CFB-GBM
Glioblastoma, with pre- and post-treatment MRI, planning CT, RTDOSE, tumor masks, and GTV
Open the source page ↗ See it in the directory
At a glance
- What it is
- Glioblastoma, with pre- and post-treatment MRI, planning CT, RTDOSE, tumor masks, and GTV
- Area
- Neuro
- Modality
- MR, CT
- Format
- NIfTI
- Size
- 264 subjects; about 208 GB (3,981 images in the NIfTI package)
- 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
- 2026-10-21
- Last checked
- 2026-11-11
- Source
- www.cancerimagingarchive.net/collection/cfb-gbm/
How to access
Open the collection page and use the download control in the Data Access table (TCIA Data Retriever or Aspera, whichever that row names). A public Creative Commons row does not need an application. Read the Citations & Data Usage Policy tab before use. Images and segmentations are one NIfTI package, and that row requires the IBM Aspera Connect plugin. Clinical, treatment, imaging-availability, RANO, and PyRadiomics TSVs are separate small downloads on the same table.
Limitations
NIfTI only, and skull-stripped. DICOM is deliberately not provided, to avoid leakage of header metadata. MRI brain extraction used ANTsPyNet on the pre-treatment post-contrast T1, and the other MRI series were rigidly registered to that scan. Planning CT was defaced with TotalSegmentator (thermoplastic mask removal) and then CTA-DEFACE. Not healthy controls: 264 deceased adults with glioblastoma, treated with the Stupp protocol at one center (Centre François Baclesse) from November 2017 to December 2023, and not enrolled in a trial. Not every sequence or time point exists for every patient (planning CT 195, RTDOSE 194; tumor masks follow the post-contrast T1 exams). GTV contours are from routine radiotherapy planning. Clinical, treatment, and RANO TSVs are included, plus a PyRadiomics feature table. Version 4 (updated 2026-09-11) corrected the RANO TSV to enhancing-tumor measurements and renumbered some folders; the images were not changed.
Citation required?
Yes. Cite the collection DOI on the TCIA page (10.7937/v9pn-2f72, version 4) and follow the TCIA Data Usage Policy.
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
- TorchIO: Medical image loading, preprocessing and augmentation for PyTorch
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)
- 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
- ISLES'24: CT, MR · CC BY-NC-SA 4.0
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.