Intended Use

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.

Technology

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.

Performance

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.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    4/30/2021

    6 months
  • 2

    FDA Approval

    11/19/2021

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.