AI Heap
Published on

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

arXiv:2401.12208 - [arXiv,PDF]
Authors
  • Name
    Zhihong Chen
  • Name
    Maya Varma
  • Name
    Justin Xu
  • Name
    Magdalini Paschali
  • Name
    Dave Van Veen
  • Name
    Andrew Johnston
  • Name
    Alaa Youssef
  • Name
    Louis Blankemeier
  • Name
    Christian Bluethgen
  • Name
    Stephan Altmayer
  • Name
    Jeya Maria Jose Valanarasu
  • Name
    Mohamed Siddig Eltayeb Muneer
  • Name
    Eduardo Pontes Reis
  • Name
    Joseph Paul Cohen
  • Name
    Cameron Olsen
  • Name
    Tanishq Mathew Abraham
  • Name
    Emily B. Tsai
  • Name
    Christopher F. Beaulieu
  • Name
    Jenia Jitsev
  • Name
    Sergios Gatidis
  • Name
    Jean-Benoit Delbrouck
  • Name
    Akshay S. Chaudhari
  • Name
    Curtis P. Langlotz
  • Affiliation
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.