RT Journal Article
SR Electronic
T1 Nuclear Medicine and Artificial Intelligence: Best Practices for Algorithm Development
JF Journal of Nuclear Medicine
JO J Nucl Med
FD Society of Nuclear Medicine
SP jnumed.121.262567
DO 10.2967/jnumed.121.262567
A1 Tyler J. Bradshaw
A1 Ronald Boellaard
A1 Joyita Dutta
A1 Abhinav K. Jha
A1 Paul Jacobs
A1 Quanzheng Li
A1 Chi Liu
A1 Arkadiusz Sitek
A1 Babak Saboury
A1 Peter J.H. Scott
A1 Piotr J. Slomka
A1 John J. Sunderland
A1 Richard L. Wahl
A1 Fereshteh Yousefirizi
A1 Sven Zuehlsdorff
A1 Arman Rahmim
A1 Irène Buvat
YR 2021
UL http://jnm.snmjournals.org/content/early/2021/11/04/jnumed.121.262567.abstract
AB The nuclear medicine field has seen a rapid expansion of academic and commercial interests in developing artificial intelligence (AI) algorithms. Users and developers can avoid some of the pitfalls of AI by recognizing and following best practices in AI algorithm development. In this article, recommendations for technical best practices for developing AI algorithms in nuclear medicine are provided, beginning with general recommendations followed by descriptions on how one might practice these principles for specific topics within nuclear medicine. This report was produced by the AI Task Force of the Society of Nuclear Medicine and Molecular Imaging.