PROTEAS brain metastases dataset
Longitudinal diagnostic and follow-up MRI and CT from patients with brain metastases, with manual segmentations, radiotherapy plans, and radiomics
Open the source page ↗ See it in the directory
At a glance
- What it is
- Longitudinal diagnostic and follow-up MRI and CT from patients with brain metastases, with manual segmentations, radiotherapy plans, and radiomics
- Area
- Neuro
- Modality
- MR, CT
- Format
- DICOM, NIfTI
- Size
- 40 patients. The Scientific Data paper counts 185 MRI studies (744 MRI scans), 45 planning CT scans, and 45 radiotherapy plans, with segmentations of 65 metastases. Zenodo v5 lists 15.1 GB of files. The Zenodo summary says 185 MRI and CT imaging studies
- Normals included
- No
- License
- CC BY 4.0
- Commercial use
- Allowed by the license, with its attribution terms
- Access
- Open download, no account
- Status
- Verified: source page reviewed by Hounsfield Lab
- Added
- 2026-11-04
- Last checked
- 2026-11-11
- Source
- zenodo.org/records/23171182
How to access
Open the Zenodo record and download the patient zip files plus the clinical/demographic spreadsheet and the MRI radiomics spreadsheet. No registration. Version v5 was published 5 October 2026 (DOI 10.5281/zenodo.23171182; concept DOI 10.5281/zenodo.15499111). Radiomics code is at https://github.com/InSilicoModellingGroup/pyRadiomicBM .
Limitations
No healthy controls. All 40 patients had brain metastases, identified at the Bank of Cyprus Oncology Centre and imaged at six diagnostic centers in Cyprus (University of Cyprus and Bank of Cyprus Oncology Centre). The Scientific Data data record says the raw pre-treatment and follow-up scans are DICOM, and that BraTS-space MRI (T1, T2, post-contrast T1, and FLAIR), the planning CT, the radiotherapy plan, and the segmentations are NIfTI. Segmentations of 65 metastases cover enhancing tumor, edema, and necrotic core. The same mask files also label ventricles, white matter, grey matter, and CSF. The paper's data-availability link is an earlier Zenodo version (10.5281/zenodo.17253793); this row uses the current v5 record. Folder names may include exam dates. The paper states that DICOM headers were de-identified with the Eclipse anonymizer before deposit. The clinical spreadsheet includes dates of diagnosis, lesion detection, and treatment. The Scientific Data article is CC BY-NC-ND 4.0; that is the article license, not the dataset license.
Citation required?
Yes. Cite Flouri et al., A longitudinal MRI dataset of brain metastases with tumor segmentations, clinical and radiomic data, Scientific Data, https://doi.org/10.1038/s41597-025-06131-0 , and the Zenodo version DOI 10.5281/zenodo.23171182. CC BY 4.0 requires attribution.
Related open-source tools
- HD-BET: Deep-learning brain extraction (skull stripping) for MRI
- FastSurfer: Deep-learning whole-brain segmentation and cortical surface reconstruction, a fast alternative to FreeSurfer recon-all
- FreeSurfer: Neuroimaging analysis and visualization suite
- BrainChop: In-browser 3D MRI rendering and segmentation
- Neuro-VL: Neuroimaging vision-language model (Neuro-VL-8B-Thinking, Qwen3-8B language model with an HLIP visual encoder) that reads complete MRI and CT exams, converses about findings, drafts reports with reasoning traces and compares serial exams; trained on nearly 1 million clinical neuroimaging studies from 450,000 patients; released with the NeuroBench benchmark
- dcm2niix: Converts DICOM to NIfTI with JSON sidecars; the standard converter in many brain MRI and BIDS pipelines
- pydicom: Read, modify and write DICOM files in Python
More neuro datasets
- BrainMetShare: MR · Stanford AIMI research use agreement (non-commercial; commercial license sold separately)
- Burdenko-GBM-Progression: MR, CT · NIH Controlled Data Access Policy (images); CC BY 4.0 (clinical and genomic CSV)
- CFB-GBM: MR, CT · CC BY 4.0
- CPAISD: CT · CC BY 4.0
- CQ500: CT · CC BY-NC-SA 4.0
- CT-ICH: CT · PhysioNet Restricted Health Data License 1.5.0
Hounsfield Lab links to the source and does not host images. The license and access summary reflects the source page on the last-checked date; terms can change, so read the source before you download. Not legal advice.