Research Overview
Assistant Professor of Computer Science in Radiology
My research encompasses many computational problems in medical imaging. My recent work has focused on the reconstruction of MR images from partially obtained data and on improving MRI resolution. I am the inventor of the EPIGRAM algorithm for reconstructing highly under-sampled data using graph-cuts. I am now focusing on brain imaging, particularly network-theoretic analysis of neuroimaging data like Diffusion Tendor Imaging, functional MRI and MRI brain morphometry. The goal is to find network characteristics that distinguish healthy brains from pathological brains for a number of brain disorders like Alzheimer's, Epilepsy, Autism, Schizophrenia and Stroke. New methods coming out of my lab include 1. graph-cut software for the Bayesian reconstruction of accelerated MR imaging 2. a spatially adaptive algorithm for high angular resolution diffusion imaging (HARDI) with greatly enhanced crossing fiber resolution 3. network-level analysis of regional cortical thickness from structural MRI 4. a new method of creating whole-brain networks from DTI data
