Nuclear Medicine and Artificial Intelligence: Best Practices for Algorithm Development

The Journal of Nuclear Medicine

article

Tyler J. Bradshaw¹  Ronald Boellaard²  Joyita Dutta³  Abhinav K. Jha⁴  Paul Jacobs⁵  Quanzheng Li⁶  Chi Liu⁷  Arkadiusz Sitek⁸  Babak Saboury⁹  Peter J.H. Scott^1,10  Piotr J. Slomka^1,11  John J. Sunderland^1,12  Richard L. Wahl^1,13  Fereshteh Yousefirizi^1,14  Sven Zuehlsdorff^1,15  Arman Rahmim^1,16  Irène Buvat^1,17 

[1] Department of Radiology, University of Wisconsin–Madison;Department of Radiology and Nuclear Medicine, Cancer Centre Amsterdam, Amsterdam University Medical Centres;Department of Electrical and Computer Engineering, University of Massachusetts Lowell;Department of Biomedical Engineering and Mallinckrodt Institute of Radiology, Washington University in St. Louis;MIM Software Inc.;Department of Radiology, Massachusetts General Hospital and Harvard Medical School;Department of Radiology and Biomedical Imaging, Yale University;Sano Centre for Computational Medicine;Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health;Department of Radiology, University of Michigan Medical School;Department of Imaging, Medicine, and Cardiology, Cedars-Sinai Medical Center;Departments of Radiology and Physics, University of Iowa;Mallinckrodt Institute of Radiology, Washington University in St. Louis;Department of Integrative Oncology, BC Cancer Research Institute;Siemens Medical Solutions USA, Inc.;Departments of Radiology and Physics, University of British Columbia;Institut Curie, Université PSL, INSERM, Université Paris-Saclay

关键词: computer/PACS;    research methods;    statistics;    algorithm;    artificial intelligence;    best practices;   

DOI  :  10.2967/jnumed.121.262567

学科分类：医学（综合）

来源: Society of Nuclear Medicine

【 摘 要 】

The nuclear medicine field has seen a rapid expansion of academic and commercial interest 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 on technical best practices for developing AI algorithms in nuclear medicine are provided, beginning with general recommendations and then continuing with descriptions of 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.

【 授权许可】

CC BY