Dataset Overview

Definition:Colposcopy and Cervicoscopy Endoscopy Video Datasetis provided byChangsha Langhui Information Technology Co., Ltd.The large-scale vulcanography survey image a database, constructed by Long Salang Langhui Information Technology, Ltd., is designed to record the full time series of time series images following the cervical and vaginal sectional acetic anhydride test, to retain the equipment to export the original full inspection video and key original maps, along with CIN grade (LSIL/HSIL), the beaurate region label, the results of the iodine test and HPV detection correlation data.

Dataset NameColposcopy and Cervicoscopy Endoscopy Video Dataset
Total Data VolumeTotal Endoscopy Volume Included: 1,000,000 Cases
Imaging ModalityEndoscopy Video (White Light / Aceto-White Time Series / Iodine Test)
Covered Body PartsCervical/vaginal/extravain/alphagus week
Raw DataComplete examination videos and key original images exported directly from the equipment
Dedicated FieldsDiverse acrylic acid changes (time series multiple frames), iodine test results, pathological region/size/boundary, CIN classification (LSIL/HSIL), HPV type
Multi-equipmentSupport multi-equipment type acquisition, cross-equipment generic labels
Pathology CorrelationPriority is given to cervical screening pathology, HPV testing, cytology and follow-up
Source InstitutionCo-operation with MCA Hospital Gynaecology and Obstetrics/ Cervical Clinic
Use CasesCervical cancer AI screening, CIN automatic classification, white acetic acid region partition, HPV positive diversion

Delivery Specifications and Field Requirements

The data set strictly follows the ENDO-COLPO uniform delivery index requirements to ensure data quality and traceability.

Delivery & Counting:One full vaginal lens check per row; one multi-series/multi-view only

Coverage:Complete time-series multiple images of the cervix and vaginal sectional acetic acid test (60/90/1500.180 seconds)

Positives and Composition:CIN I/II/III and leaching cancer stratification; suspected, not except for pathological diagnosis

Time series notation:Aceto-white changes are annotated as a time series, supporting the training of temporal attention models

Cross-Data Association:Must relate to official vaginal lens reports; priority to be given to cervical pathology, HPV testing, cytology

2026 Frontier AI Research Progress

Domain Review:In 2025-2026, vaginal mirror AI made progress in time series multi-frame integration (TLS-Net, Scientific Reports 2026) and multi-equipment extension, with Smart Spope AI being 93.46 per cent specific as a POC screening tool.

TLS-Net time series vaginal lense partition

Scientific Reports, 2026

Using the Swin Transformer encoder and time-series attention module, the integration of 60/90/1500.180 seconds of white acetate images is achieved to achieve a precise partition of the cervical-crystals stove area.

Automatic multi-equipment vaginal/alcoscope pre-cancer cancer detection

2025

320 tests (3 equipment types), CNN classified lower (LSIL) and higher (HSIL) gill-like internal pathologies.

Smart Spope AI POC Screening Scrutinization

Cureus, 2024

Smart Spope AI 93.46%, AUC 0.73 (95% CI: 0.60-0.86), Sensitivity 52.17% as a prompt screening diversion tool.

U-NET++ and RepVGG Early detection of cervical cancer

Frontiers in Oncology, 2025

The model, with a forecast accuracy rate of 83.01 per cent in 424 cases, has a better ability to identify early CIN I and CIN II pathologies.

Annotation Workflow & Quality Control

1

Image Acquisition & De-identification

Standardized acquisition workflow: complete data is exported directly from the equipment, and patient identifying information (PHI) is removed before the data is stored。

2

Initial Annotation (Specialist Physician)

Attending physicians annotate case by case against the standards, including lesion localization, morphological description and disease term determination。

3

Review (Associate Chief Physician or Above)

Experts with the title of Associate Chief Physician or above review the initial annotation results item by item, correcting erroneous annotations and supplementing missing dimensions。

4

Consistency Assessment

10% of samples are randomly selected and independently annotated by 3 physicians to calculate Fleiss' Kappa; below 0.Dimensions scored 75 are flagged for rework。

License and Usage Agreement

Academic Research License

For universities and research institutions, supporting academic research related to medical AI。After signing the agreement, a de-identified data subset is provided; the source must be acknowledged:Langhui Technology DataAssetsAPI。

Commercial License

For medical device companies and AI diagnostics companies, supporting medical AI product R&D and medical device registration。Provides full datasets + custom annotation + incremental update services。

Data Compliance Statement

All images come from legally authorized sources; PHI fields are fully de-identified and contain no information that can directly identify an individual, in compliance with the Personal Information Protection Law and the Data Security Law。

Customized services

Supports extended requirements such as adding specific disease types, multimodal annotation expansion, and custom training of AI-assisted diagnostic models。

Quick Facts

Dataset CodeENDO-COLPO
Total Data Volume1 Million Cases
Imaging ModalityEndoscopy Video (White Light / Aceto-White Time Series / Iodine Test)
Source InstitutionPartner Grade-A Tertiary Hospitals
Quality Control StandardsKappa ≥ 0.75
Compliance & LicensingEnd-to-End Compliance

AI Frontier Research

In 2025-2026, vaginal mirror AI made progress in time series multi-frame integration (TLS-Net, Scientific Reports 2026) and multi-equipment extension, with Smart Spope AI being 93.46 per cent specific as a POC screening tool.

Latest 2025–2026 Papers
Nature / Nature Medicine-level Research
FDA / NMPA / CE Regulatory Updates