The new system is expected to increase polyp detection rates by 30%
Colorectal cancer is a malignancy that begins either in the colon, the final part of the digestive tract, or the rectum. Colorectal cancer typically affects older adults, though it can occur at any age and usually begins as small, noncancerous (benign) clumps of cells called polyps that form inside the colon. Over time, some of these polyps can develop into colorectal cancers.
Polyps may be small and produce few, if any, symptoms. Consequently, regular screening tests are recommended to help prevent cancer by identifying and removing polyps before they turn cancerous.
For the first time at Sheba Medical Center, an artificial intelligence diagnostic system has been integrated into the clinical activities of the Gastroenterology Institute, raising the accuracy of early-stage colorectal cancer diagnosis with improved polyp detection.
The system works by analyzing the video feed of a colonoscopy and identifying, through the use of an advanced algorithm, polyps within a few milliseconds as they appear. After the system detects polyps, they are marked with a square on the screen monitored by a physician, reducing the likelihood of missing polyps by approximately 30%.
“During a colonoscopy, we locate and remove polyps, an action which lowers colorectal cancer mortality by about 60%, particularly in the case of distal colorectal cancer,” explains Dr. Idan Levi, an expert physician at the Gastroenterology Institute and Head of the Endoscopic Innovation Service at Sheba.
According to Dr. Levi, “The system might well decrease colorectal cancer rates among those tested by it.”
For his part, Prof. Shomron Ben-Horin, Director of the Gastroenterology Institute at Sheba, added: “All future colonoscopies at Sheba will make use of AI. However, the final decision regarding the removal of a polyp will remain at the doctor’s discretion – the system simply helps him to reach an accurate diagnosis.”