Magnetic Resonance Enterography (MRE) of 114 inflammatory bowel disease (IBD) patients with 10 intestinal segment masks

Provider
Zhong Z., Huang B. et al.; mirrored by MedOtter
License
CC-BY-4.0 (source)
Size
232 files
Format
NIfTI, Parquet (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/MedOtter/IBD)
Access
Free and public. No account with the data provider is needed.
DOI
10.5281/zenodo.13839321
Category
Health & Biomedical
Source
https://doi.org/10.1038/s41597-025-04760-z

About this dataset

Magnetic resonance enterography (MRE), an MRI exam of the small and large bowel, from 114 patients with inflammatory bowel disease (IBD, including Crohn's disease), with pixel-level segmentation of ten gastrointestinal segments: stomach, duodenum, small intestine, appendix, cecum, ascending colon, transverse colon, descending colon, sigmoid colon and rectum. Images are coronal T2-weighted HASTE sequences, with 3,195 annotated coronal slices in total. The repository is a flat folder with one {id}_data.nii.gz volume and one {id}_label.nii.gz label map per patient, plus preview images; about 460 MB (measured 2026-11-21). There is no official train/test split. Read with nibabel or SimpleITK, or load into MONAI or nnU-Net pipelines. Use for bowel and intestinal segment segmentation, automated localization of IBD lesions along the gut and abdominal MRI anatomy models. Mirrored by MedOtter from the authors' Zenodo record, released under CC BY 4.0 with DOI 10.5281/zenodo.13839321; cite Zhong et al., Scientific Data 2025 (doi 10.1038/s41597-025-04760-z).

How to load this dataset in Python

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

Data structure

File types in sampled files: NIfTI, Parquet

Files

Example file: preview/train-00000-of-00001.parquet

Analyze this dataset without downloading it

On Scigantic, Magnetic Resonance Enterography (MRE) of 114 inflammatory bowel disease (IBD) patients with 10 intestinal segment masks 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