Yogesh Rathi, PhD :: The Baker Center For Children and Families

Yogesh Rathi, PhD

Associate Professor, Harvard Medical School

Research Roles/Affiliations

Associate Professor, Department of Psychiatry and Radiology, BWH

Associate Director, PNL

Research Associate, Department of Psychiatry, MGH

Contact Information

E-mail: yogesh@bwh.harvard.edu

Relevant Links

Google Scholar profile

PubMed profile

Harvard Catalyst Profile

Research

Yogesh received his PhD in Electrical and Computer Engineering in 2006 from Georgia Institute of Technology, Atlanta. He obtained a Master’s in Mathematics and Bachelors in Electrical and Electronics Engineering from the Birla Institute of Technology and Science, Pilani, India.

His research interests lie in developing smart computational magnetic resonance imaging techniques to understand brain structure and function. He has developed several compressed sensing algorithms for fast imaging of diffusion MRI — a technology that can be used to obtain fast MRI scans while preserving quality (use cases include children and adults who cannot stay still in the scanner for a long period). His current research focus is on 1). Ultra-high resolution diffusion imaging combining acquisition and reconstruction, 2). Harmonization of MRI data acquired from different scanners, from acquisition to post-processing, 3). Developing and validating advanced tractography algorithms for uncovering the mysteries of white matter connectivity in human and primate brains, 4). Estimating tissue microstructure (e.g. axon diameter) from biophysical and stochastic models of diffusion, and 5). Time-series analysis for understanding functional connectivity using fMRI data. His clinical research focus includes using and developing sophisticated tractography algorithms for precise targeting of deep-brain stimulation (DBS) and transcranial magnetic stimulation (TMS) in obsessive compulsive disorder (OCD), Parkinson’s and major depressive disorder (MDD). His broad research focus is in the areas of signal and image-processing, statistics, control theory, machine learning, computer vision and related applications to solve inverse problems in medical imaging.