PathoWAve: A Deep Learning-based Weight Averaging Method for Improving Domain Generalization in Histopathology Images

TL;DR

PathoWAve is a novel deep learning weight averaging technique designed to enhance domain generalization in histopathology image analysis, effectively addressing domain shifts caused by staining and scanner variations.

Contribution

It introduces the first weight averaging method specifically for domain generalization in histopathology image analysis, combining regular and histopathology-specific augmentations for improved model robustness.

Findings

Outperforms previous methods on Camelyon17 WILDS dataset

Significantly improves model generalization to unseen domains

First to apply weight averaging for DG in histopathology images

Abstract

Recent advancements in deep learning (DL) have significantly advanced medical image analysis. In the field of medical image processing, particularly in histopathology image analysis, the variation in staining protocols and differences in scanners present significant domain shift challenges, undermine the generalization capabilities of models to the data from unseen domains, prompting the need for effective domain generalization (DG) strategies to improve the consistency and reliability of automated cancer detection tools in diagnostic decision-making. In this paper, we introduce Pathology Weight Averaging (PathoWAve), a multi-source DG strategy for addressing domain shift phenomenon of DL models in histopathology image analysis. Integrating specific weight averaging technique with parallel training trajectories and a strategically combination of regular augmentations with histopathology-specific data augmentation methods, PathoWAve enables a comprehensive exploration and precise convergence within the loss landscape. This method significantly enhanced generalization capabilities of DL models across new, unseen histopathology domains. To the best of our knowledge, PathoWAve is the first proposed weight averaging method for DG in histopathology image analysis. Our quantitative results on Camelyon17 WILDS dataset demonstrate PathoWAve's superiority over previous proposed methods to tackle the domain shift phenomenon in histopathology image processing. Our code is available at \url{https://github.com/ParastooSotoudeh/PathoWAve}.