AI carries ‘enormous potential’ to transform cardiac MRI, reduce scan times without using contrast
A newly developed artificial intelligence system produces higher quality heart scans compared to traditional modalities but without required contrast.
The technology—known as virtual native enhancement or VNE—combines augmented, T1 heart maps with MRI cines to create images superior to contrast-enhanced cardiac MR heart images. After developing and testing it on more than 2,500 cardiomyopathy datasets, the AI better captured evidence of scarring on patients’ hearts.
It’s an important advancement, particularly if its developers can expand the technology to other patient populations, Christopher Kramer, MD, chief of the Division of Cardiovascular Medicine at UVA Health, said Tuesday.
“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,” Kramer added in a statement. “CMR scans would be done without contrast, saving cost and any risk, albeit low, from the contrast agent.”
The VNE approach is based on more than 1,300 hypertrophic cardiomyopathy patients who provided 4,093 matched T1 maps, cines and late gadolinium enhancement CMR datasets. More than 2,600 sets were used to develop the tool and 345 were saved for independent testing.
Four readers blinded to results agreed, VNE produced higher-quality images compared to gadolinium-enhanced CMR scans. And in 121 patients, AI-generated scans correlated with traditional heart imaging for detecting and quantifying hyperintensity myocardial lesions and intermediate-intensity lesions.
Kramer and colleagues, who are currently seeking a patent related to their imaging technology, only see more possibilities ahead.
“While currently validated in the hypertrophic cardiomyopathy population, there is a clear pathway to extend the technology to a wider range of myocardial pathologies,” the group added. “VNE has enormous potential to significantly improve clinical practice, reduce scan time and costs, and expand the reach of CMR in the near future.”
Read more about the technique in Circulation.
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.