ERCPMP-Gx: A Multimodal Endoscopic, Histopathological, and Genomic Dataset for Hereditary Colorectal Polyposis

Forum topic · 小凯 · 2026-09-19

Summary

ERCPMP-Gx is a publicly available endoscopic, histopathological, and genomic dataset designed to support AI research on the recognition, characterization, and classification of hereditary colorectal polyposis syndromes. Most examinations were performed with the Olympus EVIS X1 system using white light endoscopy (WLE), narrow-band imaging (NBI), magnifying NBI (M-NBI), and NBI near-focus modes, yielding 160 images with accompanying video clips. Approximately 80% of cases are clinically and/or genetically confirmed hereditary polyposis syndromes, including familial adenomatous polyposis (FAP), Peutz-Jeghers syndrome (PJS), juvenile polyposis syndrome (JPS), and ganglioneuromatosis syndrome (GNS); the remaining 20% are non-hereditary polyps and phenotypic mimics for differential classification. Each record links standardized endoscopic annotations, representative histopathology, and germline findings at the patient level, forming an AI-ready multimodal resource. The dataset is available on Mendeley (https://doi.org/10.17632/nzyfc544bx.2), with updates at https://databiox.com. The paper (arXiv:2609.20815) is by Ghaffari et al. in the computer vision field.

Paper Overview

Field: Computer Vision (CV)
Authors: Zahra Ghaffari, Massih Bahar, Mojgan Forootan, Ali Darvishi, Hamidreza Bolhasani
Published: 2026-09-17
arXiv: 2609.20815

Abstract

Hereditary polyposis syndromes can be precursor lesions to colorectal cancer and are associated with a broad spectrum of extracolonic tumors. Early identification and accurate classification of these syndromes are essential for timely diagnosis, individualized patient management, and targeted surveillance strategies for affected families. However, public endoscopic datasets are largely organized around the individual sporadic polyp, and none links the polyposis phenotype to histopathology and germline findings at the patient level.

Key Features of ERCPMP-Gx

Purpose: A multimodal endoscopic, histopathological, and genomic dataset supporting AI applications in the recognition, characterization, and classification of colorectal polyposis.
Imaging: Most procedures were performed with the Olympus EVIS X1 system, including white light endoscopy (WLE), narrow-band imaging (NBI), magnifying NBI (M-NBI), and NBI near-focus modes, producing 160 images with accompanying video clips.
Case composition:
~80% clinically and/or genetically confirmed hereditary polyposis syndromes (PG), including familial adenomatous polyposis (FAP), Peutz-Jeghers syndrome (PJS), juvenile polyposis syndrome (JPS), and ganglioneuromatosis syndrome (GNS)
~20% non-hereditary polyps and polyp-mimicking lesions with overlapping morphology (Non-PG) for differential classification
Patient-level annotations: Each released record links standardized endoscopic annotations, representative histopathology, and clinically reported germline findings where available, forming an AI-ready labeling framework.

Availability

Dataset: publicly available on Mendeley Data — https://doi.org/10.17632/nzyfc544bx.2
Latest updates and more information: https://databiox.com