Editor’s Choice: Deep learning algorithm detection of Barrett’s neoplasia with high accuracy during live endoscopic procedures

Adler_headshot GIE Senior Associate Editor, Dr. Douglas G. Adler MD, FACG, AGAF, FASGE, highlights this article from the June issue “Deep learning algorithm detection of Barrett’s neoplasia with high accuracy during live endoscopic procedures” by Albert J. de Groof, MD, et al. 

Computer aided detection (CAD) is undergoing rapid development. It seems likely that, in the near future, machines can and will be helping us during endoscopy in several contexts including polyp detection, evaluation of Barrett’s esophagus, and other indications.

This article demonstrates that computers can look at images of Barrett’s esophagus and provide valuable information about neoplastic change in real time. This and other related technologies will likely only improve with time. In Stanley Kubrick’s 1968 film “2001: A Space Odyssey,” the computer HAL 9000 was portrayed as malevolent, although in endoscopy it seems likely that computers will play a much more benevolent role.


Figure 1. Visualization of the graphic user interface of the computer-aided detection (CAD) system, providing real-time feedback to the endoscopist. In the 2 nondysplastic Barrett’s esophagus images (top), the CAD system did not detect any abnormalities, resulting in low classification scores. In the 2 neoplastic images (bottom), the CAD system detected a lesion, resulting in high classification scores and corresponding visualization of the delineation and preferred biopsy sampling location.

Read the article abstract here.

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:

WordPress.com Logo

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

Facebook photo

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

Connecting to %s