Healthy-Total-Body-CTs
Healthy adult total-body low-dose CT from the uEXPLORER PET/CT scanner, with organ segmentations
Open the source page ↗ See it in the directory
At a glance
- What it is
- Healthy adult total-body low-dose CT from the uEXPLORER PET/CT scanner, with organ segmentations
- Area
- Body
- Modality
- CT
- Format
- DICOM, NIfTI
- Size
- 30 subjects; 30 studies; CT images about 59 GB (58.95 GB in the download table). Segmentations about 109 MB
- Normals included
- Yes
- License
- NIH Controlled Data Access Policy (CT images); CC BY 4.0 (organ segmentations and demographics)
- Commercial use
- Mixed or unclear; check the source
- Access
- Credentialed access under a data-use agreement
- Status
- Verified: source page reviewed by Hounsfield Lab
- Added
- 2026-10-21
- Last checked
- 2026-11-11
- Source
- www.cancerimagingarchive.net/collection/healthy-total-body-cts/
How to access
The CT images can reconstruct a face, so they are not an open download. Follow the NIH Controlled Data Access Policy link on the collection page. Request the images in dbGaP (the policy page lists phs004225, Radiology Imaging Data Containing Faces from The Cancer Imaging Archive, for most TCIA face datasets). The request has to come from someone equivalent to a tenure-track professor or a senior scientist. After approval, create an NCI Data Commons API key and download with the TCIA Data Retriever using the manifest in the Data Access table. Organ segmentations (NIfTI and an organ-values spreadsheet) and the demographics spreadsheet are listed separately under CC BY 4.0 and do not need an application.
Limitations
Do not assume the whole collection is CC BY. Only the segmentations and demographics are CC BY 4.0. The CT requires controlled access. Thirty healthy adults, not a cancer cohort, scanned on the UC Davis uEXPLORER total-body PET/CT system; only the CT is distributed here. The 90-minute CT was about 50 mAs and the other time points about 5 mAs, all at 140 kVp. Each person has three or six same-day time points, stored as one study in version 3. Segmentations cover 37 tissues, were made with MOOSE on the 90-minute scan, and are NIfTI that may need re-orientation to match the DICOM. Version 3 (updated 2026-09-23) corrected NIfTI file names to match the DICOM.
Citation required?
Yes. Cite the collection DOI on the TCIA page (10.7937/nc7z-4f76, version 3) and follow the TCIA Data Usage Policy. Imaging access is governed by the NIH policy, not only by CC BY.
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
- pydicom: Read, modify and write DICOM files in Python
- highdicom: High-level Python API on pydicom for reading images and writing AI results as DICOM Segmentation, Structured Report, parametric map and annotation objects
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
- LDCT-and-Projection-data: CT · Chest, liver, and phantom images CC BY 4.0; head images under the NIH Controlled Data Access Policy
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.