A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretation

TL;DR

This paper introduces CheXagent, a vision-language foundation model trained on a large-scale dataset to improve efficiency and accuracy in chest X-ray interpretation, demonstrating significant time savings and versatility in clinical tasks.

Contribution

The paper presents a new large-scale dataset and a foundation model that achieves competitive performance across multiple tasks and enhances clinical workflow efficiency.

Findings

36% time saving for residents using CheXagent

81% and 61% of cases saw improved report writing efficiency for residents and attendings

Effective performance across eight CXR interpretation tasks

Abstract

Over 1.4 billion chest X-rays (CXRs) are performed annually due to their cost-effectiveness as an initial diagnostic test. This scale of radiological studies provides a significant opportunity to streamline CXR interpretation and documentation. While foundation models are a promising solution, the lack of publicly available large-scale datasets and benchmarks inhibits their iterative development and real-world evaluation. To overcome these challenges, we constructed a large-scale dataset (CheXinstruct), which we utilized to train a vision-language foundation model (CheXagent). We systematically demonstrated competitive performance across eight distinct task types on our novel evaluation benchmark (CheXbench). Beyond technical validation, we assessed the real-world utility of CheXagent in directly drafting radiology reports. Our clinical assessment with eight radiologists revealed a 36% time saving for residents using CheXagent-drafted reports, while attending radiologists showed no significant time difference editing resident-drafted or CheXagent-drafted reports. The CheXagent-drafted reports improved the writing efficiency of both radiology residents and attending radiologists in 81% and 61% of cases, respectively, without loss of quality. Overall, we demonstrate that CheXagent can effectively perform a variety of CXR interpretation tasks and holds potential to assist radiologists in routine clinical workflows.