Automatic Diagnosis of Early Esophageal Squamous Neoplasia Using pCLE With AI

Automatic Diagnosis of Early Esophageal Squamous Neoplasia Using Probe-based Confocal Laser Endomicroscopy With Artificial Intelligence

Status

Completed

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT04136236

Enrollment

Registered

2019-10-23

Start date

2019-08-01

Completion date

2023-01-31

Last updated

2024-11-19

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Artificial Intelligence, Confocal Laser Endomicroscopy, Esophageal Neoplasms

Brief summary

Detection and differentiation of esophageal squamous neoplasia (ESN) are of value in improving patient outcomes. Probe-based confocal laser endomicroscopy (pCLE) can diagnose ESN accurately.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.

Interventions

DIAGNOSTIC_TESTThe diagnosis of Artificial Intelligence and endoscopist

Suspected esophageal mucosal lesion is observed using pCLE, endoscopist and AI will make a diagnosis independently. In addition, the endoscopist can not see the diagnosis of AI. After a washout period, nonexpert endoscopists take the second assessment with AI assistance.

Study design

Observational model

COHORT

Time perspective

OTHER

Eligibility

Sex/Gender

ALL

Age

18 Years to 80 Years

Healthy volunteers

Inclusion criteria

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

Exclusion criteria

* advanced esophageal squamous cell carcinoma or esophageal stenosis; * having no suspicious lesion of ESN found by WLE and IEE * known allergy to fluorescein sodium; * having coagulopathy or impaired renal function; * being pregnant or breastfeeding.

Design outcomes

Primary

Measure	Time frame	Description
The diagnosis efficiency of Artificial Intelligence	3 years	The primary outcome is to test the diagnostic accuracy, sensitivity, specificity, PPV, NPV of the Artificial Intelligence for diagnosing esophageal mucosal disease on real-time pCLE examination.

Secondary

Measure	Time frame	Description
Contrast the diagnosis efficiency of Artificial Intelligence with endoscopists	1 month	The secondary outcome is to compare the diagnosis efficiency (including diagnostic accuracy, sensitivity, specificity, PPV, NPV for diagnosing esophageal mucosal disease on real-time pCLE examination) between Artificial Intelligence and endoscopists.

Countries

China

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026