Tyler Bradshaw, PhD was lead author on the report, “Nuclear Medicine and Artificial Intelligence: Best Practices for Algorithm Development,” from the Artificial Intelligence (AI) Task Force of the Society of Nuclear Medicine and Molecular Imaging (SNMMI) that was recently published online in the Journal of Nuclear Medicine. Dr. Bradshaw led a team within the AI Task Force whose goal was to define technical best practices for AI algorithm development in nuclear medicine.
The report provides suggestions for avoiding pitfalls that are common to AI studies in medical imaging. Dr. Bradshaw says, “It is the first of a series of reports that the AI Task Force will publish in the coming months, all of which aim to guide the nuclear medicine field in developing and validating AI algorithms.” The SNMMI AI Task Force consists of physicians, physicists, commercial software developers, and regulatory specialists working in nuclear medicine. “We provide guidelines that can help elevate the quality of AI studies in nuclear medicine, which will be particularly useful to those that are newcomers to machine learning.”