Our eyes can see, but they can also become an indicator of cardiovascular disease. German researchers have developed a method to detect atherosclerosis, a disease of the arteries, using images of the eyes. In their study, published in the journal Scientific Reports, they explain that it is the blood vessels, which are very numerous in the eyes, that make it possible to detect the signs of the disease.
Why use the eye to screen for atherosclerosis?
Atherosclerosis is an important cause of heart attacks and strokes. It is caused by the formation of plaques on the walls of the arteries.
“Because it usually causes no symptoms in the early years, atherosclerosis is often not diagnosed until after the side effects have already occurred,” explains Dr. Nadjib Schahab, one of the study’s authors. The condition can cause circulatory problems in the legs and arms, which can lead to amputation in the most severe cases. “The risk of a fatal heart attack or stroke is significantly increased – even in the early stages of the disease,” the scientist adds. He and his team are working on an early detection method to prevent the disease from progressing to these stages. Arteries and veins can be easily observed and photographed through the pupil.
An algorithm trained to recognize pathology
To test their hypothesis, the study authors photographed the eyes of 97 women and men suffering from atherosclerosis. “In more than half of them, the disease was still at a stage where it did not cause any symptoms,” says co-author Dr. Maximilian Wintergerst. At the same time, images were taken of 34 people who did not have the disease. In a second step, the images were scanned into a software program called a convolutional neural network: this is inspired by the way the human brain works. The scientists taught the software to recognize the signs of disease by first training it with a different pathology of the eye vessels. This allowed the algorithm to detect whether or not the presented eye images were from a patient with atherosclerosis. “80 percent of all presented people were correctly identified, taking into account 20 percent false positives, i.e. healthy people who were misclassified as sick by the algorithm,” says Thomas Schultz, another co-author. This is amazing because even for trained ophthalmologists, atherosclerosis cannot be detected from fundus images.”
A future screening technique
The study authors are not leaving it at that for these first exciting results: they want to improve their method even further. In particular, they plan to collaborate with ophthalmology and vascular medicine centers to obtain additional fundus images of people suffering from atherosclerosis. Their long-term goal is to develop a simple, fast, and reliable diagnostic tool.