The National Science Foundation awarded Roshan D’Souza, associate professor of mechanical engineering and Alan D. Kulwicki ’77 faculty fellow, a $1.1 million grant to research the hemodynamics from subtraction-computed tomography angiography (SCTA). The four-year grant comes through NSF’s Smart and Connected Health Program and starts in September.
SCTA is a non-invasive diagnostic imaging technique to assess cerebral artery stenosis, or arteries in the brain that are fully or partially blocked. The condition can lead to strokes.
While SCTA produces static images of anatomy of blood vessels, D’Souza’s project is a physics-informed machine-learning approach to map time-resolved blood flow velocities from SCTA. The goal is accurate image-based analysis of blood flow which could lead to prognostic tools based on hemodynamic biomarkers in diseases such as cerebral aneurysms.
D’Souza’s research is advancing image-based hemodynamic analysis of cardiovascular diseases
D’Souza is advancing hemodynamics analysis of cardiovascular diseases through advanced processing of blood flow images from imaging scans using flow physics-informed deep learning.
In 2021, the NSF awarded him a three-year, $298,000 grant to research hurdles to 4D-Flow MRI, which represents the newest generation of Magnetic Resonance Imaging (MRI) technology; 4D MRI adds a time dimension to this traditionally 3D technology, making it possible to image time-resolved hemodynamic flows.
The concept feasibility studies for both grant proposals were supported by seed grants from the college’s Dean’s Office in 2019 and 2020.