Quantitative MRI and Physics-informed Pan-Contrast AI

Registration Required
Speaker Short Biography: Dan Ma, PhD, is an Associate Professor of Neurosurgery and Biomedical Engineering at Duke University. Her research focuses on quantitative MRI across acquisition, reconstruction, and analysis, with clinical applications in neurological diseases, pediatric imaging, cancer imaging. She is a Senior Member of the National Academy of Inventors, a Junior Fellow of the International Society for Magnetic Resonance in Medicine (ISMRM), and a recipient of the ISMRM I. I. Rabi Young Investigator Award
Talk Summary or Abstract: This talk will present recent advances in quantitative MRI and physics-based image synthesis as a foundation for pan-contrast AI. I will describe how qMR parameter mapping enables reproducible tissue property characterization and how signal modeling and simulation can be used to synthesize clinically meaningful contrasts from a single, short MR scan. These synthetic images can be used to train contrast-agnostic AI models that are more generalizable and robust for downstream tasks, such as segmentation, detection and treatment planning.