Chest X-ray Foundation Model with Global and Local Representations Integration

TL;DR

CheXFound is a self-supervised foundation model for chest X-ray analysis that learns robust representations from over one million images, enabling effective multi-task classification, out-of-distribution generalization, and label-efficient adaptation.

Contribution

The paper introduces CheXFound, a novel self-supervised vision model with a GLoRI module for integrating global and local features, improving performance and generalization in chest X-ray tasks.

Findings

Outperforms state-of-the-art models on 40 disease classification tasks

Exhibits superior label efficiency with limited training data

Achieves significant improvements on out-of-distribution datasets

Abstract

Chest X-ray (CXR) is the most frequently ordered imaging test, supporting diverse clinical tasks from thoracic disease detection to postoperative monitoring. However, task-specific classification models are limited in scope, require costly labeled data, and lack generalizability to out-of-distribution datasets. To address these challenges, we introduce CheXFound, a self-supervised vision foundation model that learns robust CXR representations and generalizes effectively across a wide range of downstream tasks. We pretrain CheXFound on a curated CXR-1M dataset, comprising over one million unique CXRs from publicly available sources. We propose a Global and Local Representations Integration (GLoRI) module for downstream adaptations, by incorporating disease-specific local features with global image features for enhanced performance in multilabel classification. Our experimental results show that CheXFound outperforms state-of-the-art models in classifying 40 disease findings across different prevalence levels on the CXR-LT 24 dataset and exhibits superior label efficiency on downstream tasks with limited training data. Additionally, CheXFound achieved significant improvements on new tasks with out-of-distribution datasets, including opportunistic cardiovascular disease risk estimation and mortality prediction. These results highlight CheXFound's strong generalization capabilities, enabling diverse adaptations with improved label efficiency. The project source code is publicly available at https://github.com/RPIDIAL/CheXFound.