CPTAC-LUAD
The Clinical Proteomic Tumor Analysis Consortium Lung Adenocarcinoma Collection (CPTAC-LUAD)
Standard-of-care CT, PET and MRI and whole-slide pathology images of 244 patients from the NCI CPTAC lung adenocarcinoma cohort, linked by patient ID to proteomic, genomic and clinical data in the NCI data commons.
Overview
CPTAC-LUAD holds the images of the lung adenocarcinoma cohort of the National Cancer Institute's Clinical Proteomic Tumor Analysis Consortium. The Cancer Imaging Archive gathers radiology and pathology images of CPTAC patients so that image features can be related to the proteomic, genomic and clinical data of the same people. Patient IDs are the same as in the Proteomic Data Commons and Genomic Data Commons. The first version appeared in January 2018, and the collection has been updated 13 times, most recently in August 2025.
Composition
The collection page counts 244 subjects. Radiology covers 38 of them, with 75 studies, 448 DICOM series and 72,555 images. Pathology covers 243 subjects with 1,137 whole-slide images in SVS format. In the radiology metadata, 37 subjects have CT, 11 have PET and 2 have MRI. The consortium's "Discovery Cohort" has its own radiology and pathology download links. The full collection takes 476.82 GB.
Acquisition
Radiology comes from routine clinical care shortly before the pathological diagnosis, plus follow-up scans where available, so modality, scanner and protocol differ between patients. The radiology metadata lists Siemens, GE, Philips and Hitachi systems, and the examined body parts range from chest to whole body. Slides were produced in the CPTAC tissue qualification workflow. Acknowledged contributors include hospitals and biobanks in the United States and Poland. DICOM dates are shifted by a random offset, and a DICOM tag records the days between each scan and the pathological diagnosis.
Annotations
The collection has no image labels of its own. TCIA lists the SAROS analysis result as derived from this collection.
Known limitations
- Most subjects contribute only pathology slides; fewer than one in six have radiology.
- Radiology is heterogeneous in modality, vendor and protocol, and follow-up coverage varies by patient.
- Clinical and molecular data are not in the TCIA download and have to be exported from the data commons.
- The collection page labels version 13 CC BY 4.0, while version 12 and the radiology metadata file name CC BY 3.0.
Cohort
Aggregate numbers from the sources below. Bars are relative to the 244 subjects.
Sex
- Male 22 59%
- Female 15 41%
Covers 37 of 244 subjects.
Modality
subjects
- Pathology slides 243 100%
- CT 37 15%
- PET 11 5%
- MRI 2 <1%
Scanner vendor
subjects
- Siemens Healthineers 18 7%
- GE HealthCare 17 7%
- Philips 10 4%
- Hitachi / Fujifilm 1 <1%
License and access
Our reading of the license, not legal advice. Before you use the data, read the original license and confirm that your use is allowed. We take no responsibility for how you use a dataset. Full disclaimer
Download without an account
DICOM radiology is downloaded with the TCIA Data Retriever from a manifest file, slides through IBM Aspera. No account is needed. Clinical, proteomic and genomic data are in the Proteomic and Genomic Data Commons.
Creative Commons Attribution 4.0 International
Use, share and adapt the data for any purpose, including commercial use, as long as you credit the creators.
What you can do
- Yes
- Yes
- Yes
- Yes
What you can share
- Yes
- Yes
- Yes
What you must do
- Yes
- Share alike No
- No
- No
- Manuscript review No
- Release code No
- Return results No
- Delete after use No
Limits
- No
- Location limits No
Citation
National Cancer Institute Clinical Proteomic Tumor Analysis Consortium (CPTAC). (2018). The Clinical Proteomic Tumor Analysis Consortium Lung Adenocarcinoma Collection (CPTAC-LUAD) (Version 13) [dataset]. The Cancer Imaging Archive. https://doi.org/10.7937/k9/tcia.2018.pat12tbs. Acknowledgement: "Data used in this publication were generated by the National Cancer Institute Clinical Proteomic Tumor Analysis Consortium (CPTAC)."
All numbers
Every number on this page, as stored in stats.csv, with its source.
| Measure | Breakdown | Value | Source |
|---|---|---|---|
| Subjects | total all subjects in the collection, radiology and pathology | 244 | tcia-cptac-luad Collection Snapshot |
| Subjects | modality=SM subjects with tissue slide images | 243 | tcia-cptac-luad Data Access (Version 13) |
| Slides | total | 1,137 | tcia-cptac-luad Data Access (Version 13) |
| Studies | total radiology only (38 subjects) | 75 | tcia-cptac-luad Data Access (Version 13) |
| Scans | total DICOM series | 448 | tcia-cptac-luad Data Access (Version 13) |
| Images | total DICOM images | 72,555 | tcia-cptac-luad Data Access (Version 13) |
| Subjects | modality=CT radiology subset (38 subjects) only | 37 | tcia-cptac-luad-digest Patient ID, Modality columns |
| Subjects | modality=PT radiology subset (38 subjects) only | 11 | tcia-cptac-luad-digest Patient ID, Modality columns |
| Subjects | modality=MR radiology subset (38 subjects) only | 2 | tcia-cptac-luad-digest Patient ID, Modality columns |
| Subjects | sex=male radiology subset only, 1 subject without a value | 22 | tcia-cptac-luad-digest Patient ID, Patient Sex columns |
| Subjects | sex=female radiology subset only, 1 subject without a value | 15 | tcia-cptac-luad-digest Patient ID, Patient Sex columns |
| Subjects | vendor=siemens radiology subset only, 4 subjects have series without a manufacturer | 18 | tcia-cptac-luad-digest Patient ID, Manufacturer columns |
| Subjects | vendor=ge radiology subset only, 4 subjects have series without a manufacturer | 17 | tcia-cptac-luad-digest Patient ID, Manufacturer columns |
| Subjects | vendor=philips radiology subset only, 4 subjects have series without a manufacturer | 10 | tcia-cptac-luad-digest Patient ID, Manufacturer columns |
| Subjects | vendor=hitachi radiology subset only, recorded as Hitachi Medical Corporation | 1 | tcia-cptac-luad-digest Patient ID, Manufacturer columns |
Sources
The keys used in the table above.
- tcia-cptac-luad TCIA CPTAC-LUAD collection page (version 13, updated 2025/08/01) website
- tcia-cptac-luad-digest TCIA CPTAC-LUAD radiology metadata digest (TCIA-CPTAC-LUAD_v13_20250801-nbia-digest.xlsx, open download), counted per unique Patient ID computed