Artificial intelligence and colorectal polyp detection
Editorial

Artificial intelligence and colorectal polyp detection

Brandon J. Teng1, Michael F. Byrne2

1Division of Gastroenterology, University of Washington, Seattle, WA, USA; 2Division of Gastroenterology, Vancouver General Hospital, University of British Columbia, Vancouver, British Columbia, Canada

Correspondence to: Brandon J. Teng, MD. Division of Gastroenterology, University of Washington, Seattle, WA, USA. Email: brandonteng@gmail.com.

Received: 03 September 2019; Accepted: 06 September 2019; Published: 23 September 2019.

doi: 10.21037/jmai.2019.09.04


Colorectal cancer (CRC) is the second leading cause of cancer death, and is a significant cause of morbidity and mortality. This is a growing topic discussed on public media networks due to the worldwide rise in CRC incidence among people under 50 years of age and recent American Cancer Society recommendations for earlier CRC screening. Colonoscopy remains the most effective method of detection and removal of neoplastic polyps. There is an expanding body of literature describing the imperfections of colonoscopy with regard to polyp detection, primarily due to missed lesions and subsequent interval development of CRC. This occurs even with ideal bowel preparation and adherence to national and societal based guidelines for surveillance exams. Higher adenoma detection rate (ADR) is associated with a decrease in interval CRC rate, thus much of the focus for improving clinical outcomes is centered on improving detection of neoplastic lesions during colonoscopy.

Artificial intelligence (AI) and computer aided detection (CAD) in colonoscopy is a rapidly evolving field, with much of the excitement surrounding technology with potential to be used efficiently in real-time for busy endoscopy practices to improve ADR. Possible improvements over standard white light endoscopy would include detecting missed lesions in the endoscopic field of view, identifying unexamined mucosal folds and alerting the endoscopist to areas not adequately visualized on withdrawal. Dr. Omer F. Ahmad of University College London, United Kingdom, is a gastroenterologist on the forefront of this exciting field, with expertise in the role of machine learning and convolutional neural networks for CAD with colonoscopy. He will discuss the current status of CAD in colonoscopy and polyp detection and explore the potential hurdles facing widespread clinical adoption in the future.


Acknowledgments

None.


Footnote

Conflicts of Interest: Michael F. Byrne is the CEO and Founder, Satisfai Health. He is also the founder of Ai4gi Joint Venture, which has a co-development agreement with Olympus America. The other author has no conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

doi: 10.21037/jmai.2019.09.04
Cite this article as: Teng BJ, Byrne MF. Artificial intelligence and colorectal polyp detection. J Med Artif Intell 2019;2:18.