Learning Domain-Agnostic Visual Representation for Computational Pathology Using Medically-Irrelevant Style Transfer Augmentation

Rikiya Yamashita, Jin Long, Snikitha Banda, Jeanne Shen, Daniel L. Rubin

Research output: Contribution to journalArticlepeer-review

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 sources 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. Our code is available at https://github.com/rikiyay/style-transfer-for-digital-pathology.

Original languageEnglish (US)
Pages (from-to)3945-3954
Number of pages10
JournalIEEE Transactions on Medical Imaging
Volume40
Issue number12
DOIs
StatePublished - Dec 1 2021
Externally publishedYes

Keywords

  • Computational pathology
  • data augmentation
  • deep learning
  • domain-agnostic learning
  • style transfer

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Learning Domain-Agnostic Visual Representation for Computational Pathology Using Medically-Irrelevant Style Transfer Augmentation'. Together they form a unique fingerprint.

Cite this