Office of Undergraduate Research

Deep Learning-based Tracking of Ascending Thoracic Aorta on Human and Murine Echocardiograms DUIRI - Discovery Undergraduate Interdisciplinary Research Internship Spring 2026 Accepted Global Health According to the World Health Organization, cardiovascular disease is the leading cause of death worldwide, with over 75% of deaths resulting from cardiovascular disease being in lower- and middle-income countries. One type of cardiovascular disease is the development of aortic aneurysms. Aortic aneurysms result from weakness in the aortic wall that leads to wall expansion and ballooning. Aortic wall dissection can follow this expansion, ultimately leading to rupture of the aorta, which has a very high mortality rate. The goal of this project is to better predict the dynamics of the ascending thoracic aortic aneurysms (ATAAs), which occur in the portion of the aorta originating from the heart, using echocardiograms obtained from juvenile mice models at Purdue BME and pediatric patients at Riley Hospital for Children. We plan on developing and training deep learning models for the automated segmentation of the aortic root, to get more accurate diameter measurements, etc. that eventually affect the clinical diagnosis and development of an ATAA, based on the American Heart Association (AHA) guidelines. Shubh Parag Mehta Craig J Goergen Students assisting with this project would be expected to assist with the development and validation of deep learning models for the segmentation of ATAAs on echocardiograms obtained from pediatric patients at Riley Hospital for Children and IACUC-approved juvenile murine models at Purdue University. They will also have the opportunity to conduct comparative statistical analyses of the quantified metrics obtained from deep learning models and board-certified pediatric cardiologists (for example, Dr. Landis, a collaborator on this project. https://engineering.purdue.edu/cvirl
https://pubmed.ncbi.nlm.nih.gov/39299353/
https://docs.lib.purdue.edu/duri/60 Students interested in medical imaging and having previous coding experience in MATLAB and/or Python are highly encouraged to apply. A basic understanding of cardiovascular anatomy will be helpful but not required. 0 5 (estimated)