Post written by Xia Xie, MD, PhD, and Shi-Ming Yang, MD, PhD, from the Department of Gastroenterology, The Second Affiliated Hospital, The Third Military Medical University, Chongqing, China.

This research primarily focuses on analysis of artificial intelligence (AI)’s capacity for recognizing lesions in the stomach and small intestine as well as its potential to augment the diagnostic proficiency of endoscopists.

Currently, the AI system used in capsule endoscopy (CE) centers on isolated segments of the digestive tract, such as the small intestine or stomach, and exhibits lack of comprehensive recognition capabilities for GI lesions.

Previous research has predominantly examined the diagnostic capabilities of AI in isolating diseases within individual segments of the digestive tract, with limited investigations concentrating on AI-based diagnosis in CE for gastric diseases. This study aims to emphasize the diagnostic value of AI in the context of continuous digestive tract diseases and further evaluates the impact of AI assistance on the diagnostic proficiency of endoscopists.

Our findings reveal that the newly developed convolutional neural network—based algorithm, SS Plus, demonstrates the ability to detect GI lesions and enhances diagnostic accuracy of junior endoscopists in interpreting CE videos.

Looking ahead, AI in CE is anticipated to achieve broader lesion recognition across multiple digestive tract organs, including the esophagus, stomach, small intestine, and colorectum, while expanding the scope of lesion types it can identify.

Graphical abstract

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.