Related Experiment Video
Updated: Oct 27, 2025
Intraoperative Gastroscopy for Tumor Localization in Laparoscopic Surgery for Gastric Adenocarcinoma
Published on: August 9, 2016
Effect of a deep learning-based system on the miss rate of gastric neoplasms during upper gastrointestinal endoscopy:
Lianlian Wu1, Renduo Shang1, Prateek Sharma2
1Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China; Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China; Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China.
Background:
White light endoscopy is a pivotal first-line tool for the detection of gastric neoplasms. However, gastric neoplasms can be missed during upper gastrointestinal endoscopy due to the subtle nature of these lesions and varying skill among endoscopists. Here, we aimed to evaluate the effect of an artificial intelligence (AI) system designed to detect focal lesions and diagnose gastric neoplasms on reducing the miss rate of gastric neoplasms in clinical practice.
Methods:
This single-centre, randomised controlled, tandem trial was done at Renmin Hospital of Wuhan University, China. We recruited consecutive patients (≥18 years old) undergoing routine upper gastrointestinal endoscopy for screening, surveillance, or investigation of symptoms. Same-day tandem upper gastrointestinal endoscopy was done where patients first underwent either AI-assisted (AI-first) or routine (routine-first) white light endoscopy, followed immediately by the other procedure, with targeted biopsies for all detected lesions taken at the end of the second examination. Patients were randomly assigned (1:1) to the AI-first or routine-first group using a computer-generated random numerical series and block randomisation (block size of four). Endoscopists were not blinded to randomisation status, whereas patients and pathologists were. The primary endpoint was the miss rate of gastric neoplasms and the analysis was done per protocol. This trial is registered with the Chinese Clinical Trial Registry, ChiCTR2000034453, and has been completed.
Findings:
Between July 6, 2020, and Dec 11, 2020, 907 patients were randomly assigned to the AI-first group and 905 to the routine-first group. The gastric neoplasm miss rate was significantly lower in the AI-first group than in the routine-first group (6·1%, 95% CI 1·6-17·9 [3/49] vs 27·3%, 15·5-43·0 [12/44]; relative risk 0·224, 95% CI 0·068-0·744; p=0·015). The only reported adverse event was bleeding from a target lesion after biopsy.
Interpretation:
The use of an AI system during upper gastrointestinal endoscopy significantly reduced the gastric neoplasm miss rate. AI-assisted endoscopy has the potential to improve the yield of gastric neoplasms by endoscopists.
Funding:
The Project of Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision and the Hubei Province Major Science and Technology Innovation Project.
