AID-RT: Standardising Artificial Intelligence Documentation in RadioTherapy with a domain-specific model card

作者：Ana M. Barragán-Montero, Margerie Huet-Dastarac, Silvia M. Herranz-Hernández, Benjamin Tengler, Emma Skarsø Buhl, Arthur Galapon, Carlos E. S. Cárdenas, M. Fusella, Geoffroy Herbin, Y. de Hond, Franziska Knuth, Ciaran Malone, Peter M. A. van Ooijen, Charlotte Robert, Michele Zeverino, Coen Hurkmans, Tomas Janssen, Stine Korreman, Charlotte L. Brouwer · 发表于：Physics and Imaging in Radiation Oncology · 年份：2026 · DOI：10.1016/j.phro.2026.100940 · 被引用次数：3 · 研究领域：Artificial Intelligence in Healthcare and Education、Radiology practices and education、Explainable Artificial Intelligence (XAI)

Background and Purpose: Insufficient documentation of artificial intelligence (AI) models remains a widespread issue, which hampers reproducibility in research environments and safe integration in clinical departments. Our goal was to develop a standardised, structured, and domain-specific reporting framework tailored to AI models in radiotherapy (RT), enhancing transparency and accountability. Methods: We reviewed existing initiatives for AI model and data reporting and drafted an initial template, which was sent for review to all participants. Three popular RT applications were selected to define task-specific fields: synthetic CT, segmentation, and dose prediction. Five review rounds were performed, where suggested changes were voted in a shared online document. Unclear fields and conflicting votes were discussed at online meetings, and consensus was reached by majority voting. Results: The final template included 6 sections: 0) Card metadata, 1) Model basic information; 2) Model technical specifications (i.e. architecture, software and hardware); 3) Training data, methodology, and information; 4) Evaluation data, methodology, and results (a.k.a commissioning for clinical models); and 5) Other considerations, including ethical use, risk analysis, and monitoring. It is publicly available as a downloadable document template and as an interactive web-based form to facilitate information entry. Conclusions: We proposed a practical, consensus-driven template tailored to the uni...