Skip to content

IXI: ~600 healthy-subject brain MRIs (T1, T2, PD, MRA) from three London hospitals

pl.load("ixi_brain_mri") loads this dataset. The Information eXtraction from Images dataset: T1, T2, PD-weighted and MR angiography volumes of nearly 600 healthy subjects acquired at Guy's, Hammersmith and the Institute of Psychiatry (1.5 T and 3 T). One tar per modality on the Imperial College server, read subject by subject with HTTP Range (indexing a tar walks its ~580 headers once, a few minutes). Subject ids such as IXI002-Guys-0828 join the modalities into one sample. Demographics are in IXI.xls on the website.

import pardesline as pl

ds = pl.load("ixi_brain_mri")
print(ds.describe())  # roles, frames, units, labels, licence, citation
s = ds[0]
obj = s.t1  # fetched now, cached under ~/.cache/pardesline/datasets/ixi_brain_mri

Provenance and licence
Source remote archive read by HTTP Range: http://biomedic.doc.ic.ac.uk/brain-development/downloads/IXI/IXI-T1.tar, http://biomedic.doc.ic.ac.uk/brain-development/downloads/IXI/IXI-T2.tar, http://biomedic.doc.ic.ac.uk/brain-development/downloads/IXI/IXI-PD.tar, http://biomedic.doc.ic.ac.uk/brain-development/downloads/IXI/IXI-MRA.tar
Scheme archive
Size of the whole source 24.6 GB
Licence CC-BY-SA-3.0
Commercial use allowed by the licence
Redistribution allowed
Licence note Creative Commons CC BY-SA 3.0 as stated on the IXI website (checked 2026-10-14).
Terms https://brain-development.org/ixi-dataset/
Homepage https://brain-development.org/ixi-dataset/
Cite IXI dataset, brain-development.org (Imperial College London, Biomedical Image Analysis Group), EPSRC GR/S21533/02.
Samples grouped by id

Roles (what each sample contains)

Role Type Frame Units Labels / layout Pattern or file
t1 volume (MR) from the file header from the file header {id}-T1.nii.gz
T1-weighted
t2 volume (MR) from the file header from the file header {id}-T2.nii.gz
T2-weighted
pd volume (MR) from the file header from the file header {id}-PD.nii.gz
Proton density
mra volume (MR) from the file header from the file header {id}-MRA.nii.gz
MR angiography

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("ixi_brain_mri").take(2)
ds.export("./standardized")        # PLY / MetaImage + sidecars + manifest.json

Algorithms and models that run on it

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