EndoScreener is a computer-assisted detection software that automatically identifies and highlights potential polyps during colonoscopy procedures. It processes the live video feed from the colonoscope and overlays blue boxes on suspected polyps, alerting the physician in real-time to improve polyp detection and assist clinical decision-making during colonoscopy in adults.
EndoScreener is intended as a stand-alone software for real-time automatic detection of polyps in colonoscopy video streams during the procedure, to be used by licensed endoscopists in adults with white light colonoscopy.
The device processes colonoscopy video streams in real-time using a customized deep learning AI model to detect colorectal polyps, outputting bounding boxes highlighting suspected polyps on the video image and optionally alerting physicians. It is similar in function to the predicate device GI Genius but uses distinct AI model customization.
The device's deep learning algorithm was validated on multiple datasets including 1,138 polyp patients with histological confirmation, showing expected sensitivity and specificity. Clinical performance was assessed in a multi-center randomized controlled trial with 223 patients, demonstrating significantly lower adenoma miss rates and higher adenomas per colonoscopy when using EndoScreener. The device caused no imaging degradation and minimal latency.
No predicate devices specified
Submission
4/30/2021
FDA Approval
11/19/2021
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.