An AI algorithm that helps doctors detect suspicious colon cancer lesions in real time during a colonoscopy. It is possible thanks to a medical device that uses this algorithm that has just been approved by the American Food and Drug Administration (Fda) with all Italian data. In fact, the algorithm was validated in the Humanitas AI Center with a study that also saw the participation of the Regina Margherita hospitals in Rome and Valduce in Como.
AI reveals 13% more polyps
Colonoscopy is the best ‘tool’ for the prevention and diagnostic confirmation of this type of cancer. The examination involves the introduction of a flexible tube inside the body, which allows to identify colon polyps, or small changes in the mucosa that could develop into cancer. Some polyps, however, ‘escape’ the diagnosis or are not correctly classified with colonoscopy alone. The AI endoscopic device, called GI Genius, helps detect 13% more adenomas (polyps) or colon cancer lesions by generating low-volume markers and sounds that signal to the doctor where a more in-depth visual evaluation is needed . “The device, applied to traditional colonoscopy, suggests areas of the colon that they may not have noticed, reducing the human risk of not seeing suspicious lesions and increasing diagnostic accuracy for colorectal cancer,” he explains. Alessandro Repici, director of the Department of Gastroenterology and Digestive Endoscopy of Humanitas and professor of Humanitas University. The device, however, does not replace the specialist or laboratory tests and does not suggest how to manage suspected polyps. “It is up to the doctor – Repici clarifies – to decide whether the lesion is suspicious, and how to proceed according to standard clinical practice and guidelines”.
From molecular diagnosis to telepathology, the evolution of pathological anatomy
by Irma D’Aria
The Italian study
The FDA has evaluated the safety and efficacy of GI Genius with an all-Italian multicenter study, conducted on 700 patients, of which 35% in Humanitas, aged between 40 and 80 who underwent a colonoscopy for the colorectal cancer screening or surveillance, following blood in stool or gastrointestinal symptoms. Study participants had standard colonoscopy with the AI device or standard colonoscopy only. “The use of artificial intelligence applied to traditional colonoscopy was able to identify laboratory-confirmed adenomas or carcinomas with 13% increased diagnostic accuracy,” Repici points out. The work is continuing with further in-depth studies in this area. After FDA approval, when will the European one and then the Italian one arrive? “In reality – explains the gastroenterologist – the system was approved with the CE mark for use in Europe about a year ago and this approval also applies to Italy”. The other good news is that it is a system that can be used on a large scale in Italian hospitals: “It can be applied to any type of colonoscopy and to any brand of endoscope so it is practically universal,” Repici confirms.
A mini-camera pill to discover bowel diseases
by Annalisa Bonfranceschi
Colon cancer
Colorectal cancer is the second most frequent cancer in Italy. It typically starts from adenomas (intestinal polyps) that form on the colon wall or from other precancerous lesions in the rectum or colon (large intestine). Endoscopic colonoscopy, part of the colorectal cancer screening and surveillance plan, is done by endoscopy doctors to detect changes or abnormalities in the lining of the colon and rectum. Colonoscopy involves passing an endoscope, which is a thin, flexible tube with a camera at the end, through the rectum and along the length of the colon, which allows the experienced doctor to view any signs of cancer or precancerous lesions.
Colon cancer: microbiota bacteria responsible for liver metastases
by Irma D’Aria
.