Projects

Overhauser Dynamic Nuclear Polarization of Water Vapor

This project develops an Overhauser dynamic nuclear polarization platform to enhance nuclear magnetic resonance and magnetic resonance imaging signals through efficient electron–nuclear polarization transfer using a custom microwave transmission system, loop-gap resonator, and inhalable hyperpolarized aerosols for high-sensitivity pulmonary imaging at low magnetic fields.

NMR

Noninvasive Estimation of Electrical Properties from Magnetic Resonance Measurements

This project develops a three-pronged strategy—combining global inverse modeling, physics-informed neural networks, and vision transformers—to generate high-resolution maps of tissue electrical properties using MRI, with broad applications in medical imaging and treatment.

QUANTITATIVE MRI   SIMULATIONS

Multiparametric Mapping of Knee Joint with Magnetic Resonance Fingerprinting

This project develops advanced magnetic resonance fingerprinting (MRF) methods enhanced with machine learning to improve the efficiency and robustness of MRI for early detection of osteoarthritis (OA) in the knee by identifying biochemical and structural changes before visible damage occurs.

MSK   QUANTITATIVE MRI

Prediction Models of Knee Osteoarthritis Incidence and Progression using Deep Learning

This project develops and validates deep-learning models that analyze clinical and imaging data to predict individuals' five-year risk of knee osteoarthritis progression and total knee replacement, aiming to enable early intervention and personalized treatment.

AI   MSK

Biomarkers of Abnormal Brain Aging

This research investigates early mechanisms of abnormal brain aging and validates early biomarkers to identify pre-symptomatic stages before clinical symptoms appear.

AGING   BRAIN
1 5 6 7