Journal
IEEE TRANSACTIONS ON MEDICAL IMAGING
Volume 40, Issue 12, Pages 3945-3954Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2021.3101985
Keywords
Biomedical imaging; Histopathology; Task analysis; Painting; Data models; Visualization; Computational modeling; Computational pathology; data augmentation; deep learning; domain-agnostic learning; style transfer
Categories
Funding
- Stanford Department of Biomedical Data Science and Pathology through a Stanford Clinical Data Science Fellowship
Ask authors/readers for more resources
This paper introduces a data augmentation method called STRAP based on style transfer for learning domain-agnostic visual representations in computational pathology. The method achieves state-of-the-art performance on two specific classification tasks in computational pathology, particularly excelling in the presence of domain shifts.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available