Faculty Friday: How AI Cuts the Time Humans Spend in MRI Machines

Paul Hand

 

How can artificial intelligence techniques shorten the length of time people spend in MRI machines? In this #FacultyFriday video, Paul Hand, assistant professor of mathematics and computer science at Northeastern University and key member of the Institute for Experiential AI explains how AI methods like generative modeling and unsupervised learning help mimic human tissue in an MRI – and how how this cuts the time people spend in an MRI machine.

 

Biography

Paul Hand is an assistant professor of mathematics and computer science. His research group builds theory and algorithms in machine learning and AI in the context of vision and imaging. His work includes AI methods related to X-ray crystallography, astronomical imaging, MRI, image manipulation, among others.

With the intent of using AI to reduce the time and cost of acquiring image data, Hand trains on tens of thousands of sample images to help AI learn patterns, which he applies to more efficiently and quickly construct new images. His team also builds effective AI techniques that resist biases in these training datasets.

Widely published in prominent mathematics journals and leading machine learning conferences, Hand’s research received funding through a National Science Foundation CAREER award. Hand has also presented at the Conference on Neural Information Processing Systems.

Before joining Northeastern, Hand was an assistant professor of computational and applied mathematics at Rice University and an applied mathematics instructor at MIT. He earned his doctoral degree in mathematics from New York University, where he received the Kurt O. Friedrichs Prize for outstanding dissertation in mathematics. He completed his postdoctoral work in the Department of Cardiology at New York University.