# AI polyp detection in colonoscopy

Source: https://onco.cc/technologies/ai-endoscopy-detection/  
OnCo record `ai-endoscopy-detection` (Technology). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Real-time software that highlights polyps on the colonoscopy screen, helping doctors find more of the growths that could become bowel cancer.

## Summary

Computer-aided detection systems such as GI Genius (Medtronic, FDA authorised 2021) analyse the live video during colonoscopy and draw a box around suspected polyps. Randomised trials show higher adenoma detection rates, mainly of small lesions, while the effect on interval cancer remains to be shown; computer-aided characterisation aims to tell benign from precancerous polyps to avoid unnecessary removal.

## Fields

- Kind: Technology
- Status: approved
- Last checked: 2026-09-04
- Principle: A neural network runs on each video frame and marks regions whose appearance matches polyps in training data, with adjustable sensitivity.
- Since: 2021
- Strengths: Higher adenoma detection in randomised trials; Works with existing scopes; Reduces miss rates between endoscopists
- Limitations: More small polyps found, more resections and pathology; Unproven effect on cancer incidence and mortality; False alarms slow procedures

## Sources

- Wikipedia: https://en.wikipedia.org/wiki/Colonoscopy
- Wikipedia: https://en.wikipedia.org/wiki/Colonoscopy

## Connected records

- cancers: [Colorectal cancer](https://onco.cc/cancers/colorectal/)
- fronts: [AI & Computation](https://onco.cc/fronts/ai-computation/), [Early Detection & Screening](https://onco.cc/fronts/early-detection/)
- technologies: [Colorectal cancer screening (colonoscopy, FIT, stool DNA, blood)](https://onco.cc/technologies/colorectal-screening/)

---
JSON: https://onco.cc/api/v1/entities/ai-endoscopy-detection.json