FindTrial
Sign In

Deep learning-enabled Hill quantifying of esophagogastric junction using endoscopic images

Deep learning-enabled Hill quantifying of esophagogastric junction using endoscopic images

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2500115355
Enrollment
Unknown
Registered
2025-12-25
Start date
2025-12-31
Completion date
Unknown
Last updated
2026-01-05

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

Conditions

None listed

Interventions

Patients undergoing gastroscopy examination:NA

Sponsors

Hunan Provincial People's Hospital
Lead Sponsor

Eligibility

Sex/Gender
All

Inclusion criteria

Inclusion criteria: Complete and clear image of the gastroesophageal junction during gastroscopy with inverted endoscope.

Exclusion criteria

Exclusion criteria: 1. Postoperative cases and tumor invasion of the gastroesophageal junction; 2. The image failed to display the gastroesophageal junction; 3. Lack of depth or width images of esophageal hiatal hernia sac.

Design outcomes

Primary

MeasureTime frame
Morphology of the gastroesophageal junction;sensitivity;specificity;accuracy;AUC;—

Countries

China

Contacts

Public ContactQingqing Li

Hunan Provincial People's Hospital

7400984@qq.com+86 731 8476 2699

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026