New AI Tool Enhances Low-Quality Cardiac MRI Scans and Speeds Up Imaging
A novel artificial intelligence model known as TagGen can restore low-quality cardiac MRI images, enabling clinicians to extract critical diagnostic information even from blurred scans, according to findings published in Magnetic Resonance in Medicine.
Developed by a multidisciplinary team of biomedical engineers, radiologists, and cardiologists, TagGen offers a solution to a common challenge in cardiac imaging: poor image sharpness.
“If you have a blurry image, you have very few ways to recover the fine details or quality of the image,” said lead author Changyu Sun, PhD, an MRI researcher at the University of Missouri School of Medicine. “The sharpness reveals very important information for the clinical diagnosis, like if there’s abnormal movement or any dysfunction.”
Trained, validated, and tested on more than 2,000 MRI images collected from a single hospital between August 2022 and June 2024, TagGen demonstrated its ability to enhance resolution and recover critical features in cardiac scans. In particular, it produces clearer taglines—visual markers that track muscle movement—giving cardiologists the clarity needed for accurate assessments.
One of the most promising aspects of TagGen is its ability to reduce scan times while preserving diagnostic quality. This not only enhances patient comfort but also boosts efficiency for imaging centers.
“During a heart MRI scan, patients are asked to hold their breath to reduce chest movement from breathing, which helps create clearer images,” Sun explained. “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.”
Looking forward, the researchers plan to continue refining TagGen and exploring its application across other imaging modalities, potentially extending its benefits beyond cardiac MRI.