Detecting Disease-Related Structural Changes in Neurological Disorders
Award Imaging Scientist
Funding Cycle Cycle 2
Pramod Pisharady, PhD
University of Minnesota (Center for Magnetic Resonance Research)
Dr. Pisharady’s expertise is in developing novel computational algorithms for improved decoding of information from images. His journey in imaging started at the National University of Singapore (NUS), where he did his doctoral research in computer vision and pattern recognition. He began research in medical imaging when he was a postdoctoral researcher at Massachusetts Institute of Technology (MIT), where he developed computational algorithms for diffusion magnetic resonance imaging (MRI) analysis. In his current position as Research Associate at the Center for Magnetic Resonance Research (CMRR) at the University of Minnesota Medical School, he works on diffusion MRI-based estimation of brain and spinal cord microstructure, with applications in detecting disease-related structural changes in neurological disorders. He also works as a scientist in the NIH-funded image analysis core at CMRR, providing advice, analysis support, and training to the other imaging cores at CMRR and across the University.
The goal of this research is to accomplish early diagnosis of neurodegenerative diseases such as Amyotrophic Lateral Sclerosis (ALS), Parkinson’s disease, and ataxia. This project will develop analysis tools to understand the microlevel cellular structures and the neural circuit connections through the noninvasive imaging modality, MRI. The project aims to make a substantial step forward in bridging the gap between microscopic imaging—the gold standard for tissue microstructure—and MRI, the gold standard for clinical imaging. Dr. Pisharady will propose machine learning algorithms for microstructure estimation, transferring a deep neural network trained using diffusion MRI and microscopy data in the animal domain to the human domain, in order to better detect tissue microstructural alterations in neurodegenerative diseases and improve disease diagnosis from clinical MRI data.