1 citations · 1 across the 4 of their papers we have counts for
4 papers
Benchmarking Dependence Measures to Prevent Shortcut Learning in Medical Imaging
Sarah Müller, Louisa Fay, Lisa M. Koch +3
Medical imaging cohorts are often confounded by factors such as acquisition devices, hospital sites, patient backgrounds, and many more. As a result, deep learning models tend to l…
Benchmarking Retinal Blood Vessel Segmentation Models for Cross-Dataset and Cross-Disease Generalization
Jeremiah Fadugba, Patrick Köhler, Lisa Koch +2
Retinal blood vessel segmentation can extract clinically relevant information from fundus images. As manual tracing is cumbersome, algorithms based on Convolution Neural Networks h…
Right for the Wrong Reason: Can Interpretable ML Techniques Detect Spurious Correlations?
Susu Sun, Lisa M. Koch, Christian F. Baumgartner
While deep neural network models offer unmatched classification performance, they are prone to learning spurious correlations in the data. Such dependencies on confounding informat…
Deep Hypothesis Tests Detect Clinically Relevant Subgroup Shifts in Medical Images
Lisa M. Koch, Christian M. Schürch, Christian F. Baumgartner +2
Distribution shifts remain a fundamental problem for the safe application of machine learning systems. If undetected, they may impact the real-world performance of such systems or…