Skip to content

Medical Segmentation Decathlon, Task01 BrainTumour

pl.load("msd_task01_braintumour") loads this dataset. Brain tumour (BraTS 2016/17 subset): 484 + 266 multimodal MRIs with four channels per file (FLAIR, T1w, T1gd, T2w) - a 4-D NIfTI. Read case by case out of the official MSD tar on S3 (HTTP Range: one 512-byte header per member to index, each volume its own size). ds.filter(split='Tr') keeps the labelled cases; the test split has images only.

import pardesline as pl

ds = pl.load("msd_task01_braintumour")
print(ds.describe())  # roles, frames, units, labels, licence, citation
s = ds[0]
obj = s.mri  # fetched now, cached under ~/.cache/pardesline/datasets/msd_task01_braintumour

Provenance and licence
Source remote archive read by HTTP Range: https://msd-for-monai.s3-us-west-2.amazonaws.com/Task01_BrainTumour.tar
Scheme archive
Size of the whole source 7.4 GB
Licence CC-BY-SA-4.0
Commercial use allowed by the licence
Redistribution allowed
Licence note CC-BY-SA 4.0 as stated in the archive's dataset.json (checked 2026-10-14); share-alike applies to derived data.
Terms http://medicaldecathlon.com/
Homepage http://medicaldecathlon.com/
Cite Antonelli M., Reinke A., Bakas S., et al. The Medical Segmentation Decathlon. Nat Commun 13:4128, 2022. Simpson A.L. et al. A large annotated medical image dataset for the development and evaluation of segmentation algorithms. arXiv:1902.09063, 2019.
Samples grouped by id

Roles (what each sample contains)

Role Type Frame Units Labels / layout Pattern or file
mri volume (MR) from the file header from the file header Task01_BrainTumour/images{split}/{id}.nii.gz
MR image (NIfTI, LPS mm from the header); split Tr = labelled, Ts = test
mask labels from the file header from the file header 1=edema, 2=non_enhancing_tumor, 3=enhancing_tumor Task01_BrainTumour/labelsTr/{id}.nii.gz
Label map (training cases only)

Standardized layout

Files are fetched on first access into the dataset cache and stay in their original format; ds.export(folder) writes every sample as standard files (PLY for points and meshes, MetaImage for volumes and label maps) with a .pardesline.json sidecar carrying frame, units, labels, licence and provenance, plus a manifest for the folder. Label maps become exact surfaces with to_mesh(label=k), DICOM series become one volume, raw arrays are decoded through the layout above.

ds = pl.load("msd_task01_braintumour").take(2)
ds.export("./standardized")        # PLY / MetaImage + sidecars + manifest.json

Algorithms and models that run on it

Generated from src/pardesline/data/manifests/msd_task01_braintumour.json on 2026-10-14.