Appearance-based Debiasing of Deep Learning Models in Medical Imaging

Wilm F, Reimann MK, Taubmann O, Mühlberg A, Breininger K (2024)


Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2024

Journal

Publisher: Springer Vieweg

Series: Informatik aktuell

City/Town: Wiesbaden

Pages Range: 19-24

Conference Proceedings Title: Bildverarbeitung für die Medizin 2024. BVM 2024

Event location: Erlangen DE

ISBN: 9783658440367

DOI: 10.1007/978-3-658-44037-4_9

Abstract

Out-of-distribution data can substantially impede the performance of deep learning models. In medical imaging, domain shifts can, for instance, be caused by different image acquisition protocols. To address these domain shifts, domain adversarial training can be employed to constrain a model to domainagnostic features. This, however, requires prior knowledge about the domain variable, which might not always be accessible. Recent approaches make use of control regions to guide the training process and thereby alleviate the need for prior domain knowledge. In this work, we combine these approaches with traditional domain adversarial training to exploit the benefits of both methods.We test the proposed method on two medical datasets and demonstrate performance increases of up to 10 %, compared to a baseline trained without debiasing.

Authors with CRIS profile

Additional Organisation(s)

How to cite

APA:

Wilm, F., Reimann, M.K., Taubmann, O., Mühlberg, A., & Breininger, K. (2024). Appearance-based Debiasing of Deep Learning Models in Medical Imaging. In Andreas Maier, Thomas M. Deserno, Heinz Handels, Klaus Maier-Hein, Christoph Palm, Thomas Tolxdorff (Eds.), Bildverarbeitung für die Medizin 2024. BVM 2024 (pp. 19-24). Erlangen, DE: Wiesbaden: Springer Vieweg.

MLA:

Wilm, Frauke, et al. "Appearance-based Debiasing of Deep Learning Models in Medical Imaging." Proceedings of the German Conference on Medical Image Computing, BVM 2024, Erlangen Ed. Andreas Maier, Thomas M. Deserno, Heinz Handels, Klaus Maier-Hein, Christoph Palm, Thomas Tolxdorff, Wiesbaden: Springer Vieweg, 2024. 19-24.

BibTeX: Download