UMDISTO: Unsupervised Model Discovery

visual for third-party funded project UMDISTO

The project aims to develop novel methods for unsupervised multi-matching to map cellular-level correspondences in organisms like C. elegans. Using fluorescence microscopy data from 265 specimens, it seeks to create a comprehensive gene expression atlas, advancing reverse-engineering of the organism’s DNA-encoded “program”.

Project partners

Bogdan Savchynskyy, Ruprecht-Karls-Universität Heidelberg

Involved Helmholtz Imaging Units

Research Unit MDC

Primary Contact

Dagmar Kainmueller

dagmar.kainmueller@mdc-berlin.de

Other projects

QGRIS: Quantitative Gamma-Ray Imaging System

Compton cameras are used for the radiological characterization of nuclear power plants. In this project, a suitable camera system is designed, and the associated algorithms for image reconstruction and nuclide characterization are implemented as user software.

decorative visual; blue-futuristic-stream-data-communication-flying

Image: Envato Elements

FONDA: Dependability, Adaptability and Uncertainty Quantification for Data Analysis Workflows in Large-Scale Biomedical Image Analysis

The project aims to enhance infrastructures for machine learning (ML)-intensive DAWs in advanced biomedical imaging applications.

Bayesian Computations for Large-scale (Nonlinear) Inverse Problems in Imaging

During research stays with the collaborating group at Caltech, we aim to investigate various aspects of statistical inverse problems. This includes inquiries into particle- and PDE-based sampling methods, as well as robust regularization using neural networks.