Enhancing Whole Slide Image Classification through Supervised Contrastive Domain Adaptation
This work addresses the problem of domain shift in whole-slide image classification for skin cancer subtypes, which is incremental as it builds on existing contrastive learning approaches.
The paper tackled domain shift in histopathological imaging by proposing a supervised contrastive domain adaptation method to handle variability between images from multiple centers, achieving superior performance compared to baseline methods without domain adaptation.
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.