Dataset Overview

Definition:Cholangiopancreatoscopy Endoscopy Video Datasetis provided byChangsha Langhui Information Technology Co., Ltd.The large-scale Cyclops Cyclops check video-image database, built by Long Salang Langhui Information Technology Ltd., is built. It records the entire process of screening the Cyclops under ERCP, maintains the equipment to produce original and complete video and key maps, supports multi-manufacturing equipment data such as Olympus and Boston Scientific, and supports the narrow necrotyty stylist, quartz/tumour/inflammation markers and pathology confirmation.

Dataset NameCholangiopancreatoscopy Endoscopy Video Dataset
Total Data VolumeTotal Endoscopy Volume Included: 1,000,000 Cases
Imaging ModalityEndoscopy Video (POCS / SpyScope, etc.)
Covered Body PartsCourage main tube/pental choreography/insulin/bourbon
Raw DataOriginal equipment export complete inspection video and key original maps to support multi-producer equipment
MultiproducerOlympus CHF-B260/B290 and Boston Scientific SpyScope DS/DS II, etc.
Dedicated FieldsCyclops/long, surface form, vascular texture, stones/tumours/inflammations, biopsy, pathology
Pathology CorrelationPriority for cholesterol examination pathology, ERCP cellology, EUS and follow-up
Source InstitutionCooperative MNA Hospital digestive internal/hepatococal surgery
Use CasesDiagnosis of cholesterol cancer, narrow necrosis of the cholesterol, automatic detection of stones, ERCP navigation

Delivery Specifications and Field Requirements

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

Delivery & Counting:One full pancreatic examination in one line; one multi-series/multi-view case only

Coverage:Completely records the entire cholangiopancreatoscopy procedure under ERCP, including the common bile duct / intrahepatic bile duct / pancreatic duct / ampulla

Cross-producer:Support multi-producer equipment data, labelling inter-equipment consistency

Positives and Composition:Identify malignant pathologies as the subject; narrow benignness, inflammation and uncertain cases are retained, respectively

Cross-Data Association:Must relate to official ERCP reports; prioritize choreology of choreology, ERCP cytology, EUS

2026 Frontier AI Research Progress

Domain Review:In 2025, Caucocal Insulin mirror AI made breakthroughs in cross-manufactor ViT structure and multi-centre validation, and AI identified malignancies as continuing to be better than standard ERCP sampling, but still in the early clinical validation phase.

Cross-producer ViT Cholesterol A.

Digestive Endoscopy, 2025

The POCS AI system based on the ViT structure achieves cross-producer consistency between the Olympus and Boston Scientific devices, which have superior diagnostic capabilities to CNN.

Insulin mirror ACV

PubMed, 2025

The multi-centre validation of the existing CVI system showed that it continued to outperform the standard ERCP sampling method in the identification of malignant pathogenesis.

AIG-DVC overview and Meta analysis

Houston Methodist Scholars

Systematic reviews and meta-analyses show that AI-assisted cholangioscopy diagnosis has diagnostic value for indeterminate and malignant biliary strictures。

A. Overview of the effects of AI on pancreas endoscopy

2025

AI has been used in EUS for cystaltic disease detection and pancreatic edema identification, but the application of choreal and cholesterol cancer AI is still at an early stage.

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-CHOLANGIO
Total Data Volume1 Million Cases
Imaging ModalityEndoscopy Video (POCS / SpyScope, etc.)
Source InstitutionPartner Grade-A Tertiary Hospitals
Quality Control StandardsKappa ≥ 0.75
Compliance & LicensingEnd-to-End Compliance

AI Frontier Research

In 2025, Caucocal Insulin mirror AI made breakthroughs in cross-manufactor ViT structure and multi-centre validation, and AI identified malignancies as continuing to be better than standard ERCP sampling, but still in the early clinical validation phase.

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