A5: Dependability, Adaptability and Uncertainty Quantification for Data Analysis Workflows in Large-Scale Biomedical Image Analysis



Scientific data analysis workflows (DAWs) increasingly include tasks that implement some form of large-scale machine learning (ML). This is particularly true in biomedical image analysis, where many recent breakthroughs rooted in the application of advanced ML for image analysis based on increasingly large training data sets. Such ML-heavy DAWs have the disadvantage of not being dependable in terms of the quality of predictions on real-life test data, one reason being a lack of adaptability to varying data distributions. In this subproject, we aim at improving the abilities of DAWs for ML-based biomedical image analysis by means of automated assessment the suitability of their models for new data sets, and adaptation of these models – whenever possible and appropriate – to test data that is different from the respective training data.




Marc-Andre Schulz; Alexander Koch; Vanessa Emanuela Guarino; Dagmar Kainmueller; Kerstin Ritter

Data augmentation via partial nonlinear registration for brain-age prediction Inproceedings

In: Machine Learning in Clinical Neuroimaging, Lecture Notes in Computer Science, 2022.


Marc-Andre Schulz; Danilo Bzdok; Stefan Haufe; John-Dylan Haynes; Kerstin Ritter

Performance reserves in brain-imaging-based phenotype prediction Working paper

bioAxiv, 2022.



Fabian Eitel; Marc-Andre Schulz; Moritz Seiler; Henrik Walter; Kerstin Ritter

Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research Journal Article

In: Experimental Neurology, vol. 339, 2021.


Josef Lorenz Rumberger; Xiaoyan Yu; Peter Hirsch; Melanie Dohmen; Vanessa Emanuela Guarino; Ashkan Mokarian; Lisa Mais; Jan Funke; Dagmar Kainmueller

How Shift Equivariance Impacts Metric Learning for Instance Segmentation Journal Article

In: CoRR, vol. abs/2101.05846, 2021.

Links | BibTeX