Marketing authorized for first AI device to detect potential signs of colon cancer

The device uses artificial intelligence (AI) based on machine learning to assist clinicians in the real-time detection of lesions, such as polyps or suspected tumors, in the colon during a colonoscopy.


The FDA has authorized marketing of the first device that uses artificial intelligence (AI) based on machine learning to help clinicians detect lesions, such as polyps or suspected tumors, during colon cancer screening and surveillance, the agency announced on April 9.

The GI Genius is designed to be compatible with many FDA-cleared standard video endoscopy systems and is composed of software that uses AI algorithm techniques to identify regions of interest in the colon. During a colonoscopy, the system generates markers and superimposes them on the video from the endoscope camera when it identifies a potential lesion. These signs signal to the clinician that further assessment may be needed, such as a closer visual inspection, tissue sampling, testing or removal, or ablation of the lesion.

Safety and effectiveness were assessed in a multicenter randomized controlled study in Italy with 700 participants ages 40 to 80 years who were undergoing colonoscopy. The primary analyses from the study were based on a subgroup of 263 participants who were being screened or surveilled every three years or more. They received white light standard colonoscopy with the GI Genius (136 patients) or standard white light colonoscopy alone (127 patients). Colonoscopy plus the system was able to identify lab-confirmed adenomas or carcinomas in about 55% of patients compared to 42% of patients with standard colonoscopy, a difference of 13%. Use of the device led to more biopsies, but no additional adverse events were reported; however, there was a slight increase in the number of lesions biopsied that were not adenomas.

The system is not intended to characterize or classify a lesion or to replace lab sampling as a means of diagnosis, the FDA said. It only identifies regions of the colon within the endoscope's field of view where a colorectal polyp might be located, allowing for a more extended examination during colonoscopy. It is up to the clinician to decide whether the identified region actually contains a suspected lesion and how the lesion should be managed, the FDA said.