Creative Commons Attribution 4.0 International
Use, share and adapt the data for any purpose, including commercial use, as long as you credit the creators.
Our reading of the license, not legal advice. Before you use the data, read the original license and confirm that your use is allowed. We take no responsibility for how you use a dataset. Full disclaimer
What you can do
- Yes
- Yes
- Yes
- Yes
What you can share
- Yes
- Yes
- Yes
What you must do
- Yes
- Share alike No
- No
- No
- Manuscript review No
- Release code No
- Return results No
- Delete after use No
Limits
- No
- Location limits No
Datasets under this license
- BraTS 2021 (TCIA copy (DOI 10.7937/jc8x-9874): training and validation data of both tasks, 1,480 subjects, NIfTI and DICOM, plus the BraTS-to-TCIA ID crosswalk.)
Pre-operative multi-parametric brain MRI (T1, contrast-enhanced T1, T2, FLAIR) of 2,040 adult glioma patients from many institutions, with expert-approved tumor sub-region segmentations and MGMT promoter methylation labels.
- ISLES 2022
Acute to subacute ischemic stroke MRI (FLAIR, DWI and ADC) with expert infarct masks from Munich, Bern and Hamburg: 400 cases for the ISLES 2022 challenge, of which the 250 training cases are on Zenodo under CC BY 4.0.
- LINCHPIN CT and pathology set (CT ratings, APOE genotype, neuropathology ratings and analysis code on Edinburgh DataShare)
Admission non-contrast head CT of 110 adults with first-ever intracerebral haemorrhage in Lothian, Scotland, who died and had a research autopsy, with masked CT ratings, APOE genotype and CAA grading. The ratings are open; the CT images are not shared.
- OpenMind
113,921 3D head and brain volumes (all MRI except 653 PET) from 800 OpenNeuro datasets and about 34,000 subjects, with diffusion-derived maps, defacing and anatomy masks and harmonized metadata, for self-supervised pre-training. CC BY 4.0 on Hugging Face.
- QSM Reconstruction Challenge 2.0 (simulated)
Simulated data, not patient scans: four multi-echo gradient-echo magnitude and phase datasets at 1 mm from a realistic in silico head phantom built from one volunteer's 7T MRI, with ground-truth susceptibility maps and tissue segmentations for benchmarking QSM.
- TotalSegmentator CT
1,228 routine clinical CT series from University Hospital Basel, randomly sampled across body regions, scanners and pathologies, with reviewed segmentations of 117 anatomical structures. Basis of the TotalSegmentator model.