From left, ECE graduate student Li Chen, with UW Medicine researchers Niranjan Balu and Chun Yuan studying artificial intelligence’s ability to help read radiology scans.
MRI scans of 4,796 patients’ knees have become a digital trove, helping to prove that artificial intelligence (AI) can recognize cardiovascular risk as accurately as medical specialists can – and in a fraction of the time. “This will be valuable for cardiologists, neurologists, radiologists, epidemiologists and for patients who need preventive care for heart attack and strokes,” said Chun Yuan, a bioengineer and UW Medicine radiology researcher.
Yuan is the principal investigator in a massive study to establish a computer algorithm’s ability to identify an artery and delineate its inner and outer boundaries, just as radiologists do by hand to discern vessel wall thickening.
The initial findings were published recently in the journal Magnetic Resonance in Medicine.
Knee MRIs, of course, are not intended to diagnose atherosclerosis, but rather to reveal sources of musculoskeletal pain. These patient scans had initially been ordered in a study of osteoarthritis. But knee MRIs inevitably include the popliteal artery, which runs vertically behind the knee joint. It has the potential to depict someone’s vascular health as well as vessels nearer the heart.
“This project was among many funded by the American Heart Association to explore AI,” said Yuan. “It took more than a year to develop the algorithm that we used to analyze about 3.5 million images.”
The algorithm was written by Electrical & Computer Engineering (UW ECE) Ph.D. student Li Chen, with guidance about knee MRI from Niranjan Balu, a research assistant professor of radiology. Chen is a research assistant in the Vascular Imaging Lab (VIL) led by Dr. Yuan, focusing on MRI vessel wall analysis, including artery tracing, vessel wall segmentation and quantification. By learning new computer vision knowledge under UW ECE professor Jenq-Neng Hwang, Chen has successfully adapted and applied innovative techniques in computer vision to medical problems such as this.
AI’s magic lies in its speed and consistency. It would be unthinkable for a radiologist to hand-label 3.5 million blood vessels and contours. It only took seven minutes for AI to process one knee scan, versus as long as three hours for an experienced human (one MRI knee series is comprised of around 70 images, collectively covering about 4 vertical inches of knee joint). Chen believes further exploration in machine learning will transform the current medical system, offering it the ability to deliver more accurate, intelligent and efficient healthcare for patients.
Depicted in the video above, artificial intelligence (right image) identifies and traces the popliteal artery behind the knee. “We did an extensive validation study in parallel showing that AI can learn to analyze scans of blood vessels with comparable accuracy to experienced humans,” Yuan said. “Cutting the review time is only part of the accomplishment here; adding AI raises the confidence that any scan of a blood vessel can help predict a person’s cardiovascular risk.”
“Think of how many knee MRIs are out there. An AI algorithm to read knee MRIs for cardiovascular risk adds value that wasn’t there before,” Yuan added.
As a bonus, the patients’ knee MRIs also covered a span of eight years, so Yuan has data about how the vessel lesions evolve. And because the scans emerged initially from suspicions of osteoarthritis, those patients are considered “near-normal population” – that is, people for whom cardiovascular risk didn’t factor into their inclusion in the study.
Their research has won an AHA competition on precision medicine, earning an award amount of $250,000.
Story adapted from UW Medicine | Newsroom