ARCADE: X-ray coronary angiography images for SYNTAX segment labeling and stenosis detection

Provider
Maxim Popov, Akmaral Amanturdieva et al.; mirrored by MedOtter
License
CC0-1.0 (source)
Size
8 files
Format
Parquet (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/MedOtter/ARCADE)
Access
Free and public. No account with the data provider is needed.
DOI
10.5281/zenodo.10390295
Category
Health & Biomedical
Source
https://doi.org/10.1038/s41597-023-02871-z

About this dataset

ARCADE (Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs) provides 3,000 grayscale 512x512 invasive X-ray coronary angiography (XCA) frames for two tasks. The syntax subset (1,500 images) labels coronary artery segments into 26 anatomical classes following the SYNTAX Score methodology; the stenosis subset (1,500 images) marks atherosclerotic stenotic lesions as an extra class on top of the segment labels. Each subset has 1,000 training, 200 validation and 300 test images, stored under syntax/ and stenosis/ with pixel-level masks (0 = background). About 600 MB (measured 2026-11-17). Use for coronary artery segmentation, vessel segment classification and stenosis detection. Mirrored on Hugging Face by MedOtter from the authors' release, with a card documenting provenance and any normalization. The authors' Zenodo record 10390295 is released under CC0 1.0; cite Popov et al., Dataset for Automatic Region-based Coronary Artery Disease Diagnostics Using X-Ray Angiography Images, Scientific Data 11, 20 (2024).

How to load this dataset in Python

from datasets import load_dataset
ds = load_dataset("MedOtter/ARCADE")
print(ds)

Data structure

File types in sampled files: Parquet

Files

Example file: stenosis/test-00000-of-00001.parquet

Analyze this dataset without downloading it

On Scigantic, ARCADE: X-ray coronary angiography images for SYNTAX segment labeling and stenosis detection opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Health & Biomedical datasets