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

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

doi:10.2967/jnumed.121.263239

Back

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

Journal article

Open access

Peer reviewed

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

Abhinav K. Jha, Tyler J. Bradshaw, Irene Buvat, Mathieu Hatt, K. C. Prabhat, Chi Liu, Nancy F. Obuchowski, Babak Saboury, Piotr J. Slomka, John J. Sunderland, …

The Journal of nuclear medicine (1978), Vol.63(9), pp.1288-1299

09/01/2022

DOI: 10.2967/jnumed.121.263239

PMCID: PMC9454473

PMID: 35618476

Files and links (1)

url

https://doi.org/10.2967/jnumed.121.263239View

Published (Version of record) Open Access

Abstract

An important need exists for strategies to perform rigorous objective clini-cal-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) guide-lines. 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 scien-tists, and representatives from industry and regulatory agencies.

Life Sciences & Biomedicine

Radiology, Nuclear Medicine & Medical Imaging

Science & Technology

Details

Title: Subtitle: Nuclear Medicine and Artificial Intelligence: Best Practices for Evaluation (the RELAINCE Guidelines)
Creators: Abhinav K. Jha - Washington University in St. Louis
Tyler J. Bradshaw - University of Wisconsin–Madison
Irene Buvat - PSL Research University
Mathieu Hatt - LaTiM, INSERM, UMR 1101, Univ Brest.
K. C. Prabhat - US FDA, Ctr Devices & Radiol Hlth, Silver Spring, MD USA
Chi Liu - Yale University
Nancy F. Obuchowski - Cleveland Clinic
Babak Saboury - National Institutes of Health Clinical Center
Piotr J. Slomka - Cedars-Sinai Medical Center
John J. Sunderland - University of Iowa
Richard L. Wahl - Mallinckrodt
Zitong Yu - Washington University in St. Louis
Sven Zuehlsdorff - Medical Solutions
Arman Rahmim - University of British Columbia
Ronald Boellaard - Amsterdam University Medical Centers
Resource Type: Journal article
Publication Details: The Journal of nuclear medicine (1978), Vol.63(9), pp.1288-1299
DOI: 10.2967/jnumed.121.263239
PMID: 35618476
PMCID: PMC9454473
NLM abbreviation: J Nucl Med
ISSN: 0161-5505
eISSN: 1535-5667
Publisher: Soc Nuclear Medicine Inc
Number of pages: 12
Language: English
Date published: 09/01/2022
Academic Unit: Radiology; Physics and Astronomy; Radiation Oncology
Record Identifier: 9984312983602771

Metrics

14 Record Views

67 Times Cited - Web of Science

See more details