Simultaneous detection and characterization of diminutive polyps with the use of AI

Mori_headshotPost written by Yuichi Mori, MD, PhD, from the Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Japan.

We present a novel computer-aided system that enables automated polyp detection followed by immediate polyp characterization in a real-time fashion using an endocytoscope, a colonoscope with a function of 520-fold endomicroscopy (CF-H290ECI; Olympus Corp., Tokyo, Japan).

Artificial intelligence for colonoscopy is an important and rapidly growing area of research; however, there has not yet been any report of technology capable of simultaneous polyp detection and characterization, which is the optimal situation for fully automated colonoscopic observation.

This kind of technology could be a game changer of colonoscopy practice; however, the efficacy and safety of this system should be thoroughly assessed in an international setting to assure its reliability and reproducibility. Supporting evidence of the presented software is still limited (Misawa, et al. Gastroenterology 2018; Mori et al. Ann Intern Med 2018).

Regarding the regulatory approval of the introduced software, the automated detection has not been approved, while the automated characterization was approved by PMDA (Pharmaceuticals and Medical Devices Agency), a Japanese regulatory body on December 6, 2018.

Read the full article online.

The information presented in Endoscopedia reflects the opinions of the authors and does not represent the position of the American Society for Gastrointestinal Endoscopy (ASGE). ASGE expressly disclaims any warranties or guarantees, expressed or implied, and is not liable for damages of any kind in connection with the material, information, or procedures set forth.

Leave a Comment

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s