LDCT-and-Projection-data
Non-contrast head CT for acute cognitive or motor deficit, low-dose non-contrast chest CT for lung-nodule screening, and contrast-enhanced abdominal CT for liver metastases. Pathology annotations and patient age are in the clinical spreadsheet.
Open the source page ↗ See it in the directory
At a glance
- What it is
- Non-contrast head CT for acute cognitive or motor deficit, low-dose non-contrast chest CT for lung-nodule screening, and contrast-enhanced abdominal CT for liver metastases. Pathology annotations and patient age are in the clinical spreadsheet.
- Area
- Neuro, Chest, Body
- Modality
- CT
- Format
- DICOM
- Size
- 299 subjects; about 1.29 TB. Version 8 download table: chest 256.81 GB (99 subjects), liver 604.12 GB (100 subjects), head 462.77 GB (99 subjects), phantom 1.8 GB (1 subject). The collection text still describes 100 chest scans.
- Normals included
- Partial (mixed or unlabeled)
- License
- Chest, liver, and phantom images CC BY 4.0; head images under the NIH Controlled Data Access Policy
- 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
- 2026-11-11
- Last checked
- 2026-11-11
- Source
- www.cancerimagingarchive.net/collection/ldct-and-projection-data/
How to access
Head images can reconstruct a face, so they are not an open download. Follow the NIH Controlled Data Access Policy link on the collection page and complete that request before using the head manifest with the TCIA Data Retriever. Chest, liver, and phantom images, and the clinical spreadsheet, are public Creative Commons rows. Open the collection page and use the download control in the Data Access table (TCIA Data Retriever). Those rows do not need an application. Read the Citations & Data Usage Policy tab before use.
Limitations
Do not assume the whole collection is CC BY. Chest, liver, and phantom images are CC BY 4.0, which allows commercial use with attribution. Head images are under the NIH Controlled Data Access Policy because a face could be reconstructed. The clinical spreadsheet is CC BY 4.0. The Matlab DICOM-CT-PD dictionary and reader on the same table are CC BY 3.0. Version 8 (updated 2026-11-09) corrected 8 chest lesion coordinates in the clinical spreadsheet and clarified the manual; the snapshots were not changed. Very large. Built for reconstruction and denoising research. Each case includes DICOM images and DICOM-CT-PD projection data at the routine dose and at a simulated lower dose (25% for head and abdomen, 10% for chest). Reconstructions are filtered back projection only. The page includes low-dose reconstructed images for the Siemens SOMATOM Definition Flash cases. Scanners named on the page are the Siemens SOMATOM Definition Flash and the GE Lightspeed VCT. These are mixed clinical exams, not a healthy-volunteer set. Check the clinical spreadsheet before treating a case as normal.
Citation required?
Yes. McCollough C, Chen B, Holmes III D, Duan X, Yu Z, Yu L, Leng S, Fletcher J (2020). Low Dose CT Image and Projection Data (LDCT-and-Projection-data) (Version 8). The Cancer Imaging Archive. https://doi.org/10.7937/9npb-2637 . Also cite Moen TR et al., Medical Physics 2020, https://doi.org/10.1002/mp.14594 . Acknowledge NIBIB grants EB017095 and EB017185. Follow the TCIA Data Usage Policy.
Related open-source tools
- 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
- Pillar-0 (finetune code + HF weights): Open 3D radiology foundation model; finetuning framework, weights on Hugging Face
- 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
- nnU-Net: Self-configuring segmentation framework
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.