TotalSegmentator CT dataset
Routine clinical CT scans with segmentations of 117 anatomical structures (organs, bones, muscles, vessels); version 3 adds 291 pediatric CTs
Open the source page ↗ See it in the directory
At a glance
- What it is
- Routine clinical CT scans with segmentations of 117 anatomical structures (organs, bones, muscles, vessels); version 3 adds 291 pediatric CTs
- Area
- Body, Chest, MSK
- Modality
- CT
- Format
- NIfTI
- Size
- 1,939 CT images (version 3.0.0); one 37.4 GB zip
- Normals included
- Partial (mixed or unlabeled)
- 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
- 2026-10-19
- Last checked
- 2026-11-11
- Source
- zenodo.org/records/22688904
How to access
Open the Zenodo record and download the zip. No account is needed. The record also links a faster Dropbox copy and a 102-subject subset for a quick look. Earlier versions (1,228 images) remain on Zenodo under their own DOIs.
Limitations
Labels are anatomy, not disease, and the scans have no normal or abnormal label even though many pathologies are present. NIfTI, not DICOM. The segmentations were made with a model-assisted workflow, so they can carry systematic errors; version 3 fixed many label errors and vertebra mix-ups. The paper describes version 1.
Citation required?
Yes. The record asks you to cite Wasserthal et al., TotalSegmentator, Radiology: Artificial Intelligence 2023, and the Zenodo DOI 10.5281/zenodo.22688904.
Related open-source tools
- TotalSegmentator: Segments more than 100 anatomical structures in CT and MR
- NV-Segment-CT: CT segmentation built from MONAI VISTA3D: 117 structures automatically, or 132 promptable by point or class. Research use only, not for clinical care. Needs a CUDA GPU; weights are about 872 MB
- Merlin: 3D vision-language model for CT that uses structured EHR and report supervision
- Pillar-0 (finetune code + HF weights): Open 3D radiology foundation model; finetuning framework, weights on Hugging Face
- nnU-Net: Self-configuring segmentation framework
- TotalSpineSeg: Two-stage nnU-Net tool that segments and individually labels every vertebra and intervertebral disc plus the spinal cord and canal, using an odd/even vertebra scheme and landmark discs (C2-C3, C7-T1, T12-L1, L5-S) to avoid fused or split vertebrae; works on localizers and short-FOV scans; peer-reviewed in European Radiology (Nov 7, 2026)
- 3D Slicer: Open platform for visualization, segmentation and image computing
More body datasets
- AMOS (abdominal multi-organ segmentation): CT, MR · CC BY 4.0
- C4KC-KiTS: CT · CC BY 3.0
- Colorectal-Liver-Metastases: CT · CC BY 4.0
- CT Colonography: CT · CC BY 3.0 and CC BY 4.0 (see the file table)
- CT-ORG: CT · CC BY 3.0
- Healthy-Total-Body-CTs: CT · NIH Controlled Data Access Policy (CT images); CC BY 4.0 (organ segmentations and demographics)
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.