IMPaSh: A Novel Domain-shift Resistant Representation for Colorectal Cancer Tissue Classification

TL;DR

This paper introduces IMPaSh, a self-supervised contrastive learning framework with PatchShuffling augmentation, to create domain-shift resistant representations for colorectal cancer tissue classification, outperforming existing methods.

Contribution

The paper presents a novel self-supervised learning method, IMPaSh, with PatchShuffling augmentation, specifically designed to improve domain generalization in histopathology image classification.

Findings

IMPaSh outperforms traditional domain-adaptation methods.

The learned representations are more resistant to domain-shift.

Code is publicly available for reproducibility.

Abstract

The appearance of histopathology images depends on tissue type, staining and digitization procedure. These vary from source to source and are the potential causes for domain-shift problems. Owing to this problem, despite the great success of deep learning models in computational pathology, a model trained on a specific domain may still perform sub-optimally when we apply them to another domain. To overcome this, we propose a new augmentation called PatchShuffling and a novel self-supervised contrastive learning framework named IMPaSh for pre-training deep learning models. Using these, we obtained a ResNet50 encoder that can extract image representation resistant to domain-shift. We compared our derived representation against those acquired based on other domain-generalization techniques by using them for the cross-domain classification of colorectal tissue images. We show that the proposed method outperforms other traditional histology domain-adaptation and state-of-the-art self-supervised learning methods. Code is available at: https://github.com/trinhvg/IMPash .