Curated endoscopic retrograde cholangiopancreatography images dataset

2026-01-23

AI Summary

This study addresses the critical scarcity of public ERCP image datasets, which has significantly hindered the advancement of AI-driven diagnosis for biliopancreatic diseases. To bridge this gap, the authors present a high-quality, large-scale ERCP image dataset comprising 38,335 images from 1,602 patients, including 5,519 images meticulously reviewed and collaboratively annotated by multiple senior gastroenterologists. Rigorous manual curation and a multi-expert annotation protocol ensure the dataset’s accuracy and reliability, which are further validated through classification experiments demonstrating its effectiveness. As the first publicly available and authoritative benchmark resource for ERCP imagery, this dataset fills a crucial void in the field and establishes a foundational platform for future research in intelligent diagnosis of biliopancreatic disorders.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Computer Vision: Medical and Biological Imaging
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Endoscopic Retrograde Cholangiopancreatography (ERCP) is a key procedure in the diagnosis and treatment of biliary and pancreatic diseases. Artificial intelligence has been pointed as one solution to automatize diagnosis. However, public ERCP datasets are scarce, which limits the use of such approach. Therefore, this study aims to help fill this gap by providing a large and curated dataset. The collection is composed of 19.018 raw images and 19.317 processed from 1.602 patients. 5.519 images are labeled, which provides a ready to use dataset. All images were manually inspected and annotated by two gastroenterologist with more than 5 years of experience and reviewed by another gastroenterologist with more than 20 years of experience, all with more than 400 ERCP procedures annually. The utility and validity of the dataset is proven by a classification experiment. This collection aims to provide or contribute for a benchmark in automatic ERCP analysis and diagnosis of biliary and pancreatic diseases.

Problem

• ERCP
• dataset
• biliary diseases
• pancreatic diseases
• medical imaging

Innovation

• ERCP dataset
• curated medical images
• expert annotation
• biliary and pancreatic disease diagnosis
• AI benchmark