Stroke diagnosis, assessment, and outcome prediction

Abstract: In this talk, I will present some of our results on automatic characterization of stroke severity and long-term outcome prediction using morphometric features. I will also discuss predicting brain hemodynamics using physics-informed neural networks (PINN), where we employ in vivo real-time transcranial Doppler (TCD) ultrasound velocity measurements at several locations in the brain and baseline vessel cross-sectional areas acquired from 3D magnetic resonance imaging (MRI) angiograms to provide high-resolution maps of velocity, area, and pressure in the entire vasculature. We validate our predictions against in vivo velocity measurements obtained via 4D flow MRI scans.

Bio: Dr. Laksari is an Assistant Professor at the Department of Biomedical Engineering at the University of Arizona. He received his PhD from Temple University and completed his postdoctoral scholarship at Stanford University. Dr. Laksari’s lab focuses on biomechanics of traumatic brain injury and stroke, using a combination of medical imaging, wearable sensors and novel machine learning techniques. He is a recipient of the NIH Trailblazer award.