MedAug: Contrastive learning leveraging patient metadata improves representations for chest X-ray interpretation

TL;DR

MedAug introduces a patient metadata-based contrastive learning method that enhances chest X-ray representations, significantly improving disease classification performance by intelligently selecting positive image pairs.

Contribution

The paper proposes a novel approach to select positive pairs in contrastive learning using patient metadata, leading to better representations for medical image interpretation.

Findings

Using patient metadata improves downstream classification performance.

Best strategy involves same patient, same study, across all lateralities.

Maximizing different images in query pairing enhances results.

Abstract

Self-supervised contrastive learning between pairs of multiple views of the same image has been shown to successfully leverage unlabeled data to produce meaningful visual representations for both natural and medical images. However, there has been limited work on determining how to select pairs for medical images, where availability of patient metadata can be leveraged to improve representations. In this work, we develop a method to select positive pairs coming from views of possibly different images through the use of patient metadata. We compare strategies for selecting positive pairs for chest X-ray interpretation including requiring them to be from the same patient, imaging study or laterality. We evaluate downstream task performance by fine-tuning the linear layer on 1% of the labeled dataset for pleural effusion classification. Our best performing positive pair selection strategy, which involves using images from the same patient from the same study across all lateralities, achieves a performance increase of 14.4% in mean AUC from the ImageNet pretrained baseline. Our controlled experiments show that the keys to improving downstream performance on disease classification are (1) using patient metadata to appropriately create positive pairs from different images with the same underlying pathologies, and (2) maximizing the number of different images used in query pairing. In addition, we explore leveraging patient metadata to select hard negative pairs for contrastive learning, but do not find improvement over baselines that do not use metadata. Our method is broadly applicable to medical image interpretation and allows flexibility for incorporating medical insights in choosing pairs for contrastive learning.