compound%20scaling%20at%20multiple%20levels%20%28depth%2C%20width%2C%20kernel%20size%29%20of%20MedNeXt.%20This%20leads%20to%20state-of-the-art%20performance%20on%204%20tasks%20on%20CT%20and%20MRI%20modalities%20and%20varying%20dataset%20sizes%2C%20representing%20a%20modernized%20deep%20architecture%20for%20medical%20image%20segmentation.%20Our%20code%20is%20made%20publicly%20available%20at%3A%20https%3A%5C%2F%5C%2Fgithub.com%5C%2FMIC-DKFZ%5C%2FMedNeXt.%22%2C%22date%22%3A%222023%22%2C%22language%22%3A%22%22%2C%22DOI%22%3A%2210.48550%5C%2FARXIV.2303.09975%22%2C%22ISSN%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2303.09975%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-05-02T09%3A03%3A26Z%22%7D%7D%2C%7B%22key%22%3A%22HKU8NPWR%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Ulrich%20et%20al.%22%2C%22parsedDate%22%3A%222023%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BUlrich%2C%20C.%2C%20Isensee%2C%20F.%2C%20Wald%2C%20T.%2C%20Zenk%2C%20M.%2C%20Baumgartner%2C%20M.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20H.%20%282023%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BMultiTalent%3A%20A%20Multi-Dataset%20Approach%20to%20Medical%20Image%20Segmentation%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B%20%28Vol.%2014222%2C%20pp.%20648%26%23x2013%3B658%29.%20https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-43898-1_62%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22bookSection%22%2C%22title%22%3A%22MultiTalent%3A%20A%20Multi-Dataset%20Approach%20to%20Medical%20Image%20Segmentation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tassilo%22%2C%22lastName%22%3A%22Wald%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maximilian%22%2C%22lastName%22%3A%22Zenk%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Baumgartner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%5D%2C%22abstractNote%22%3A%22The%20medical%20imaging%20community%20generates%20a%20wealth%20of%20datasets%2C%20many%20of%20which%20are%20openly%20accessible%20and%20annotated%20for%20specific%20diseases%20and%20tasks%20such%20as%20multi-organ%20or%20lesion%20segmentation.%20Current%20practices%20continue%20to%20limit%20model%20training%20and%20supervised%20pre-training%20to%20one%20or%20a%20few%20similar%20datasets%2C%20neglecting%20the%20synergistic%20potential%20of%20other%20available%20annotated%20data.%20We%20propose%20MultiTalent%2C%20a%20method%20that%20leverages%20multiple%20CT%20datasets%20with%20diverse%20and%20conflicting%20class%20definitions%20to%20train%20a%20single%20model%20for%20a%20comprehensive%20structure%20segmentation.%20Our%20results%20demonstrate%20improved%20segmentation%20performance%20compared%20to%20previous%20related%20approaches%2C%20systematically%2C%20also%20compared%20to%20single%20dataset%20training%20using%20state-of-the-art%20methods%2C%20especially%20for%20lesion%20segmentation%20and%20other%20challenging%20structures.%20We%20show%20that%20MultiTalent%20also%20represents%20a%20powerful%20foundation%20model%20that%20offers%20a%20superior%20pre-training%20for%20various%20segmentation%20tasks%20compared%20to%20commonly%20used%20supervised%20or%20unsupervised%20pre-training%20baselines.%20Our%20findings%20offer%20a%20new%20direction%20for%20the%20medical%20imaging%20community%20to%20effectively%20utilize%20the%20wealth%20of%20available%20data%20for%20improved%20segmentation%20performance.%20The%20code%20and%20model%20weights%20will%20be%20published%20here%3A%20%5Btba%5D%22%2C%22bookTitle%22%3A%22%22%2C%22date%22%3A%222023%22%2C%22language%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2303.14444%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222025-02-03T12%3A30%3A14Z%22%7D%7D%2C%7B%22key%22%3A%22SR9D5MKA%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Isensee%20et%20al.%22%2C%22parsedDate%22%3A%222023%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BIsensee%2C%20F.%2C%20Ulrich%2C%20C.%2C%20Wald%2C%20T.%2C%20%26amp%3B%20Maier-Hein%2C%20K.%20H.%20%282023%29.%20%26lt%3Bb%26gt%3BExtending%20nnU-Net%20Is%20All%20You%20Need%26lt%3B%5C%2Fb%26gt%3B.%20In%20T.%20M.%20Deserno%2C%20H.%20Handels%2C%20A.%20Maier%2C%20K.%20Maier-Hein%2C%20C.%20Palm%2C%20%26amp%3B%20T.%20Tolxdorff%20%28Eds.%29%2C%20%26lt%3Bi%26gt%3BBildverarbeitung%20f%26%23xFC%3Br%20die%20Medizin%202023%26lt%3B%5C%2Fi%26gt%3B%20%28pp.%2012%26%23x2013%3B17%29.%20Springer%20Fachmedien.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-658-41657-7_7%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-658-41657-7_7%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Extending%20nnU-Net%20Is%20All%20You%20Need%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Constantin%22%2C%22lastName%22%3A%22Ulrich%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tassilo%22%2C%22lastName%22%3A%22Wald%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%20H.%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Thomas%20M.%22%2C%22lastName%22%3A%22Deserno%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Heinz%22%2C%22lastName%22%3A%22Handels%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Andreas%22%2C%22lastName%22%3A%22Maier%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Christoph%22%2C%22lastName%22%3A%22Palm%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Thomas%22%2C%22lastName%22%3A%22Tolxdorff%22%7D%5D%2C%22abstractNote%22%3A%22Semantic%20segmentation%20is%20one%20of%20the%20most%20popular%20research%20areas%20in%20medical%20image%20computing.%20Perhaps%20surprisingly%2C%20despite%20its%20conceptualization%20dating%20back%20to%202018%2C%20nnU-Net%20continues%20to%20provide%20competitive%20out-of-the-box%20solutions%20for%20a%20broad%20variety%20of%20segmentation%20problems%20and%20is%20regularly%20used%20as%20a%20development%20framework%20for%20challenge-winning%20algorithms.%20Here%2C%20we%20use%20nnU-Net%20to%20participate%20in%20the%20AMOS-2022%20challenge%2C%20which%20was%20a%20MICCAI22%20challenge%20and%20comes%20with%20a%20unique%20set%20of%20tasks%3A%20not%20only%20is%20the%20dataset%20one%20of%20the%20largest%20ever%20created%20and%20boasts%2015%20target%20structures%2C%20but%20the%20second%20task%20of%20the%20competition%20also%20requires%20submitted%20solutions%20to%20handle%20both%20MRI%20and%20CT%20scans.%20Through%20careful%20modification%20of%20nnU-net%5Cu2019s%20hyperparameters%2C%20the%20addition%20of%20residual%20connections%20in%20the%20encoder%20and%20the%20design%20of%20a%20custom%20postprocessing%20strategy%2C%20we%20were%20able%20to%20substantially%20improve%20upon%20the%20nnU-Net%20baseline.%20Advances%20in%20GPU%20memory%20capacity%20and%20processing%20speed%20allowed%20larger%20models%20and%20batch%20sizes%20than%20the%20default%20nnU-Net.%20Our%20final%20ensemble%20achieves%20Dice%20scores%20of%2090.13%20for%20Task%201%20%28CT%29%20and%2089.06%20for%20Task%202%20%28CT%2BMRI%29%20in%20a%205-fold%20cross-validation%20on%20the%20provided%20training%20cases.We%20submitted%20almost%20the%20same%20solution%20for%20both%20tasks%2C%20but%20adjusted%20the%20intensity%20normalization%20for%20task%202%20to%20account%20for%20the%20additional%20MRI%20images.%20For%20the%20final%20testing%20stage%2C%20participants%20were%20asked%20to%20provide%20a%20docker%20container%20with%20their%20final%20solution%20to%20be%20applied%20to%20an%20unpublished%20test%20set.%20On%20both%20tasks%2C%20our%20nnU-Net%20extension%20achieved%20the%20first%20place%20by%20a%20wide%20margin.%22%2C%22date%22%3A%222023%22%2C%22proceedingsTitle%22%3A%22Bildverarbeitung%20f%5Cu00fcr%20die%20Medizin%202023%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22de%22%2C%22DOI%22%3A%2210.1007%5C%2F978-3-658-41657-7_7%22%2C%22ISBN%22%3A%22978-3-658-41657-7%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T14%3A04%3A00Z%22%7D%7D%2C%7B%22key%22%3A%22MSUD5Z65%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Klein%20et%20al.%22%2C%22parsedDate%22%3A%222023%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BKlein%2C%20L.%2C%20Ziegler%2C%20S.%2C%20Laufer%2C%20F.%2C%20Debus%2C%20C.%2C%20G%26%23xF6%3Btz%2C%20M.%2C%20Maier-Hein%2C%20K.%2C%20Paetzold%2C%20U.%2C%20Isensee%2C%20F.%2C%20%26amp%3B%20Jaeger%2C%20P.%20%282023%29.%20%26lt%3Bb%26gt%3BUnderstanding%20Scalable%20Perovskite%20Solar%20Cell%20Manufacturing%20with%20Explainable%20AI%26lt%3B%5C%2Fb%26gt%3B.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fpublikationen.bibliothek.kit.edu%5C%2F1000167169%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fpublikationen.bibliothek.kit.edu%5C%2F1000167169%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22webpage%22%2C%22title%22%3A%22Understanding%20Scalable%20Perovskite%20Solar%20Cell%20Manufacturing%20with%20Explainable%20AI%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lukas%22%2C%22lastName%22%3A%22Klein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sebastian%22%2C%22lastName%22%3A%22Ziegler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Felix%22%2C%22lastName%22%3A%22Laufer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Charlotte%22%2C%22lastName%22%3A%22Debus%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Markus%22%2C%22lastName%22%3A%22G%5Cu00f6tz%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Klaus%22%2C%22lastName%22%3A%22Maier-Hein%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ulrich%22%2C%22lastName%22%3A%22Paetzold%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%22%2C%22lastName%22%3A%22Jaeger%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222023%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpublikationen.bibliothek.kit.edu%5C%2F1000167169%22%2C%22language%22%3A%22de%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-03-04T12%3A29%3A27Z%22%7D%7D%2C%7B%22key%22%3A%22ZXFX2AHT%22%2C%22library%22%3A%7B%22id%22%3A4725570%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Yang%20et%20al.%22%2C%22parsedDate%22%3A%222023%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BYang%2C%20L.%2C%20Kumar%2C%20P.%2C%20Sengupta%2C%20A.%2C%20Farnoud%2C%20A.%2C%20Shen%2C%20R.%2C%20Trofimova%2C%20D.%2C%20Ziegler%2C%20S.%2C%20Davoudi%2C%20N.%2C%20Doryab%2C%20A.%2C%20Yildirim%2C%20A.%2C%20Schiller%2C%20H.%2C%20Razansky%2C%20D.%2C%20Piraud%2C%20M.%2C%20Liu%2C%20Q.%2C%20Rehberg%2C%20M.%2C%20Stoeger%2C%20T.%2C%20Burgstaller%2C%20G.%2C%20Kreyling%2C%20W.%2C%20Isensee%2C%20F.%2C%20%26amp%3B%20Schmid%2C%20O.%20%282023%29.%20%26lt%3Bi%26gt%3B%26lt%3Bb%26gt%3B%26lt%3Bspan%20style%3D%26quot%3Bfont-style%3Anormal%3B%26quot%3B%26gt%3BMultimodal%20imaging%20and%20deep%20learning%20unveil%20pulmonary%20delivery%20profiles%20and%20acinar%20migration%20of%20tissue-resident%20macrophages%20in%20the%20lun%26lt%3B%5C%2Fspan%26gt%3B%26lt%3B%5C%2Fb%26gt%3B%26lt%3B%5C%2Fi%26gt%3B.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.21203%5C%2Frs.3.rs-2994336%5C%2Fv1%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.21203%5C%2Frs.3.rs-2994336%5C%2Fv1%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22report%22%2C%22title%22%3A%22Multimodal%20imaging%20and%20deep%20learning%20unveil%20pulmonary%20delivery%20profiles%20and%20acinar%20migration%20of%20tissue-resident%20macrophages%20in%20the%20lun%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lin%22%2C%22lastName%22%3A%22Yang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pramod%22%2C%22lastName%22%3A%22Kumar%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Arunima%22%2C%22lastName%22%3A%22Sengupta%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ali%22%2C%22lastName%22%3A%22Farnoud%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ruolin%22%2C%22lastName%22%3A%22Shen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Darya%22%2C%22lastName%22%3A%22Trofimova%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sebastian%22%2C%22lastName%22%3A%22Ziegler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Neda%22%2C%22lastName%22%3A%22Davoudi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ali%22%2C%22lastName%22%3A%22Doryab%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ali%22%2C%22lastName%22%3A%22Yildirim%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Herbert%22%2C%22lastName%22%3A%22Schiller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%22%2C%22lastName%22%3A%22Razansky%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marie%22%2C%22lastName%22%3A%22Piraud%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Qiongliang%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Markus%22%2C%22lastName%22%3A%22Rehberg%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tobias%22%2C%22lastName%22%3A%22Stoeger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gerald%22%2C%22lastName%22%3A%22Burgstaller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Wolfgang%22%2C%22lastName%22%3A%22Kreyling%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22Isensee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Otmar%22%2C%22lastName%22%3A%22Schmid%22%7D%5D%2C%22abstractNote%22%3A%22Holistic%20deciphering%20of%20spatially-resolved%20delivery%20and%20biokinetics%20of%20nanoparticles%20%28NPs%29%20in%20the%20lung%2C%20along%20with%20the%20mobility%20of%20tissue-resident%20macrophages%20%28TRMs%29%20and%20their%20role%20in%20regulating%20NP%20cellular%20fate%2C%20remains%20unclear.%20Multimodal%20imaging%20and%20deep%20learning%20were%20applied%20to%20elucidate%20the%20longitudinal%20inter-%20and%20intra-acinar%20deposition%20features%20and%20regional%20dosimetry%20of%20NPs.%20The%20initial%20NP%20distribution%20patterns%20depended%20significantly%20on%20the%20pulmonary%20delivery%20routes%20and%20were%20most%20uniform%20for%20aerosol%20inhalation.%20Artificial%20intelligence-driven%203D%20airway%20segmentation%20enabled%20direct%20determination%20of%20bronchial%20and%20acinar%20NP%20dose.%20Longitudinal%20imaging%20uncovered%20an%20intra-acinar%20NP%20kinetics%20profile%20independent%20of%20delivery%20route.%20Contrary%20to%20the%20traditional%20notion%20of%20passive%20diffusion%2C%20this%20study%20reveals%20that%20long-term%20NP%20lung%20retention%20is%20facilitated%20by%20intra-acinar%20NP%20transport%20mediated%20by%20phagocytosis%20and%20patrolling%20of%20TRMs.%20Overall%2C%20this%20study%20elucidates%20the%20complexities%20of%20NP-lung%20delivery%20features%20and%20TRM%20immunity%20on%20the%20fate%20of%20biopersistent%20NPs.%22%2C%22reportNumber%22%3A%22%22%2C%22reportType%22%3A%22%22%2C%22institution%22%3A%22%22%2C%22date%22%3A%222023%22%2C%22language%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.21203%5C%2Frs.3.rs-2994336%5C%2Fv1%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-02-15T10%3A32%3A21Z%22%7D%7D%5D%7D
Isensee, F., Rokuss, M., Krämer, L., Dinkelacker, S., Ravindran, A., Stritzke, F., Hamm, B., Wald, T., Langenberg, M., Ulrich, C., Deissler, J., Floca, R., & Maier-Hein, K. (2025). nnInteractive: Redefining 3D Promptable Segmentation (arXiv:2503.08373). arXiv. https://doi.org/10.48550/arXiv.2503.08373
Bassi, P. R. A. S., Li, W., Tang, Y., Isensee, F., Wang, Z., Chen, J., Chou, Y.-C., Kirchhoff, Y., Rokuss, M., Huang, Z., Ye, J., He, J., Wald, T., Ulrich, C., Baumgartner, M., Roy, S., Maier-Hein, K. H., Jaeger, P., Ye, Y., … Zhou, Z. (2025). Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation? (arXiv:2411.03670). arXiv. https://doi.org/10.48550/arXiv.2411.03670
Isensee, F., Kirchhoff, Y., Kraemer, L., Rokuss, M., Ulrich, C., & Maier-Hein, K. H. (2024). Scaling nnU-Net for CBCT Segmentation (arXiv:2411.17213). arXiv. https://doi.org/10.48550/arXiv.2411.17213
Yang, L., Liu, Q., Kumar, P., Sengupta, A., Farnoud, A., Shen, R., Trofimova, D., Ziegler, S., Davoudi, N., Doryab, A., Yildirim, A. Ö., Diefenbacher, M. E., Schiller, H. B., Razansky, D., Piraud, M., Burgstaller, G., Kreyling, W. G., Isensee, F., Rehberg, M., … Schmid, O. (2024). LungVis 1.0: an automatic AI-powered 3D imaging ecosystem unveils spatial profiling of nanoparticle delivery and acinar migration of lung macrophages. Nature Communications, 15(1), 10138. https://doi.org/10.1038/s41467-024-54267-1
Wald, T., Ulrich, C., Köhler, G., Zimmerer, D., Denner, S., Baumgartner, M., Isensee, F., Jaini, P., & Maier-Hein, K. H. (2024). Decoupling Semantic Similarity from Spatial Alignment for Neural Networks (arXiv:2410.23107). arXiv. https://doi.org/10.48550/arXiv.2410.23107
Klein, L., Ziegler, S., Gerst, F., Morgenroth, Y., Gotkowski, K., Schöniger, E., Heni, M., Kipke, N., Friedland, D., Seiler, A., Geibelt, E., Yamazaki, H., Häring, H. U., Wagner, S., Nadalin, S., Königsrainer, A., Mihaljević, A. L., Hartmann, D., Fend, F., … Wagner, R. (2024). Explainable AI-based analysis of human pancreas sections identifies traits of type 2 diabetes. medRxiv. https://doi.org/10.1101/2024.10.23.24315937
Rokuss, M., Kovacs, B., Kirchhoff, Y., Xiao, S., Ulrich, C., Maier-Hein, K. H., & Isensee, F. (2024). From FDG to PSMA: A Hitchhiker’s Guide to Multitracer, Multicenter Lesion Segmentation in PET/CT Imaging (arXiv:2409.09478). arXiv. https://doi.org/10.48550/arXiv.2409.09478
Rokuss, M., Kirchhoff, Y., Roy, S., Kovacs, B., Ulrich, C., Wald, T., Zenk, M., Denner, S., Isensee, F., Vollmuth, P., Kleesiek, J., & Maier-Hein, K. (2024). Longitudinal Segmentation of MS Lesions via Temporal Difference Weighting (arXiv:2409.13416). arXiv. https://doi.org/10.48550/arXiv.2409.13416
Kovacs, B., Xiao, S., Rokuss, M., Ulrich, C., Isensee, F., & Maier-Hein, K. H. (2024). Data-Centric Strategies for Overcoming PET/CT Heterogeneity: Insights from the AutoPET III Lesion Segmentation Challenge (arXiv:2409.10120). arXiv. https://doi.org/10.48550/arXiv.2409.10120
Rädsch, T., Reinke, A., Weru, V., Tizabi, M. D., Heller, N., Isensee, F., Kopp-Schneider, A., & Maier-Hein, L. (2024). Quality Assured: Rethinking Annotation Strategies in Imaging AI (arXiv:2407.17596). arXiv. https://doi.org/10.48550/arXiv.2407.17596
Isensee, F., Wald, T., Ulrich, C., Baumgartner, M., Roy, S., Maier-Hein, K., & Jaeger, P. F. (2024). nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation (arXiv:2404.09556). arXiv. https://doi.org/10.48550/arXiv.2404.09556
Kirchhoff, Y., Rokuss, M. R., Roy, S., Kovacs, B., Ulrich, C., Wald, T., Zenk, M., Vollmuth, P., Kleesiek, J., Isensee, F., & Maier-Hein, K. (2024). Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures (arXiv:2404.03010). arXiv. https://doi.org/10.48550/arXiv.2404.03010
Wood, A. M., Abdallah, N., Heller, N., Benidir, T., Isensee, F., Tejpaul, R., Suk-Ouichai, C., Curry, C., You, A., Remer, E., Haywood, S., Campbell, S., Papanikolopoulos, N., & Weight, C. (2024). Fully Automated Versions of Clinically Validated Nephrometry Scores Demonstrate Superior Predictive Utility versus Human Scores. BJU International, 133(6), 690–698. https://doi.org/10.1111/bju.16276
Yang, L., Kumar, P., Liu, Q., Chen, P., Li, C., Lüth, C., Krämer, L., Gabriel, C., Jeridi, A., Piraud, M., Stoeger, T., Staab-Weijnitz, C. a., Jäger, P., Rehberg, M., Isensee, F., & Schmid, O. (2024). Fresh Perspectives on Lung Morphometry and Pulmonary Drug Delivery: AI-powered 3D Imaging in Healthy and Fibrotic Murine Lungs. In B30. SCARRED FOR LIFE: TRANSLATIONAL RESEARCH IN INTERSTITIAL ABNORMALITIES AND LUNG FIBROSIS (Vol. 1–299, pp. A3242–A3242). American Thoracic Society. https://doi.org/10.1164/ajrccm-conference.2024.209.1_MeetingAbstracts.A3242
Yang, K., Musio, F., Ma, Y., Juchler, N., Paetzold, J. C., Al-Maskari, R., Höher, L., Li, H. B., Hamamci, I. E., Sekuboyina, A., Shit, S., Huang, H., Prabhakar, C., Rosa, E. de la, Waldmannstetter, D., Kofler, F., Navarro, F., Menten, M., Ezhov, I., … Menze, B. (2024). Benchmarking the CoW with the TopCoW Challenge: Topology-Aware Anatomical Segmentation of the Circle of Willis for CTA and MRA (arXiv:2312.17670). arXiv. https://doi.org/10.48550/arXiv.2312.17670
Ulrich, C., Knobloch, C., Holzschuh, J. C., Wald, T., Rokuss, M. R., Zenk, M., Fischer, M., Baumgartner, M., Isensee, F., & Maier-Hein, K. H. (2024). Mitigating False Predictions In Unreasonable Body Regions (arXiv:2404.15718). arXiv. https://doi.org/10.48550/arXiv.2404.15718
Gutsche, R., Lowis, C., Ziemons, K., Kocher, M., Ceccon, G., Brambilla, C. R., Shah, N. J., Langen, K., Galldiks, N., Isensee, F., & Lohmann, P. (2024). Deep learning-based amino acid PET brain tumor segmentation for automated response assessment in patients with brain tumors. Nuklearmedizin - NuclearMedicine, 63, L53. https://doi.org/10.1055/s-0044-1782321
Gotkowski, K., Lüth, C., Jäger, P. F., Ziegler, S., Krämer, L., Denner, S., Xiao, S., Disch, N., Maier-Hein, K. H., & Isensee, F. (2024). Embarrassingly Simple Scribble Supervision for 3D Medical Segmentation (arXiv:2403.12834). arXiv. https://doi.org/10.48550/arXiv.2403.12834
Reinke, A., Tizabi, M. D., Baumgartner, M., Eisenmann, M., Heckmann-Nötzel, D., Kavur, A. E., Rädsch, T., Sudre, C. H., Acion, L., Antonelli, M., Arbel, T., Bakas, S., Benis, A., Buettner, F., Cardoso, M. J., Cheplygina, V., Chen, J., Christodoulou, E., Cimini, B. A., … Maier-Hein, L. (2024). Understanding metric-related pitfalls in image analysis validation. Nature Methods, 1–13. https://doi.org/10.1038/s41592-023-02150-0
Maier-Hein, L., Reinke, A., Godau, P., Tizabi, M. D., Buettner, F., Christodoulou, E., Glocker, B., Isensee, F., Kleesiek, J., Kozubek, M., Reyes, M., Riegler, M. A., Wiesenfarth, M., Kavur, A. E., Sudre, C. H., Baumgartner, M., Eisenmann, M., Heckmann-Nötzel, D., Rädsch, T., … Jäger, P. F. (2024). Metrics reloaded: recommendations for image analysis validation. Nature Methods, 21(2), 195–212. https://doi.org/10.1038/s41592-023-02151-z
Yang, K., Musio, F., Ma, Y., Juchler, N., Paetzold, J. C., Al-Maskari, R., Höher, L., Li, H. B., Hamamci, I. E., Sekuboyina, A., Shit, S., Huang, H., Waldmannstetter, D., Kofler, F., Navarro, F., Menten, M., Ezhov, I., Rueckert, D., Vos, I., … Menze, B. (2024). TopCoW: Benchmarking Topology-Aware Anatomical Segmentation of the Circle of Willis (CoW) for CTA and MRA (arXiv:2312.17670). arXiv. https://doi.org/10.48550/arXiv.2312.17670
Gupta, S., da Assuncao Godinho, J. R., Gotkowski, K., & Isensee, F. (2024). Standardized and semiautomated workflow for 3D characterization of liberated particles. Powder Technology, 433, 119159. https://doi.org/10.1016/j.powtec.2023.119159
Lamm, L., Zufferey, S., Righetto, R. D., Wietrzynski, W., Yamauchi, K. A., Burt, A., Liu, Y., Zhang, H., Martinez-Sanchez, A., Ziegler, S., Isensee, F., Schnabel, J. A., Engel, B. D., & Peng, T. (2024). MemBrain v2: an end-to-end tool for the analysis of membranes in cryo-electron tomography. bioRxiv. https://doi.org/10.1101/2024.01.05.574336
Gotkowski, K., Gupta, S., Godinho, J. R. A., Tochtrop, C. G. S., Maier-Hein, K. H., & Isensee, F. (2024). ParticleSeg3D: A scalable out-of-the-box deep learning segmentation solution for individual particle characterization from micro CT images in mineral processing and recycling. Powder Technology, 434, 119286. https://doi.org/10.1016/j.powtec.2023.119286
Roy, S., Koehler, G., Baumgartner, M., Ulrich, C., Isensee, F., Jaeger, P. F., & Maier-Hein, K. (2024). Abstract: 3D Medical Image Segmentation with Transformer-based Scaling of ConvNets. In A. Maier, T. M. Deserno, H. Handels, K. Maier-Hein, C. Palm, & T. Tolxdorff (Eds.), Bildverarbeitung für die Medizin 2024 (pp. 79–79). Springer Fachmedien. https://doi.org/10.1007/978-3-658-44037-4_23
Koehler, G., Wald, T., Ulrich, C., Zimmerer, D., Jaeger, P. F., Franke, J. K., Kohl, S., Isensee, F., & Maier-Hein, K. H. (2024). RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 810–818. https://openaccess.thecvf.com/content/WACV2024/html/Kohler_RecycleNet_Latent_Feature_Recycling_Leads_to_Iterative_Decision_Refinement_WACV_2024_paper.html
Isensee, F., & Maier-Hein, K. H. (2023). Look Ma, no code: fine tuning nnU-Net for the AutoPET II challenge by only adjusting its JSON plans (arXiv:2309.13747). arXiv. https://doi.org/10.48550/arXiv.2309.13747
Kofler, F., Möller, H., Buchner, J. A., de la Rosa, E., Ezhov, I., Rosier, M., Mekki, I., Shit, S., Negwer, M., Al-Maskari, R., Ertürk, A., Vinayahalingam, S., Isensee, F., Pati, S., Rueckert, D., Kirschke, J. S., Ehrlich, S. K., Reinke, A., Menze, B., … Piraud, M. (2023). Panoptica -- instance-wise evaluation of 3D semantic and instance segmentation maps (arXiv:2312.02608). arXiv. https://doi.org/10.48550/arXiv.2312.02608
Kovacs, B., Netzer, N., Baumgartner, M., Schrader, A., Isensee, F., Weißer, C., Wolf, I., Görtz, M., Jaeger, P. F., Schütz, V., Floca, R., Gnirs, R., Stenzinger, A., Hohenfellner, M., Schlemmer, H.-P., Bonekamp, D., & Maier-Hein, K. H. (2023). Addressing image misalignments in multi-parametric prostate MRI for enhanced computer-aided diagnosis of prostate cancer. Scientific Reports, 13(1), 19805. https://doi.org/10.1038/s41598-023-46747-z
Klein, L., Ziegler, S., Laufer, F., Debus, C., Götz, M., Maier‐Hein, K., Paetzold, U. W., Isensee, F., & Jäger, P. F. (2023). Discovering Process Dynamics for Scalable Perovskite Solar Cell Manufacturing with Explainable AI. Advanced Materials, 2307160. https://doi.org/10.1002/adma.202307160
Abdallah, N., Wood, A., Benidir, T., Heller, N., Isensee, F., Tejpaul, R., Corrigan, D., Suk-Ouichai, C., Struyk, G., Moore, K., Venkatesh, N., Ergun, O., You, A., Campbell, R., Remer, E. M., Haywood, S., Krishnamurthi, V., Abouassaly, R., Campbell, S., … Weight, C. J. (2023). AI-generated R.E.N.A.L.+ Score Surpasses Human-generated Score in Predicting Renal Oncologic Outcomes. Urology, 180, 160–167. https://doi.org/10.1016/j.urology.2023.07.017
Kovacs, B., Netzer, N., Baumgartner, M., Eith, C., Bounias, D., Meinzer, C., Jaeger, P. F., Zhang, K. S., Floca, R., Schrader, A., Isensee, F., Gnirs, R., Goertz, M., Schuetz, V., Stenzinger, A., Hohenfellner, M., Schlemmer, H.-P., Wolf, I., Bonekamp, D., & Maier-Hein, K. H. (2023). Anatomy-informed Data Augmentation for Enhanced Prostate Cancer Detection (arXiv:2309.03652). arXiv. https://doi.org/10.48550/arXiv.2309.03652
Gutsche, R., Lowis, C., Ziemons, K., Kocher, M., Ceccon, G., Brambilla, C. R., Shah, N. J., Langen, K.-J., Galldiks, N., Isensee, F., & Lohmann, P. (2023). Automated Brain Tumor Detection and Segmentation for Treatment Response Assessment Using Amino Acid PET. Journal of Nuclear Medicine: Official Publication, Society of Nuclear Medicine, jnumed.123.265725. https://doi.org/10.2967/jnumed.123.265725
Wald, T., Ulrich, C., Isensee, F., Zimmerer, D., Koehler, G., Baumgartner, M., & Maier-Hein, K. H. (2023). Exploring new ways: Enforcing representational dissimilarity to learn new features and reduce error consistency (arXiv:2307.02516). arXiv. https://doi.org/10.48550/arXiv.2307.02516
Heller, N., Isensee, F., Trofimova, D., Tejpaul, R., Zhao, Z., Chen, H., Wang, L., Golts, A., Khapun, D., Shats, D., Shoshan, Y., Gilboa-Solomon, F., George, Y., Yang, X., Zhang, J., Zhang, J., Xia, Y., Wu, M., Liu, Z., … Weight, C. (2023). The KiTS21 Challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CT (arXiv:2307.01984). arXiv. https://doi.org/10.48550/arXiv.2307.01984
Yang, L., Liu, Q., Kumar, P., Sengupta, A., Farnoud, A., Shen, R., Trofimova, D., Ziegler, S., Kutschke, D., Kreyling, W., Piraud, M., Isensee, F., Burgstaller, G., Rehberg, M., Stöger, T., & Schmid, O. (2023). 60 Multimodal Imaging and Artificial Intelligence Unveil Hot-Spot Deposition, Bronchial/Alveolar Dose and Cellular Fate of Biopersistent Nanoparticles in the Lung. Annals of Work Exposures and Health, 67, i53–i53. https://doi.org/10.1093/annweh/wxac087.129
Roy, S., Koehler, G., Baumgartner, M., Ulrich, C., Petersen, J., Isensee, F., & Maier-Hein, K. (2023). Transformer Utilization in Medical Image Segmentation Networks (arXiv:2304.04225). arXiv. https://doi.org/10.48550/arXiv.2304.04225
Eisenmann, M., Reinke, A., Weru, V., Tizabi, M. D., Isensee, F., Adler, T. J., Ali, S., Andrearczyk, V., Aubreville, M., Baid, U., Bakas, S., Balu, N., Bano, S., Bernal, J., Bodenstedt, S., Casella, A., Cheplygina, V., Daum, M., de Bruijne, M., … Maier-Hein, L. (2023). Why is the winner the best? (arXiv:2303.17719). arXiv. https://doi.org/10.48550/arXiv.2303.17719
Vollmuth, P., Foltyn, M., Huang, R. Y., Galldiks, N., Petersen, J., Isensee, F., van den Bent, M. J., Barkhof, F., Park, J. E., Park, Y. W., Ahn, S. S., Brugnara, G., Meredig, H., Jain, R., Smits, M., Pope, W. B., Maier-Hein, K., Weller, M., Wen, P. Y., … Bendszus, M. (2023). Artificial intelligence (AI)-based decision support improves reproducibility of tumor response assessment in neuro-oncology: An international multi-reader study. Neuro-Oncology, 25(3), 533–543. https://doi.org/10.1093/neuonc/noac189
Roß, T., Bruno, P., Reinke, A., Wiesenfarth, M., Koeppel, L., Full, P. M., Pekdemir, B., Godau, P., Trofimova, D., Isensee, F., Adler, T. J., Tran, T. N., Moccia, S., Calimeri, F., Müller-Stich, B. P., Kopp-Schneider, A., & Maier-Hein, L. (2023). Beyond rankings: Learning (more) from algorithm validation. Medical Image Analysis, 102765. https://doi.org/10.1016/j.media.2023.102765
Wood, A., Benidir, T., Abdallah, N., Heller, N., Isensee, F., Tejpaul, R., Suk-ouichai, C., Curry, C., You, A., Remer, E. M., Haywood, S., Campbell, S., Papanikolopoulos, N., & Weight, C. J. (2023). Predictive accuracy of computer-generated C-index nephrometry scores compared with human-generated scores in predicting oncologic and perioperative outcomes. Journal of Clinical Oncology, 41(6_suppl), 623–623. https://doi.org/10.1200/JCO.2023.41.6_suppl.623
Bilic, P., Christ, P., Li, H. B., Vorontsov, E., Ben-Cohen, A., Kaissis, G., Szeskin, A., Jacobs, C., Mamani, G. E. H., Chartrand, G., Lohöfer, F., Holch, J. W., Sommer, W., Hofmann, F., Hostettler, A., Lev-Cohain, N., Drozdzal, M., Amitai, M. M., Vivanti, R., … Menze, B. (2023). The Liver Tumor Segmentation Benchmark (LiTS). Medical Image Analysis, 84, 102680. https://doi.org/10.1016/j.media.2022.102680
Lüth, C. T., Zimmerer, D., Koehler, G., Jaeger, P. F., Isensee, F., Petersen, J., & Maier-Hein, K. H. (2023). CRADL: Contrastive Representations for Unsupervised Anomaly Detection and Localization (arXiv:2301.02126). arXiv. https://doi.org/10.48550/arXiv.2301.02126
Maška, M., Ulman, V., Delgado-Rodriguez, P., Gómez-de-Mariscal, E., Nečasová, T., Guerrero Peña, F. A., Ren, T. I., Meyerowitz, E. M., Scherr, T., Löffler, K., Mikut, R., Guo, T., Wang, Y., Allebach, J. P., Bao, R., Al-Shakarji, N. M., Rahmon, G., Toubal, I. E., Palaniappan, K., … Ortiz-de-Solórzano, C. (2023). The Cell Tracking Challenge: 10 years of objective benchmarking. Nature Methods, 20(7), 1010–1020. https://doi.org/10.1038/s41592-023-01879-y
Roy, S., Koehler, G., Ulrich, C., Baumgartner, M., Petersen, J., Isensee, F., Jaeger, P. F., & Maier-Hein, K. (2023). MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation. https://doi.org/10.48550/ARXIV.2303.09975
Ulrich, C., Isensee, F., Wald, T., Zenk, M., Baumgartner, M., & Maier-Hein, K. H. (2023). MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation (Vol. 14222, pp. 648–658). https://doi.org/10.1007/978-3-031-43898-1_62
Isensee, F., Ulrich, C., Wald, T., & Maier-Hein, K. H. (2023). Extending nnU-Net Is All You Need. In T. M. Deserno, H. Handels, A. Maier, K. Maier-Hein, C. Palm, & T. Tolxdorff (Eds.), Bildverarbeitung für die Medizin 2023 (pp. 12–17). Springer Fachmedien. https://doi.org/10.1007/978-3-658-41657-7_7
Klein, L., Ziegler, S., Laufer, F., Debus, C., Götz, M., Maier-Hein, K., Paetzold, U., Isensee, F., & Jaeger, P. (2023). Understanding Scalable Perovskite Solar Cell Manufacturing with Explainable AI. https://publikationen.bibliothek.kit.edu/1000167169
Yang, L., Kumar, P., Sengupta, A., Farnoud, A., Shen, R., Trofimova, D., Ziegler, S., Davoudi, N., Doryab, A., Yildirim, A., Schiller, H., Razansky, D., Piraud, M., Liu, Q., Rehberg, M., Stoeger, T., Burgstaller, G., Kreyling, W., Isensee, F., & Schmid, O. (2023). Multimodal imaging and deep learning unveil pulmonary delivery profiles and acinar migration of tissue-resident macrophages in the lun. https://doi.org/10.21203/rs.3.rs-2994336/v1