REAL-Colon: A dataset for developing real-world AI applications in colonoscopy

Carlo Biffi, Giulio Antonelli, Sebastian Bernhofer, Cesare Hassan, Daizen Hirata +4 more
3/4/2024
eess.IVcs.CV

No official code found. Best implementation: cosmoimd/real-colon-dataset (57 stars, last commit 2025-09-05). 1 more below.

Abstract

Detection and diagnosis of colon polyps are key to preventing colorectal cancer. Recent evidence suggests that AI-based computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems can enhance endoscopists' performance and boost colonoscopy effectiveness. However, most available public datasets primarily consist of still images or video clips, often at a down-sampled resolution, and do not accurately represent real-world colonoscopy procedures. We introduce the REAL-Colon (Real-world multi-center Endoscopy Annotated video Library) dataset: a compilation of 2.7M native video frames from sixty full-resolution, real-world colonoscopy recordings across multiple centers. The dataset contains 350k bounding-box annotations, each created under the supervision of expert gastroenterologists. Comprehensive patient clinical data, colonoscopy acquisition information, and polyp histopathological information are also included in each video. With its unprecedented size, quality, and heterogeneity, the REAL-Colon dataset is a unique resource for researchers and developers aiming to advance AI research in colonoscopy. Its openness and transparency facilitate rigorous and reproducible research, fostering the development and benchmarking of more accurate and reliable colonoscopy-related algorithms and models.

View on arXivView PDF

Code Implementations(2)

cosmoimd/real-colon-datasetCommunity100%

Helper function for working with the REAL-Colon Dataset

578Shell, PythonFeb 24, 20231 years ago
cosmoimd/DeepLearningExamplesCommunity100%

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

100C, C++Jun 19, 20231 years ago

Similar Papers

RRTS Dataset: A Benchmark Colonoscopy Dataset from Resource-Limited Settings for Computer-Aided Diagnosis Research

92% match2025

Colon-Bench: An Agentic Workflow for Scalable Dense Lesion Annotation in Full-Procedure Colonoscopy Videos

90% match2026

PolypDB: A Curated Multi-Center Dataset for Development of AI Algorithms in Colonoscopy

89% match1 repo332024

SegCol Challenge: Semantic Segmentation for Tools and Fold Edges in Colonoscopy data

89% match1 repo72024

Synthetic Data-Driven Multi-Architecture Framework for Automated Polyp Segmentation Through Integrated Detection and Mask Generation

88% match2025

COLON: The largest COlonoscopy LONg sequence public database

88% match2024

Cite this paper

@article{biffi2024realcolon,
  title  = {REAL-Colon: A dataset for developing real-world AI applications in colonoscopy},
  author = {Carlo Biffi and Giulio Antonelli and Sebastian Bernhofer and Cesare Hassan and Daizen Hirata and Mineo Iwatate and Andreas Maieron and Pietro Salvagnini and Andrea Cherubini},
  year   = {2024},
  eprint = {2403.02163},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.02163v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.02163.svg)](https://codeofpaper.com/paper/2403.02163)

Discussion