With a 73 percent positive predictive value, the AI technique accurately identified 80 percent of the instances of plaque erosion.
“If cholesterol plaque lining arteries starts to erode it can lead to a sudden reduction in blood flow to the heart known as acute coronary syndrome, which requires urgent treatment,” said research team leader Zhao Wang from the. “Our new method could help improve the clinical diagnosis of plaque erosion and be used to develop new treatments for patients with heart disease.”
In order to address this issue, Wang collaborated with a team of engineers from his institution and medical professionals from The 2nd Affiliated Hospital of Harbin Medical University under the direction of Bo Yu to create an automated, objective method that uses AI to identify plaque erosion based on OCT images. They explain the new method in the Optica Publishing Group journaland demonstrate that it is accurate enough to possibly serve as the foundation for clinical diagnosis.
When OCT is used for intravascular imaging, the imaging probe is automatically pulled backward inside a catheter, producing hundreds of images for each pullback. The researchers tested their method using 16 pullbacks of 5,553 clinical OCT images with plaque erosion and 10 pullbacks of 3,224 images without plaque erosion. The automated method correctly predicted 80 percent of the plaque erosion cases with a positive predictive value of 73 percent.