Mind the Gap: Scanner-induced domain shifts pose challenges for representation learning in histopathology

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 tumo...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Wilm, Frauke, Fragoso, Marco, Bertram, Christof A, Stathonikos, Nikolas, Öttl, Mathias, Qiu, Jingna, Klopfleisch, Robert, Maier, Andreas, Aubreville, Marc, Breininger, Katharina
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 29.11.2022
Subjects
Algorithms
CAI
Computer assisted instruction
Domains
Image segmentation
Representations
Scanners
Training
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422