Related Experiment Video
Updated: Apr 9, 2026
08:05
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
Published on: June 10, 2025
1.4K
Artificial Intelligence and Its Role in Endoscopic Adenoma and Cancer Detection
Hannah R Phillips1, Wilfor J Diaz Fernandez1, Cadman L Leggett1
1Division of Gastroenterology and Hepatology, Mayo Clinic, Rochester, Minnesota, United States.
Clinics in Colon and Rectal Surgery
|April 8, 2026
Summary
Artificial intelligence (AI) in colonoscopy improves polyp detection and characterization. A combined AI approach (CADe, CADx, CAQ) shows promise for reducing postcolonoscopy colorectal cancer and enhancing patient outcomes.
Area of Science:
- Gastroenterology
- Medical Imaging
- Oncology
Background:
- Colorectal cancer (CRC) incidence and mortality have decreased due to screening colonoscopies.
- Postcolonoscopy colorectal cancer (PCCRC) remains a concern, occurring in up to 7% of cases and linked to examination quality.
- Artificial intelligence (AI) offers potential to enhance colonoscopy performance and patient outcomes.
Purpose of the Study:
- To review the role of AI in improving colonoscopy metrics.
- To evaluate the impact of computer-aided detection (CADe), characterization (CADx), and quality assessment (CAQ) systems.
- To discuss the potential of AI to reduce PCCRC and improve patient outcomes.
Main Methods:
- Review of randomized trials on AI-assisted colonoscopy.
- Analysis of computer-aided polyp detection (CADe) for adenoma detection, especially small lesions.
- Evaluation of computer-aided polyp characterization (CADx) for real-time optical diagnosis and management strategies.
- Assessment of computer-aided quality assessment (CAQ) systems for monitoring key colonoscopy metrics.
Main Results:
- Computer-aided polyp detection (CADe) significantly increases adenoma detection rates, particularly for diminutive polyps (≤5 mm).
- Computer-aided polyp characterization (CADx) facilitates real-time optical diagnosis, supporting strategies like resect-and-discard or diagnose-and-leave.
- Computer-aided quality assessment (CAQ) systems monitor crucial performance indicators like cecal intubation and withdrawal time.
Conclusions:
- While the impact of CADe alone on PCCRC reduction is undetermined, a combined AI approach (CADe, CADx, CAQ) is anticipated to yield the most significant improvements in patient outcomes.
- AI-assisted colonoscopy holds promise for enhancing diagnostic accuracy and procedural quality, potentially leading to better CRC prevention and management.
- Further research is needed to confirm the long-term benefits of AI in reducing PCCRC and cancer mortality.
