Artificial intelligence improves colonoscopy accuracy
By authors from HospiMedica International
Posted on March 02, 2023
Colon cancer is one of the deadliest cancers in the world today, and its incidence rate has steadily increased among younger people. Colonoscopy is currently considered the best method for detecting and preventing colon cancer. However, it is difficult to detect precancerous polyps in patients who are most at risk, particularly those with IBDs such as Crohn’s disease and ulcerative colitis. The precancerous lesions they develop can be very flat or only slightly raised, making them difficult to detect during colonoscopy. Recent studies suggest that more than half of colon cancer cases after colonoscopy are due to lesions missed during previous examinations. To address this problem, scientists are now investigating the use of AI to locate these elusive polyps.
Researchers at the Mayo Clinic (Rochester, MN, USA) are investigating the use of AI to improve the detection rate of polyps in colonoscopy. AI is being used by gastroenterologists in a variety of gastrointestinal disorders with the aim of detecting signs earlier and making them easier to treat. In the case of colon cancer, the AI system scans the real-time video feed of the colonoscopy and highlights potential polyps with small red boxes, helping doctors spot them faster. Adding AI to traditional colonoscopies can help doctors better spot polyps that might otherwise have been missed.
Image: AI can detect and eliminate cancer risk during on-site colonoscopy (Photo courtesy of Pexels)
The Mayo Clinic performs approximately 800 to 900 surveillance colonoscopies on IBD patients annually, which has provided them with a rich database for developing AI systems to improve the process. This data serves as “ground truth” or real-world examples used to train AI algorithms. The team will annotate images from a sample of 1,000 patients, review all colonoscopy videos, and mark lesions in still images from multiple angles. The annotated images are then fed into a computer to create AI machine learning algorithms that can teach the machine how to recognize polyps associated with IBD. Researchers are also creating a new digital endoscopy platform that will film all internal procedures, correlate them with medical records, and then integrate AI back into procedures where necessary.
“We are all familiar with facial recognition software. Instead of training the AI to recognize faces, we are training it to recognize polyps,” said James East, MD, a gastroenterologist at Mayo Clinic Healthcare in London.
Related Links:
Mayo Clinic
