Related Experiment Video
Updated: Jul 7, 2026
08:58
Artificial Intelligence Approaches to Assessing Primary Cilia
Published on: May 1, 2021
Evaluation of Artificial Intelligence: Computer-aided Detection of Colorectal Polyps
Yuya Hiratsuka1, Takashi Hisabe2, Kensei Ohtsu2
1Department of Endoscopy, Fukuoka University Chikushi Hospital, Chikushino, Japan.
Journal of the Anus, Rectum and Colon
|January 30, 2025
Summary
Artificial intelligence (AI) computer-aided detection (CADe) systems significantly reduced the adenoma miss rate (AMR) during colonoscopy. This AI tool shows promise in improving colorectal cancer screening by minimizing missed lesions.
Area of Science:
- Gastroenterology
- Medical Imaging
- Artificial Intelligence
Background:
- Colonoscopy is the primary method for detecting colorectal cancer and precancerous lesions.
- Advances in artificial intelligence (AI) have led to the development of computer-aided detection (CADe) systems for colonoscopy.
- The adenoma miss rate (AMR) remains a challenge in colonoscopy effectiveness.
Purpose of the Study:
- To evaluate the efficacy of the CAD-EYE AI system in reducing the AMR during colonoscopy.
- To compare the AMR between colonoscopies performed with and without AI assistance.
Main Methods:
- A randomized, open-label, single-center, tandem colonoscopy study was conducted.
- Patients were assigned to either a CADe group or a non-CADe group.
- Two different endoscopists performed tandem colonoscopies, with the second endoscopist identifying missed lesions.
Main Results:
- The study included 48 patients in the CADe group and 46 in the non-CADe group.
- The AMR was significantly lower in the CADe group (17.4%) compared to the non-CADe group (30.3%) (P=0.009).
Conclusions:
- The use of CAD-EYE AI in colonoscopy effectively reduced the adenoma miss rate.
- AI-assisted colonoscopy, specifically with CAD-EYE, shows potential for improving the detection of colorectal adenomas.
