[ad_1]
New artificial intelligence technology for cardiac imaging has the potential to improve patient care, allowing physicians to examine their hearts for scar tissue while eliminating the need for contrast injections required for imaging. traditional cardiovascular magnetic resonance.
A team of researchers who developed the technology, including doctors from UVA Health, reports the success of the approach in a new article in the scientific journal Circulation. The team compared their AI approach, known as virtual native enhancement, with contrast-enhanced cardiovascular magnetic resonance scans now used to monitor hypertrophic cardiomyopathy, the most common genetic heart disease. Researchers found that virtual native enhancement produced higher quality images and better captured evidence of scar in the heart, all without the need to inject the standard contrast agent required for resonance scans. cardiovascular magnetic.
“This is a potentially important breakthrough, especially if it can be scaled up to other patient groups,” said researcher Dr Christopher Kramer, chief of the cardiovascular medicine division at UVA Health, the only center for excellence of Virginia designated by the Hypertrophic cardiomyopathy association. “Being able to identify a scar in the heart, an important contributor to the progression of heart failure and sudden cardiac death, without contrast, would be highly significant. Cardiovascular magnetic resonance scans would be performed without contrast, saving costs and any risk, albeit low, of the contrast agent. “
Imaging Hypertrophic cardiomyopathy
Hypertrophic cardiomyopathy is the most common inherited heart disease and the most common cause of sudden cardiac death in young athletes. It causes the heart muscle to thicken and stiffen, reducing its ability to pump blood and requiring close monitoring by doctors.
New native virtual enhancement technology will allow doctors to image the heart more often and faster, the researchers say. It can also help doctors spot subtle changes in the heart earlier, although more testing is needed to confirm this.
The technology would also benefit patients who are allergic to the contrast agent injected for cardiovascular magnetic resonance exams, as well as patients with severe kidney failure, a group that avoid the use of the agent.
The new approach works by using artificial intelligence to improve the “T1 maps†of heart tissue created by magnetic resonance imaging. These maps are combined with enhanced MRI “cines”, which look like films of moving tissue – in this case, the beating heart. The superposition of the two types of images creates the artificial virtual native enhancement image.
Based on these inputs, the technology can produce something virtually identical to traditional contrast-enhanced cardiovascular magnetic resonance heart scans that doctors are accustomed to reading – only better, the researchers conclude. “Avoid the use of contrast and improve the quality of the image in [cardiovascular magnetic resonance] would only help both patients and doctors, â€Kramer said.
While the new research has examined the potential for virtual native enhancement in patients with hypertrophic cardiomyopathy, the creators of the technology envision it being used for many other heart conditions as well.
“Although currently validated in the [hypertrophic cardiomyopathy] population, there is a clear path to extend the technology to a wider range of myocardial pathologies, â€they write. “[Virtual native enhancement] has enormous potential to dramatically improve clinical practice, reduce analysis time and costs, and expand the reach of [cardiovascular magnetic resonance] in the near future. “
About the research
The research team consisted of Qiang Zhang, Matthew K. Burrage, Elena Lukaschuk, Mayooran Shanmuganathan, Iulia A. Popescu, Chrysovalantou Nikolaidou, Rebecca Mills, Konrad Werys, Evan Hann, Ahmet Barutcu, Suleyman D. Polat, HCMR researchers , Michael Salerno, Michael Jerosch-Herold, Raymond Y. Kwong, Hugh C. Watkins, Christopher M. Kramer, Stefan Neubauer, Vanessa M. Ferreira and Stefan K. Piechnik.
Kramer has no financial interest in the research, but some of his collaborators are applying for a patent related to the imaging approach. A full list of disclosures is included in the document.
The research was made possible through work funded by the British Heart Foundation, grant PG / 15/71/31731; National Institute of Heart, Lung and Blood, National Institutes of Health, grants U01HL117006-01A1; the John Fell Oxford University Press Research Fund; and the Oxford BHF Research Center of Excellence, grant RE / 18/3/34214. The research was also funded by the British Heart Foundation Clinical Research Training Fellowship FS / 19/65/34692, the National Institute for Health Research (NIHR) Oxford Biomedical Research Center at the Oxford University Hospitals NHS Foundation Trust and the National Institutes of Health.
TO
[ad_2]