Jacqueline L Brenner, James T Anibal, Lindsey A Hazen, Miranda J Song, Hannah B Huth, Daguang Xu, Sheng Xu, Bradford J Wood
{"title":"IR-GPT: AI Foundation Models to Optimize Interventional Radiology.","authors":"Jacqueline L Brenner, James T Anibal, Lindsey A Hazen, Miranda J Song, Hannah B Huth, Daguang Xu, Sheng Xu, Bradford J Wood","doi":"10.1007/s00270-024-03945-0","DOIUrl":null,"url":null,"abstract":"<p><p>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.</p>","PeriodicalId":9591,"journal":{"name":"CardioVascular and Interventional Radiology","volume":" ","pages":"585-592"},"PeriodicalIF":2.9000,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12052823/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"CardioVascular and Interventional Radiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s00270-024-03945-0","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/3/26 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0
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.
期刊介绍：
CardioVascular and Interventional Radiology (CVIR) is the official journal of the Cardiovascular and Interventional Radiological Society of Europe, and is also the official organ of a number of additional distinguished national and international interventional radiological societies. CVIR publishes double blinded peer-reviewed original research work including clinical and laboratory investigations, technical notes, case reports, works in progress, and letters to the editor, as well as review articles, pictorial essays, editorials, and special invited submissions in the field of vascular and interventional radiology. Beside the communication of the latest research results in this field, it is also the aim of CVIR to support continuous medical education. Articles that are accepted for publication are done so with the understanding that they, or their substantive contents, have not been and will not be submitted to any other publication.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
