FindTrial
Sign In

Deep learning-based automated segmentation and identification of cervical lesions by multimodal technique

Deep learning-based automated segmentation and identification of cervical lesions by multimodal technique

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2200058478
Enrollment
Unknown
Registered
2022-04-09
Start date
2022-04-11
Completion date
Unknown
Last updated
2024-01-08

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

Conditions

Cervical intraepithelial lesions

Interventions

Gold Standard:Pathological diagnosis
Index test:Automated visual evaluation system

Sponsors

The First Amliated Hospital of the Air Force Medical University
Lead Sponsor

Eligibility

Sex/Gender
Female
Age
18 Years to 80 Years

Inclusion criteria

Inclusion criteria: Previous participation in cervical screening with complete information case. Information included: age, cervical cytology, HPV, cervical photographs, pathology results, etc.

Exclusion criteria

Exclusion criteria: 1. Incomplete clinical data; 2. No biopsy after colposcopy; 3. Poor colposcopic image quality (blurry, overexposure, cervical adhesions, leucorrhea or bleeding covering the cervix).

Design outcomes

Primary

MeasureTime frame
accuracy;dice index;—

Countries

China

Contacts

Public ContactYang Hong

Department of Obstetrics and Gynecology, Xijing Hospital of Fourth Military Medical University

lijia219@yeah.net+86 18821729828

Outcome results

None listed

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