Mind the Gap: Scanner-Induced Domain Shifts Pose Challenges for Representation Learning in Histopathology

Wilm F, Fragoso M, Bertram CA, Stathonikos N, Ottl M, Qiu J, Klopfleisch R, Maier A, Aubreville M, Breininger K (2023)

Publication Type: Conference contribution

Publication year: 2023

Journal

Proceedings - International Symposium on Biomedical Imaging

Publisher: IEEE Computer Society

Book Volume: 2023-April

Conference Proceedings Title: Proceedings - International Symposium on Biomedical Imaging

Event location: Cartagena CO

ISBN: 9781665473583

DOI: 10.1109/ISBI53787.2023.10230458

Abstract

Computer-aided systems in histopathology are often challenged by various sources of domain shift that impact the performance of these algorithms considerably. We investigated the potential of using self-supervised pre-training to overcome scanner-induced domain shifts for the downstream task of tumor segmentation. For this, we present the Barlow Triplets to learn scanner-invariant representations from a multi-scanner dataset with local image correspondences. We show that self-supervised pre-training successfully aligned different scanner representations, which, interestingly only results in a limited benefit for our downstream task. We thereby provide insights into the influence of scanner characteristics for downstream applications and contribute to a better understanding of why established self-supervised methods have not yet shown the same success on histopathology data as they have for natural images.

Authors with CRIS profile

Frauke Wilm Lehrstuhl für Informatik 5 (Mustererkennung) Jingna Qiu Juniorprofessur für Artificial Intelligence in Medical Imaging Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung) Katharina Breininger Juniorprofessur für Artificial Intelligence in Medical Imaging

Involved external institutions

Veterinärmedizinische Universität Wien (Vetmeduni Vienna) / University of Veterinary Medicine, Vienna AT Austria (AT) Technische Hochschule Ingolstadt DE Germany (DE) Freie Universität Berlin DE Germany (DE) University Medical Centre Utrecht (UMC Utrecht) NL Netherlands (NL)

How to cite

APA:

Wilm, F., Fragoso, M., Bertram, C.A., Stathonikos, N., Ottl, M., Qiu, J.,... Breininger, K. (2023). Mind the Gap: Scanner-Induced Domain Shifts Pose Challenges for Representation Learning in Histopathology. In Proceedings - International Symposium on Biomedical Imaging. Cartagena, CO: IEEE Computer Society.

MLA:

Wilm, Frauke, et al. "Mind the Gap: Scanner-Induced Domain Shifts Pose Challenges for Representation Learning in Histopathology." Proceedings of the 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023, Cartagena IEEE Computer Society, 2023.

BibTeX: Download