Application of Artificial Intelligence to Diseases that Affect Bone, Muscle, and Fat. What Was New in 2023?

We will review the fundamentals of what defines artificial intelligence, how it is used, and what was new science this past year.

OBJECTIVES
  1. Describe How deep learning differs from previous methods regarding imaging analysis.
  2. Describe how large language models work and their strengths and weaknesses for generating clinically relevant text.
  3. Describe what advances were made in AI for MSK in 2023 as compared to the year before.

John Shepherd PhD, CCD

Professor/Chief Scientific Officer

University of Hawaii Cancer Center, Honolulu, HI

Dr. Shepherd is a Researcher/Professor at the University of Hawaii Cancer Center, a Fulbright Scholar, a Fellow of the American Institute for Medical and Biological Engineering (AIMBE), and a former President of the International Society for Clinical Densitometry. He received his PhD in Engineering Physics from the University of Virginia and then completed a Postdoctoral Fellowship in Biophysics at Princeton University. From there he went on to develop body composition and bone density algorithms for a major women’s health company and his patents are the basis for the accuracy of that company’s body composition algorithms. He then joined the Radiology Department of the University of California San Francisco and led his own research group for 19 years studying a wide variety of biomarkers for breast cancer, obesity and osteoporosis from medical imaging using advanced machine learning techniques. For the past 5 years, he has been with the University of Hawaii Cancer Center and is currently their Chief Scientific Officer. He also directs the UH Artificial Intelligence Precision Health Institute and the Hawaii Pacific Islands Mammography Registry. He has been continuously funded from the NIH since 2005, led 6 R01-funded studies, published over 350 peer-review publications that have been referenced over 23,000 times, and lastly is an avid surfer and island ridge hiker!

Components visible upon registration.