Learning domain-agnostic visual representation for computational pathology using medically-irrelevant style transfer augmentation

TL;DR

This paper introduces STRAP, a style transfer data augmentation method using non-medical styles to improve the generalization of computational pathology models across different domains.

Contribution

The paper proposes a novel style transfer augmentation technique, STRAP, that enhances domain-agnostic visual representation learning in medical imaging by using artistic style sources.

Findings

STRAP improves model robustness to domain shifts.

Achieves state-of-the-art performance in pathology classification tasks.

Simple augmentation method enhances generalization across datasets.

Abstract

Suboptimal generalization of machine learning models on unseen data is a key challenge which hampers the clinical applicability of such models to medical imaging. Although various methods such as domain adaptation and domain generalization have evolved to combat this challenge, learning robust and generalizable representations is core to medical image understanding, and continues to be a problem. Here, we propose STRAP (Style TRansfer Augmentation for histoPathology), a form of data augmentation based on random style transfer from non-medical style source such as artistic paintings, for learning domain-agnostic visual representations in computational pathology. Style transfer replaces the low-level texture content of an image with the uninformative style of randomly selected style source image, while preserving the original high-level semantic content. This improves robustness to domain shift and can be used as a simple yet powerful tool for learning domain-agnostic representations. We demonstrate that STRAP leads to state-of-the-art performance, particularly in the presence of domain shifts, on two particular classification tasks in computational pathology.