IR-GPT: AI Foundation Models to Optimize Interventional Radiology.

Journal: Cardiovascular and interventional radiology
Published Date: Mar 26, 2025

Abstract

Foundation artificial intelligence (AI) models are capable of complex tasks that involve text, medical images, and many other types of data, but have not yet been customized for procedural medicine. This report reviews prior work in deep learning related to interventional radiology (IR), identifying barriers to generalization and deployment at scale. Moreover, this report outlines the potential design of an "IR-GPT" foundation model to provide a unified platform for AI in IR, including data collection, annotation, and training methods-while also contextualizing challenges and highlighting potential downstream applications.

Authors

  • Jacqueline L Brenner
    Center for Interventional Oncology, NIH Clinical Center, National Institutes of Health (NIH), Bethesda, USA.
  • James T Anibal
    Center for Interventional Oncology, NIH Clinical Center, National Institutes of Health (NIH), Bethesda, USA. anibal.james@nih.gov.
  • Lindsey A Hazen
    Center for Interventional Oncology, NIH Clinical Center, National Institutes of Health (NIH), Bethesda, USA.
  • Miranda J Song
    Center for Interventional Oncology, NIH Clinical Center, National Institutes of Health (NIH), Bethesda, USA.
  • Hannah B Huth
    Center for Interventional Oncology, NIH Clinical Center, National Institutes of Health (NIH), Bethesda, USA.
  • Daguang Xu
    NVIDIA, Santa Clara, CA, USA.
  • Sheng Xu
    School of Physics and Information Engineering, Jiangsu Second Normal University, Nanjing, 211200, China.
  • Bradford J Wood
    Molecular Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.

Keywords

External Resources

Popular Topics
Recent Journals