Scholarlink

<p>As artificial intelligence (AI) becomes increasingly prevalent within interventional radiology (IR) research and clinical practice, steps must be taken to ensure the robustness of novel technological systems presented in peer-reviewed journals. This report introduces&#xa0;comprehensive standards and an&#xa0;evaluation checklist (iCARE) that&#xa0;covers the application of modern AI methods in IR-specific contexts. The iCARE checklist encompasses the full "code-to-clinic"&#xa0;pipeline of AI development, including dataset curation, pre-training, task-specific training, explainability, privacy protection, bias mitigation, reproducibility, and model deployment.&#xa0;The iCARE checklist aims to support the development of safe, generalizable technologies for enhancing IR&#xa0;workflows, the delivery of care, and patient outcomes.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Interventional Radiology Reporting Standards and Checklist for Artificial Intelligence Research Evaluation (iCARE)

  • 期刊论文

  • 发表日期：

    2025年6月25日

查看全文
  • James T. Anibal,
  • Hannah B. Huth,
  • Tom Boeken,
  • Dania Daye,
  • Judy Gichoya,
  • Fernando Gómez Muñoz,
  • Julius Chapiro,
  • Bradford J. Wood,
  • Daniel Y. Sze,
  • Klaus Hausegger

摘要

As artificial intelligence (AI) becomes increasingly prevalent within interventional radiology (IR) research and clinical practice, steps must be taken to ensure the robustness of novel technological systems presented in peer-reviewed journals. This report introduces comprehensive standards and an evaluation checklist (iCARE) that covers the application of modern AI methods in IR-specific contexts. The iCARE checklist encompasses the full "code-to-clinic" pipeline of AI development, including dataset curation, pre-training, task-specific training, explainability, privacy protection, bias mitigation, reproducibility, and model deployment. The iCARE checklist aims to support the development of safe, generalizable technologies for enhancing IR workflows, the delivery of care, and patient outcomes.