Vision, Language, and Vision-Language Modeling in Radiology, Tyler Bradshaw

Speaker: Tyler Bradshaw, PhD | Assistant Professor & Director of Clinical Nuclear Medicine Physics, Department of Radiology, University of Wisconsin – Madison

Date: Monday, September 16th, 2024

Time: 10:00 AM Central Time

Location: WIMR 2409 or Zoom

Title: Vision, Language, and Vision-Language Modeling in Radiology

Abstract: In this talk, I will discuss the convergence of vision and language AI algorithms into vision-language models. I will discuss their applications within the domain of radiology, especially in nuclear medicine. With the recent emergence of large multimodal models (LMMs), it is important for researchers and clinicians to understand how these models are developed and what their likely applications will be in medicine.

Bio: Dr. Bradshaw is an Assistant Professor at the University of Wisconsin-Madison in the Department of Radiology, Imaging Sciences Section. He obtained a PhD in Medical Physics from the University of Wisconsin in 2016. He is the Director of Clinical Nuclear Medicine Physics at UW-Madison and leads the Learning Algorithms in Radiology (LAIR) Lab. His lab focuses on using artificial intelligence to automate the analysis and interpretation of medical images. In particular, they explore novel methods for combining medical image analysis and large language modeling. Dr. Bradshaw has served on the Board of Directors for the Physics, Instrumentation, and Data Science Council (PIDSC) of the Society of Nuclear Medicine and Molecular Imaging (SNMMI) and is Co-Chair of the SNMMI Artificial Intelligence Task Force.