Researchers have developed a new artificial intelligence (AI) technology that could improve heart imaging for patients by enabling doctors to examine their hearts for scar tissue without the need of contrast injections, which are required for traditional cardiovascular magnetic resonance imaging (CMR).
The team of researchers included doctors at the University of Virginia Health System, and the paper was published in the scientific journal Circulation.
The New AI Approach
The team’s new AI approach is called Virtual Native Enhancement (VNE), and they compared it with contrast-enhanced CMR scans, which are currently used to monitor hypertrophic cardiomyopathy, which is the most common genetic heart condition.
The research demonstrated that VNE produced higher-quality images, and it better captured evidence of heart scarring without requiring the injection of the standard contrast agent.
Christopher Kramer, MD, is a researcher and the chief of the Division of Cardiovascular Medicine at UVA Health.
“This is a potentially important advance, especially if it can be expanded to other patient groups,” said Kramer. “Being able to identify scar in the heart, an important contributor to progression to heart failure and sudden cardiac death, without contrast, would be highly significant. CMR scans would be done without contrast, saving cost and any risk, albeit low, from the contrast agent.”
The most common inheritable heart disease, hypertrophic cardiomyopathy, is the most common cause of sudden cardiac death in young athletes. It reduces the heart’s ability to pump blood due to thickening and stiffening, so doctors must closely monitor it.
Doctors can use the new VNE technology to image the heart more often and more quickly, according to the researchers. It also enables early detection of subtle changes in the heart, but more testing is needed to confirm it.
The team also says that the technology could benefit patients who are allergic to the contrast agent injected for CMR. It could also help individuals with severely failing kidneys since the agent also does harm in that case.
The new approach relies on AI to enhance “T1- maps” of the heart tissue, which are created by magnetic resonance imaging (MRI). The maps are then combined with enhanced MRI “cines,” or the beating heart in this case. MRI cines are “movies” of moving tissue, and by overlaying the two types of images, the artificial VNE image is created.
Doctors are used to reading traditional contrast-enhanced CMR heart scans, but the new technology produces something almost identical and better, according to the researchers.
“Avoiding the use of contrast and improving image quality in CMR would only help both patients and physicians down the line,” Kramer said.
The new research focused on the technology’s potential in patients with hypertrophic cardiomyopathy, but the team believes it could be used for various other heart conditions.
“While currently validated in the HCM population, there is a clear pathway to extend the technology to a wider range of myocardial pathologies,” the paper says. “VNE has enormous potential to significantly improve clinical practice, reduce scan time and costs, and expand the reach of CMR in the near future.”