Enhancing Whole Slide Image Classification through Supervised Contrastive Domain Adaptation

TL;DR

This paper introduces a supervised contrastive domain adaptation method to improve the classification of histopathological whole-slide images across different centers, addressing variability in staining and digitization.

Contribution

A novel domain adaptation technique that enhances supervised contrastive learning for better generalization across diverse histopathological datasets.

Findings

Outperforms baseline methods without domain adaptation.

Improves inter-class separability in feature space.

Demonstrates effectiveness on skin cancer subtype classification.

Abstract

Domain shift in the field of histopathological imaging is a common phenomenon due to the intra- and inter-hospital variability of staining and digitization protocols. The implementation of robust models, capable of creating generalized domains, represents a need to be solved. In this work, a new domain adaptation method to deal with the variability between histopathological images from multiple centers is presented. In particular, our method adds a training constraint to the supervised contrastive learning approach to achieve domain adaptation and improve inter-class separability. Experiments performed on domain adaptation and classification of whole-slide images of six skin cancer subtypes from two centers demonstrate the method's usefulness. The results reflect superior performance compared to not using domain adaptation after feature extraction or staining normalization.