Domain and Content Adaptive Convolutions for Cross-Domain Adenocarcinoma Segmentation

Wilm F, Öttl M, Aubreville M, Breininger K (2025)

Publication Status: Submitted

Publication Type: Unpublished / Preprint

Future Publication Type: Journal article

Publication year: 2025

DOI: 10.48550/arXiv.2409.09797

Abstract

Recent advances in computer-aided diagnosis for histopathology have been largely driven by the use of deep learning models for automated image analysis. While these networks can perform on par with medical experts, their performance can be impeded by out-of-distribution data. The Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation (COSAS) challenge aimed to address the task of cross-domain adenocarcinoma segmentation in the presence of morphological and scanner-induced domain shifts. In this paper, we present a U-Net-based segmentation framework designed to tackle this challenge. Our approach achieved segmentation scores of 0.8020 for the cross-organ track and 0.8527 for the cross-scanner track on the final challenge test sets, ranking it the best-performing submission.

Authors with CRIS profile

Frauke Wilm Department Artificial Intelligence in Biomedical Engineering (AIBE) Mathias Öttl Lehrstuhl für Informatik 5 (Mustererkennung)

Additional Organisation(s)

Sonderforschungsbereich 1540: Erforschung der Mechanik des Gehirns (EBM): Verständnis, Engineering und Nutzung mechanischer Eigenschaften und Signale in der Entwicklung, Physiologie und Pathologie des zentralen Nervensystems

Involved external institutions

Fachhochschule Flensburg DE Germany (DE) Julius-Maximilians-Universität Würzburg DE Germany (DE)

How to cite

APA:

Wilm, F., Öttl, M., Aubreville, M., & Breininger, K. (2025). Domain and Content Adaptive Convolutions for Cross-Domain Adenocarcinoma Segmentation. (Unpublished, Submitted).

MLA:

Wilm, Frauke, et al. Domain and Content Adaptive Convolutions for Cross-Domain Adenocarcinoma Segmentation. Unpublished, Submitted. 2025.

BibTeX: Download