April 30, 2021
2 min read

Q&A: Endoscopy modules using AI enhances detection of colorectal polyps

You've successfully added to your alerts. You will receive an email when new content is published.

Click Here to Manage Email Alerts

We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com.

Medtronic recently received FDA de novo clearance for the GI Genius intelligence endoscopy module.

GI Genius is a computer-aided detection (CADe) system using artificial intelligence (AI) to identify colorectal polyps.

Endoscopy modules use artificial intelligence to better detect colorectal polyps. Source: Adobe Stock

Healio Gastroenterology spoke with Giovanni Di Napoli, president of the Gastrointestinal business part of the Medical Surgical Portfolio at Medtronic, about how the GI Genius will change patient care.

Healio: Can you describe how the GI Genius works?

Di Napoli: The GI Genius intelligent endoscopy module uses advanced AI to highlight the presence of precancerous lesions with a visual marker in real-time — serving as an ever vigilant second observer.

The module supplements procedures with real-time image analysis of any colonoscope video and alerts clinicians to the presence of lesions — including those with flat (non-polypoid) morphology — with a visual marker on-screen. This can increase diagnostic accuracy, improve efficacy rate of polyp detection, and reduce the risk for interval cancers that can occur between colonoscopies.

Healio: How will the GI Genius change patient care?

Di Napoli: The GI Genius intelligent endoscopy module — powered by deep AI learning algorithms with 99.7% sensitivity rate — enables clinicians to enhance their ability to detect precancerous lesions during colonoscopy procedures, including the detection of small flat polyps or sessile polyps that might go undetected. Detection of all colorectal polyps regardless of size, shape or morphology can lead to better clinical outcomes for patients. For example, the GI Genius model, as a second observer, has demonstrated a 30% relative increase in adenoma detection rate compared with colonoscopy alone for both flat (42% increase) and polyploid (36% increase) lesions, thus increasing accuracy and reducing the rise of interval cancers that can occur between colonoscopies.

Healio: How can GIs implement GI Genius in their practice?

Di Napoli: We know there are different types of facilities where colonoscopies are performed, and GIs have different needs. Therefore, we developed a platform that is highly flexible and can be integrated in the existing equipment of any facility. The GI Genius intelligent endoscopy module integrates easily and seamlessly with all major brands of endoscopes and has no impact on the current clinic workflow.

AI is a relatively new concept in gastroenterology. In practice, as the first and only commercially available CADe system using AI, GI Genius is transforming the gastroenterology field by introducing AI technology into colonoscopy procedures. We believe it will be well received because it will help with earlier polyp detection and treatment and reduce variability in patient outcomes.

Healio: What does the use of AI mean for CRC screenings?

Di Napoli: Adding AI can increase the quality of colonoscopies, which can improve diagnosis and outcomes for colon cancer patients. Because AI can perform tasks that normally require human intelligence, GI Genius provides clinicians with a reliable expert second observer to enhance the detection of polyps — of all shapes and sizes — as well as precancerous and potentially cancerous lesions in real time.

A recently released multicenter, randomized trial founded computer-aided polyp detection increases adenoma detection rates (ADR) compared with high-definition (HD) colonoscopy alone. The trial, using colonoscopies performed by expert endoscopists in three Italian centers, found that CADe and HD together delivered a:

14% absolute increase in ADR;

30% relative increase in ADR;

46% relative increase in adenomas per colonoscopy (APC);

50% greater likelihood to detect multiple polyps; and

53% greater likelihood to detect polyps in the distal colon.