Researchers at the University of Missouri have unveiled TagGen, an AI-driven model that reduces cardiac MRI scan times by 90% while significantly enhancing image quality. This cutting-edge technology promises to revolutionize heart diagnostics, offering faster, more accurate assessments and improved patient outcomes.
In a breakthrough that could revolutionize cardiac care, researchers from the University of Missouri (MU) School of Medicine and the School of Engineering have unveiled an artificial intelligence (AI) model, TagGen, that transforms low-quality MRI heart scans into high-resolution images while slashing scanning time by about 90%.
Cardiac magnetic resonance imaging (MRI) scans are vital in diagnosing heart conditions, as they reveal how well the heart is working and identify potential issues. However, these scans often suffer from poor quality due to patient movement. Traditional MRI scans typically take between 30 and 90 minutes, posing a challenge for both patients and medical professionals.
This is where TagGen steps in. Developed by MU researchers, the AI-assisted model significantly enhances the clarity of MRI images, making it easier for doctors to observe the heart’s function.
“If you have a blurry image, you have very few ways to recover the fine details or quality of the image,” lead researcher Changyu Sun, an assistant professor of radiology at the Mizzou School of Medicine and an assistant professor of biomedical engineering at the Mizzou School of Engineering, said in a news release. “The sharpness reveals very important information for the clinical diagnosis, like if there’s abnormal movement or any dysfunction.”
One of the key advantages of TagGen is its ability to improve the visibility of taglines, markers that track muscle movement within the heart. This heightened detail allows health care providers to pinpoint areas of the heart that aren’t functioning properly, facilitating more accurate diagnoses and treatment plans.
The AI-enhanced process not only improves image quality but also reduces the time needed for patients to hold their breath during the scan, from over 20 heartbeats to just three.
“During a heart MRI scan, patients are asked to hold their breath to reduce chest movement from breathing, which helps create clearer images,” Sun added. “Some scans take more than 20 heartbeats, making it harder for patients to hold their breath. By using TagGen to maintain the taglines, doctors can see information they would have otherwise missed, and patients only need to hold their breath for three heartbeats. This technology will lead to better diagnoses and improved patient outcomes.”
The implications of this technology stretch beyond cardiac MRI scans. Sun and his team are working on adapting the AI technique for other types of scans, including computed tomography (CT) scans and MRIs for different organs such as the brain. This could potentially lead to widespread improvements in imaging across various medical fields.
Co-authors of the study, published in the journal Magnetic Resonance in Medicine, include Cody Thornburgh, Yu Wang, Senthil Kumar and Talissa Altes, all affiliated with MU Health Care.