AI in Colonoscopies Detects Early Signs of Bowel Cancer

Technology using artificial intelligence (AI) to identify early signs of bowel cancer could gain prominence after a research study has demonstrated greater efficiency in detecting potential new cases.

Researchers at Newcastle University (Newcastle upon Tyne, UK) led the COLO-DETECT randomized controlled trial, where 2,032 participants were divided into two groups for colonoscopy procedures. A colonoscopy is a procedure involving a camera used to look inside the bowel to spot cancerous and precancerous polyps (adenomas). One group underwent colonoscopies with the assistance of the GI Genius AI device, a computer module that integrates with existing colonoscopy technology. The device highlights potential polyps by framing them with a green box on the monitor, though the final decision to remove a polyp rests with the clinician. The other group received standard, non-AI-assisted colonoscopies.

Image: The GI Genius in use during a colonscopy (Photo courtesy of NHS)

The findings published in Lancet Gastroenterology and Hepatology demonstrated that the AI-enhanced colonoscopies were more effective in identifying adenomas—polyps that could potentially develop into cancer. Specifically, the use of GI Genius led to the detection of an additional 0.36 adenomas per procedure, a significant improvement over traditional methods. Furthermore, the AI technology identified at least one adenoma in an additional 8 out of every 100 patients compared to those who had a standard colonoscopy. The technology was particularly effective in detecting sessile serrated adenomas, which are considered especially concerning due to their potential for rapid progression to malignancy. The study also found that smaller and flatter polyps were more frequently detected with the aid of the AI device. Importantly, the use of this technology did not lead to an increase in procedural complications. The incorporation of the GI Genius system extended the average duration of a colonoscopy by only about 90 seconds.

“We are delighted with the outcome of this trial. Simply put, it will save lives. This trial has demonstrated that using artificial intelligence can significantly increase detection of the kinds of abnormalities in the bowel that may progress to cancer. It allows us to find these lesions, remove them, and stop them from turning into cancer,” said Professor Colin Rees, Professor of Gastroenterology at Newcastle University who led the trial. “Crucially, we know that some of the polyps that lead to cancer are small polyps or flat polyps. The AI helped us find more of these lesions, it is finding the things we are concerned about as well as spotting things that we can miss with the human eye.”

Related Links:
Newcastle University