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

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.

References in corpus (9)

• A Simple Framework for Contrastive Learning of Visual Representations
• Axiomatic Attribution for Deep Networks
• Machine learning methods for histopathological image analysis
• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
• Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology
• WILDS: A Benchmark of in-the-Wild Distribution Shifts
• Domain Agnostic Learning with Disentangled Representations
• Style Augmentation: Data Augmentation via Style Randomization
• PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network with a Benchmark at Cross-modality Cardiac Segmentation

Cited by in corpus (4)

• Domain Generalization for Medical Image Analysis: A Review
• Learning to Generalize towards Unseen Domains via a Content-Aware Style Invariant Model for Disease Detection from Chest X-rays
• A Histopathology Study Comparing Contrastive Semi-Supervised and Fully Supervised Learning
• Nuclear Segmentation and Classification: On Color & Compression Generalization