MOGaMBO: T2-weighted pelvic MRI of 94 cervical cancer brachytherapy patients with organ-at-risk contours

Provider
Suresh Das, Siladittya Manna, Sayantari Ghosh, Saumik Bhattacharya; mirrored by MedOtter
License
CC-BY-4.0 (source)
Size
191 files
Format
Parquet, NIfTI (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/MedOtter/MOGaMBO)
Access
Free and public. No account with the data provider is needed.
DOI
10.5281/zenodo.15156638
Category
Health & Biomedical
Source
https://arxiv.org/abs/2503.23507

About this dataset

MOGaMBO (Multi-Organ Gynaecological Magnetic Resonance Imaging for Brachytherapy-based Oncology) is a single-center collection of T2-weighted 3D MR scans from 94 patients with locally advanced cervical cancer (FIGO stage IB2 to IVA), imaged on a 1.5 T GE Signa Explorer for interstitial and intracavitary brachytherapy planning, with bladder volume standardized by Foley catheter. Expert radiation oncologists contoured four organs at risk in ITK-SNAP: urinary bladder, rectum, sigmoid colon and femoral heads, distributed as one multi-label mask per case (labels 1 to 4, 0 background). Volumes and masks are NIfTI under train/ with preview images in preview/; about 760 MB (measured 2026-11-21). Read with nibabel or SimpleITK, or use in MONAI and nnU-Net. Use for organ-at-risk segmentation in gynecologic radiotherapy, brachytherapy planning automation and pelvic MRI anatomy models. Mirrored by MedOtter from the authors' Zenodo record, CC BY 4.0, DOI 10.5281/zenodo.15156638; cite Manna et al. 2025 (arXiv 2503.23507).

How to load this dataset in Python

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

Data structure

File types in sampled files: Parquet, NIfTI

Files

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

Analyze this dataset without downloading it

On Scigantic, MOGaMBO: T2-weighted pelvic MRI of 94 cervical cancer brachytherapy patients with organ-at-risk contours 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