Interventional Radiology Reporting Standards and Checklist for Artificial Intelligence Research Evaluation (iCARE).
Authors
Affiliations (10)
Affiliations (10)
- Center for Interventional Oncology, NIH Clinical Center, National Cancer Institute, National Institute of Biomedical Imaging and Bioengineering, National Institutes of Health (NIH), Bethesda, MD, 20892, USA. [email protected].
- Computational Health Informatics Lab, Institute of Biomedical Engineering (IBME), University of Oxford, Oxford, UK. [email protected].
- Center for Interventional Oncology, NIH Clinical Center, National Cancer Institute, National Institute of Biomedical Imaging and Bioengineering, National Institutes of Health (NIH), Bethesda, MD, 20892, USA.
- Université Paris Cité, Faculté de Médecine, 75006, Paris, France.
- Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
- Department of Radiology, Emory University School of Medicine, Atlanta, GA, USA.
- Imagen Médica, Hospital Universitario y Politécnico La Fe/Antoni Van Leeuwenhoek-NKI, Amsterdam, The Netherlands.
- Yale School of Medicine, New Haven, CT, USA.
- Journal for Vascular and Interventional Radiology, Philadelphia, USA.
- CardioVascular and Interventional Radiology, Vienna, Austria.
Abstract
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.