Automatic Real-time Diagnosis of Gastric Mucosal Disease Using pCLE With Artificial Intelligence

NCT03784209 | Completed

• 1 other identifier: 2018SDU-QILU-12
• Study Type: observational
• Target: 951
• Locations: 1 country
• Sites: 1

Brief Summary

Probe-based confocal laser endomicroscopy (pCLE) is an endoscopic technique that enables real-time histological evaluation of gastric mucosal disease during ongoing endoscopy examination. However this requires much experience, which limits the application of pCLE. The investigators designed a computer-aided diagnosis program using deep neural network to make diagnosis automatically in pCLE examination and contrast its performance with endoscopists.

Conditions

Gastric Diseases; Artificial Intelligence; Confocal Laser Endomicroscopy

Outcome Measures

Primary Outcomes (1)

• The diagnosis efficiency of Artificial Intelligence

  The primary outcome is to test the diagnostic accuracy, sensitivity, specificity, PPV, NPV of the Artificial Intelligence for diagnosing gastric mucosal disease on real-time pCLE examination.

  24 months

Secondary Outcomes (1)

• Contrast the diagnosis efficiency of Artificial Intelligence with endoscopists

  24 months

Study Arms (1)

lesions observed by pCLE

pCLE is used to distinguish the suspected lesions detected by white light endoscopy.

Diagnostic Test: The diagnosis of Artificial Intelligence and endoscopist

Interventions

The diagnosis of Artificial Intelligence and endoscopist DIAGNOSTIC_TEST

When suspected lesion is observed using pCLE, endoscopist and AI will make a diagnosis independently. In addition, the endoscopist can not see the diagnosis of AI.

lesions observed by pCLE

Eligibility Criteria

• Age: 18 Years - 80 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Consecutive patients who receive the upper gastrointestinal tract pCLE examination and screened that fulfill the eligibility criteria at Qilu Hospital, Shandong University will be enrolled into the study

You may qualify if:

• aged between 18 and 80;
• agree to give written informed consent.

You may not qualify if:

• Patients under conditions unsuitable for performing CLE including coagulopathy , impaired renal or hepatic function, pregnancy or breastfeeding, and known allergy to fluorescein sodium;
• Inability to provide informed consent

Sponsors & Collaborators

• Shandong University: lead

Study Sites (1)

Endoscopic unit of Qilu Hospital Shandong University

Jinan, Shandong, 250001, China

Location

Related Publications (1)

• Liu G, Li G, Li Z, Shao X, Ji R, Ma T, Zhang Y, Su J, Qi Q, Guo J, He Y, Yang X, Li Y, Zuo X. Deep learning-aided optical biopsy achieves whole-chain diagnosis of Correa cascade of gastric cancer: a prospective study. BMC Med. 2025 Sep 30;23(1):527. doi: 10.1186/s12916-025-04310-9.

  PMID: 41029674 DERIVED

Biospecimen

Retention: SAMPLES WITH DNA

When a gastric mucosal lesion is found using white light endoscopy , endoscopist will observe this lesion using pCLE and then take biopsy for histology examination.

MeSH Terms

Conditions

Stomach Diseases

Condition Hierarchy (Ancestors)

Gastrointestinal Diseases; Digestive System Diseases

Study Officials

• Yanqing Li

  Qilu Hospital of Shandong University

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Vice president of QiLu Hospital

Study Record Dates

• First Submitted: December 16, 2018
• First Posted: December 21, 2018
• Study Start: July 1, 2018
• Primary Completion: September 29, 2021
• Study Completion: September 29, 2021
• Last Updated: April 1, 2022

Record last verified: 2022-03

Locations

CN (1)