GI Genius is an AI-powered software and hardware system that helps doctors detect precancerous lesions like polyps in the colon during colonoscopy procedures in real-time. It enhances standard white-light endoscopy video by highlighting suspected lesions with superimposed green boxes, improving detection rates and potentially reducing colorectal cancer risk.
Intended Use
The GI Genius System is a computer-assisted reading tool designed to aid endoscopists in detecting colonic mucosal lesions (such as polyps and adenomas) in real time during standard white-light endoscopy examinations of patients undergoing screening and surveillance endoscopic mucosal evaluations.
Technology
The device operates by acquiring the Serial Digital Interface (SDI) video output from endoscope processors, processing it with a modular AI software system implementing a convolutional neural network for lesion detection, and overlaying detection markers on the live video stream which is then output to the display in real time. It is designed to function with standard white-light endoscopy video and includes hardware compatible with multiple endoscopy systems.
Performance
Performance was validated extensively with standalone algorithm testing on a curated dataset of 150 colonoscopy videos with histologically confirmed lesions, achieving lesion-based sensitivity of approximately 82% at activation time faster than expert endoscopists and frame-level false positive rate around 1.4-2%. Clinical testing in a randomized, multicenter, prospective trial (NCT04079478) with 263 low CRC risk patients demonstrated statistically significant improvement in adenoma detection rate (55.1% vs 42.0%) and adenomas per colonoscopy with non-inferior positive percent agreement, without additional adverse events or workflow disruption.
Device Timeline
- 1
Submission
9/8/2020
7 months - 2
FDA Approval
4/9/2021
Other devices from Cosmo Artificial Intelligence - AI, LTD
Ready to Sharpen Your Edge?
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.