Nuclear Medicine and Artificial Intelligence: Best Practices for Evaluation (the RELAINCE Guidelines)

Abhinav K. Jha, Tyler J. Bradshaw, Irène Buvat, Mathieu Hatt, Prabhat Kc, Chi Liu, Nancy F. Obuchowski, Babak Saboury, Piotr J. Slomka, John J. Sunderland, Richard L. Wahl, Zitong Yu, Sven Zuehlsdorff, Arman Rahmim, Ronald Boellaard

Research output: Contribution to journalArticlepeer-review

38 Scopus citations

Abstract

An important need exists for strategies to perform rigorous objective clinical-task-based evaluation of artificial intelligence (AI) algorithms for nuclear medicine. To address this need, we propose a 4-class framework to evaluate AI algorithms for promise, technical task-specific efficacy, clinical decision making, and postdeployment efficacy. We provide best practices to evaluate AI algorithms for each of these classes. Each class of evaluation yields a claim that provides a descriptive performance of the AI algorithm. Key best practices are tabulated as the RELAINCE (Recommendations for EvaLuation of AI for NuClear medicinE) guidelines. The report was prepared by the Society of Nuclear Medicine and Molecular Imaging AI Task Force Evaluation team, which consisted of nuclear-medicine physicians, physicists, computational imaging scientists, and representatives from industry and regulatory agencies.

Original languageEnglish
Pages (from-to)1288-1299
Number of pages12
JournalJournal of Nuclear Medicine
Volume63
Issue number9
DOIs
StatePublished - Sep 1 2022

Keywords

  • PET
  • SPECT
  • artificial intelligence
  • best practices
  • clinical decision making
  • clinical task
  • evaluation
  • generalizability
  • postdeployment
  • technical efficacy

Fingerprint

Dive into the research topics of 'Nuclear Medicine and Artificial Intelligence: Best Practices for Evaluation (the RELAINCE Guidelines)'. Together they form a unique fingerprint.

Cite this