Doctors currently measure how aggressive a breast tumor is using the same
generic dye-delivery curve for every patient, rather than one specific to that patient. This
is a problem because the individualized curve can’t be measured directly: it requires a
clear view of the aorta, which isn’t visible in the available scans, and no public dataset
shows that vessel clearly enough to measure it instead. We addressed this by building a
simulated dataset that inserts a mathematically accurate vessel signal into real patient
scans, verifying its placement pixel-for-pixel against an expert-annotated reference
image. Using this dataset, we trained two deep learning models (MedT and UNesT) and
compared them against an existing pretrained model (TotalSegmentator) on how
accurately and quickly each could locate the vessel. The result is a simulated dataset of
over a thousand labeled exams, a head-to-head comparison of these three vessel-
detection models, and a clear next step: adapting a faster detection model and testing all
three on real patient scans that do show the aorta.
Watch the team present this project at 00:51:42 in the session recording here.
Keywords: DCE-MRI kinetic analysis, aorta segmentation, synthetic medical imaging
dataset, deep learning vessel detection
Faculty Advisor
Batu Gundogdu holds a Ph.D. in Electrical Engineering and is an Associate Clinical Professor at the University of Chicago, bringing over 15 years of experience developing deep-learning models across the fields of speech, language, and medical imaging. Most recently, he served as Head of AI Engineering at Eva, an AI compute startup, building algorithms for a novel next-generation AI hardware.
Previously, Dr. Gundogdu served as Research Faculty in the Department of Radiology at the University of Chicago for four years, where he led AI efforts at the MRI Research Center.
In the UChicago MS in Applied Data Science program, he shares his practical insights and experiences with students on being an AI engineer and scientist across diverse venues, including research institutions (UChicago MRI Research Center), corporate companies (Analog Devices – ADI), government (Navy and NATO), and startups (Eva). He teaches courses on Bayesian Machine Learning for Generative AI and Deep Learning.
Dr. Gundogdu also teaches in UChicago’s MS in Applied Artificial Intelligence program, where he is a founding faculty member. Drawing on his experience across research, industry, and startups, he helps students connect advanced AI concepts with the realities of building and deploying AI systems in practice. He is also a Co-Founder of VicVox, a boutique AI startup analyzing social discourse.