AI calculates fat buildup around the heart from MRI scans in under 3 seconds
A new artificial intelligence tool can read standard MRI scans and automatically measure fat content around the heart, according to research published Wednesday.
Fat accumulation around this vital organ can predict heart disease and has been associated with other conditions such as diabetes and atrial fibrillation. But manually measuring this is difficult and time-consuming, Queen Mary University of London experts explained July 7 in Frontiers in Cardiovascular Medicine.
"To address this problem, we've invented an AI tool that can be applied to standard heart MRI scans to obtain a measure of the fat around the heart automatically and quickly, in under three seconds,” study lead Zahra Raisi-Estabragh, PhD, said in a statement. “This tool can be used by future researchers to discover more about the links between the fat around the heart and disease risk, but also potentially in the future, as part of a patient's standard care in hospital."
The team tested their algorithm on more than 45,000 patients’ cardiac MRI scans, including data from the U.K. Biobank—a repository of health info from more than half a million individuals. Automated MRI fat measurements were then compared to reference standard cardiac CT quantification.
The two approaches were comparable, showing the algorithm can accurately determine the amount of fat around the heart. It also accurately calculated patients’ risk of diabetes.
And with further testing, it may soon find its way into real-world practice.
"This novel tool has high utility for future research and, if clinical utility is demonstrated, may be applied in clinical practice to improve patient care,” the authors concluded.
Matt joined Chicago’s TriMed team in 2018 covering all areas of health imaging after two years reporting on the hospital field. He holds a bachelor’s in English from UIC, and enjoys a good cup of coffee and an interesting documentary.