Rapid, Deep-Learning-Based Magnetic Resonance Imaging (MRI) Reconstructions: An Overview

Speaker:

Yvonne W. Lui, MD

Professor and Vice Chair of Research

Department of Radiology, NYU Grossman School of Medicine

Abstract:

Magnetic resonance imaging (MRI) remains one of the most powerful tools for noninvasive visualization of anatomy and physiology. Yet conventional image reconstruction methods used for MRI are computationally demanding and time-intensive, limiting both throughput and accessibility. Recent advances in artificial intelligence (AI) and deep learning have revolutionized MRI reconstruction, enabling accelerated acquisition and improved image quality without sacrificing diagnostic fidelity. In this presentation, Dr. Lui, will provide an overview of state-of-the-art deep-learning approaches for rapid MRI reconstruction. She will discuss how neural networks are trained to reconstruct high-quality images from undersampled data, thereby dramatically reducing scan time and enhancing patient comfort. Examples from her own research will highlight the integration of AI-based reconstruction with quantitative neuroimaging to probe brain microstructure and function. Dr. Lui will also place these developments in a broader translational context, drawing from her team’s work applying machine learning to traumatic brain injury, concussion, and sex-related brain-structure differences. By combining innovations in physics-based modeling, advanced image processing, and neural network design, her group is advancing MRI toward a faster, smarter, and more informative clinical modality. This talk will appeal to audiences interested in medical imaging, computational modeling, and the transformative role of deep learning in healthcare diagnostics and neuroscience research.

Dr. Lui, MD, received her BS in Physics from Swarthmore College and MD from Yale University, followed by residency and neuroradiology fellowship at NYU. A board-certified neuroradiologist, she has dedicated more than two decades to advancing neuroimaging through the integration of physics, computation, and clinical medicine. Dr. Lui leads a multidisciplinary team of over 100 researchers and clinicians and serves as principal investigator on multiple NIH- and DoD-funded studies focused on traumatic brain injury, concussion, and brain microstructure mapping. A past president of both the American Society of Neuroradiology and the New York Roentgen Society, Dr. Lui has been recognized as a Distinguished Investigator by the Academy for Radiology & Biomedical Imaging Research and was recently honored with the T. Hans Newton Lecture at UCSF. Through her leadership and innovation, she continues to shape the future of AI-driven neuroimaging and translational radiology research.