Efficacy of CADe System in Detecting Gastric Neoplasia

Summary

Gastric cancer remains the 5th most common cancers worldwide. It also ranked 5th in the cancer related mortality, causing more than 650'000 deaths per year. Survival of gastric cancer is directly related to the stage of the presentation, with early stage cancers having a significantly better survival. Patients with stage I gastric cancer generally have a 5-year survival of more than 90%. In particular, T1a cancer confined to the mucosa are amenable for endoscopic resection, and patients who underwent such treatment have an excellent survival of 97.2% at 5 years. These patients are not only able to survive longer but also with good quality of life through organ preservation.

However, diagnosis of gastric cancer at an early stage has always been difficult. A meta-analysis of 22 studies from both East and Western population showed a gastric cancer miss rate of 9.4%. Early gastric cancer usually presents with subtle mucosal changes that are hard to detect endoscopically, especially for endoscopists with limited experience in early cancer diagnosis. Background chronic inflammation and high frequency of non-neoplastic lesions often pose significant diagnostic challenges for endoscopists to detect real neoplastic changes. In high incidence countries such as Japan and Korea, the combination of national screening programme as well as good endoscopy training program facilitated high proportion of early gastric cancer detection. Previous studies have showed that significant survival outcome difference between countries with high versus low early cancer detection rate.

Artificial intelligence has emerged as one of the promising technologies that helps enhance endoscopic performance. Numerous high quality randomized studies have demonstrated that computer assisted detection (CADe) system significantly improved colonic adenoma detection rate during screening colonoscopy. Development of gastric cancer CADe system has been much slower than colonic polyp detection. Despite the publication of numerous retrospective studies utilizing endoscopic images in differentiating benign versus malignant gastric lesions, there were only very few completed systems available for clinical real time application. A single centre randomized controlled trial from China demonstrated an improvement in the gastric neoplasm miss rate from 27.3% to 6.1 % when utilizing a novel CADe system.

A novel CADe prototype system (OIP-Ge1, Olympus Medical Corporations, Tokyo, Japan) has recently been developed. The system was developed through collaboration of multiple experts in diagnosing early gastric cancer, collecting more than 100'000 endoscopic images from dozens of high volume centres in Japan. There is currently no prospective clinical data on the actual performance of the prototype CADe system, especially when applied in regions with low proportion of early gastric cancer detection.

The purpose of this study is to investigate the clinical utility of the new CADe system in detection of gastric neoplasia among high risk patients.

If the current study confirms the significant difference in miss rate of gastric neoplasia with the CADe system, a multicentred international randomized controlled trial is planned to compare the efficacy of gastric neoplasia detection with or without the system.

Conditions

• Gastric Neoplasia

Interventions

DEVICE

CADe System

The endoscopy would be performed using standardized video processing system (EVIS-X1 CV-1500, Olympus Medical Corporations, Tokyo, Japan) and gastroscope (GIF-EZ1500, GIF-XZ1200). A soft black hood (MAJ-1989) would be attached to the distal end of the endoscope. The video processing system would be connected to the OIP-Ge1 (Olympus Medical Corporations, Tokyo, Japan), the novel CADe system, allowing simultaneous artificial intelligence assisted lesion detection, when turned on using conventional white light imaging (WLI).

Sponsors & Collaborators

• Chinese University of Hong Kong

  lead OTHER

Study Design

Allocation

NA

Purpose

TREATMENT

Masking

NONE

Model

SINGLE_GROUP

Eligibility

Min Age

18 Years

Sex

ALL

Healthy Volunteers

No

Timeline & Regulatory

Start

2025-12-01

Primary Completion

2028-01-31

Completion

2028-07-31

Countries

• Hong Kong

Study Locations