Understanding and analyzing plant roots using semantic segmentation of MRI images

Project "Understanding and analyzing plant roots using semantic segmentation of MRI images"

The optimization of plants has long focused on the above-ground parts. Recently, new efforts are being made to exploit the potential below ground. To this end, our partners at the FZJ have developed an imaging system which enables imaging the root system throughout the growth of the plants using MRI. Besides qualitative analysis, a precise quantitative description of the root system is of utmost importance, requiring state-of-the-art image analysis to effectively detect thin roots in a resolution and signal to noise-limited scenario. As part of this project we incorporate recent developments in AI-based image segmentation into established root extraction pipelines with the goal of improving the precision, sensitivity and robustness of the reconstructed root trees.

Other Collaborations


Paving the way for future mineral processing and recycling technologies through large-scale analysis of particulate samples

Understanding and quantifying the exact composition of mineral samples paves the way towards advanced methodologies that not only increase the effectiveness of ore processing but also enable future recycling technologies. To this end, samples consisting of ground particles embedded into an epoxy matrix are imaged with computed tomography (CT) at micrometer resolution. Due to the […]

Understanding lung diseases and optimizing their treatment

Understanding the distribution of nanoparticles after inhalation can lead to the discovery of novel, more effective drug delivering techniques. To this end we develop AI-based methods for semantic segmentation of the airways in non-dissected whole murine lungs, imaged with light sheet fluorescence microscopy. The analysis of airway properties in diseased lungs will furthermore shed light […]

Ultra Content Screening for Clinical Diagnostics and Deep Phenotyping

For the Helmholtz Imaging project UCS (Ultra Content Screening for Clinical Diagnostics and Deep Phenotyping) we developed software to allow the project partners to process their immunofluorescence labelled light microscopy data of nuclei and cells for single cell proteomics. The developed pipeline includes instance segmentation of nuclei and cells in the immunofluorescence assays, registration of […]