FDG-PET-CT-Lesions (autoPET)
Whole-body FDG-PET/CT in lymphoma, melanoma, and NSCLC, plus studies with no PET-positive malignancy
Open the source page ↗ See it in the directory
At a glance
- What it is
- Whole-body FDG-PET/CT in lymphoma, melanoma, and NSCLC, plus studies with no PET-positive malignancy
- Area
- Nuclear medicine
- Modality
- PT, CT
- Format
- DICOM
- Size
- 900 subjects; 1,014 studies. Defaced DICOM about 419 GB. Original images are a separate controlled download.
- Normals included
- Yes
- License
- CC BY 4.0 (defaced images and clinical CSV); NIH Controlled Data Access Policy (original images)
- Commercial use
- Allowed by the license, with its attribution terms
- Access
- Open download, no account
- Status
- Verified: source page reviewed by Hounsfield Lab
- Added
- 2026-10-18
- Last checked
- 2026-11-11
- Source
- www.cancerimagingarchive.net/collection/fdg-pet-ct-lesions/
How to access
Download the defaced DICOM and the clinical CSV from the collection page; those rows are CC BY 4.0 and do not need an application. Original images that include the head are under the NIH Controlled Data Access Policy linked on the page. The autoPET challenge site is a separate entry point and may not be this exact file release.
Limitations
The openly downloadable images are defaced (head blacked out from the skull base up). If you need the face-containing originals, that is controlled access, not CC BY. Negative controls mean no PET-positive malignant lesion, not healthy volunteers. Manual tumor masks are on the PET-positive studies.
Citation required?
Yes. Cite the collection DOI on the TCIA page and follow the TCIA Data Usage Policy.
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
- nnU-Net: Self-configuring segmentation framework
- 3D Slicer: Open platform for visualization, segmentation and image computing
- 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
- OHIF Viewer: Zero-footprint web DICOM viewer
More nuclear medicine datasets
- NCI Imaging Data Commons: CT, MR, PT, MG, CR · Mostly CC BY; a minority of files are CC-NC (each file is tagged)
- PSMA-PET-CT-Lesions: PT, CT · CC BY 4.0
- Soft-tissue-Sarcoma: MR, CT, PT · CC BY 3.0
- SPADe: PT, CT · Stanford AIMI research use agreement (non-commercial; commercial license sold separately)
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.