no code implementations • 21 Dec 2023 • Nina Weng, Paraskevas Pegios, Aasa Feragen, Eike Petersen, Siavash Bigdeli
Via a novel inpainting-based modification we spatially limit the changes made with no extra inference step, encouraging the removal of spatially constrained shortcut features while ensuring that the shortcut-free counterfactuals preserve their remaining image features to a high degree.
no code implementations • 9 Aug 2023 • Nina Weng, Siavash Bigdeli, Eike Petersen, Aasa Feragen
In this work, we investigate the causes of gender bias in machine learning-based chest X-ray diagnosis.
no code implementations • 2 May 2023 • Eike Petersen, Enzo Ferrante, Melanie Ganz, Aasa Feragen
Medical imaging models have been shown to encode information about patient demographics such as age, race, and sex in their latent representation, raising concerns about their potential for discrimination.
no code implementations • 28 Mar 2023 • Kilian Zepf, Eike Petersen, Jes Frellsen, Aasa Feragen
Segmentation uncertainty models predict a distribution over plausible segmentations for a given input, which they learn from the annotator variation in the training set.
no code implementations • 17 Feb 2023 • Eike Petersen, Melanie Ganz, Sune Hannibal Holm, Aasa Feragen
Further, we address how to assess the fairness of risk score models quantitatively, including a discussion of metric choices and meaningful statistical comparisons between groups.
1 code implementation • 4 Apr 2022 • Eike Petersen, Aasa Feragen, Maria Luise da Costa Zemsch, Anders Henriksen, Oskar Eiler Wiese Christensen, Melanie Ganz
Instead, while logistic regression is fully robust to dataset composition, we find that CNN performance is generally improved for both male and female subjects when including more female subjects in the training dataset.
no code implementations • 20 Jul 2021 • Eike Petersen, Yannik Potdevin, Esfandiar Mohammadi, Stephan Zidowitz, Sabrina Breyer, Dirk Nowotka, Sandra Henn, Ludwig Pechmann, Martin Leucker, Philipp Rostalski, Christian Herzog
This survey provides an overview of the technical and procedural challenges involved in creating medical machine learning systems responsibly and in conformity with existing regulations, as well as possible solutions to address these challenges.
no code implementations • 21 Mar 2019 • Eike Petersen, Christian Hoffmann, Philipp Rostalski
Factor graphs have recently gained increasing attention as a unified framework for representing and constructing algorithms for signal processing, estimation, and control.