Skip to main content


TCGA-LUSC | The Cancer Genome Atlas Lung Squamous Cell Carcinoma Collection

DOI: 10.7937/K9/TCIA.2016.TYGKKFMQ | Data Citation Required | Image Collection

Location Species Subjects Data Types Cancer Types Size Supporting Data Status Updated
Lung Human 37 CT, NM, PT, Pathology Lung Squamous Cell Carcinoma 15.02GB Clinical, Genomics Public, Complete 2020/05/29


The Cancer Genome Atlas Lung Squamous Cell Carcinoma (TCGA-LUSC) data collection is part of a larger effort to build a research community focused on connecting cancer phenotypes to genotypes by providing clinical images matched to subjects from The Cancer Genome Atlas (TCGA). Clinical, genetic, and pathological data resides in the Genomic Data Commons (GDC) Data Portal while the radiological data is stored on The Cancer Imaging Archive (TCIA). 

Matched TCGA patient identifiers allow researchers to explore the TCGA/TCIA databases for correlations between tissue genotype, radiological phenotype and patient outcomes.  Tissues for TCGA were collected from many sites all over the world in order to reach their accrual targets, usually around 500 specimens per cancer type.  For this reason the image data sets are also extremely heterogeneous in terms of scanner modalities, manufacturers and acquisition protocols.  In most cases the images were acquired as part of routine care and not as part of a controlled research study or clinical trial. 

CIP TCGA Radiology Initiative

Imaging Source Site (ISS) Groups are being populated and governed by participants from institutions that have provided imaging data to the archive for a given cancer type. Modeled after TCGA analysis groups, ISS groups are given the opportunity to publish a marker paper for a given cancer type per the guidelines in the table above. This opportunity will generate increased participation in building these multi-institutional data sets as they become an open community resource.  Learn more about the TCGA Lung Phenotype Research Group.

Data Access

Version 4: Updated 2020/05/29

Updated clinical data link with latest spreadsheets from GDC. Added new biomedical spreadsheets from GDC.

Title Data Type Format Access Points Subjects Studies Series Images License
Download requires NBIA Data Retriever
37 74 279 36,518 CC BY 3.0

Additional Resources for this Dataset

The NCI Cancer Research Data Commons (CRDC) provides access to additional data and a cloud-based data science infrastructure that connects data sets with analytics tools to allow users to share, integrate, analyze, and visualize cancer research data.

Citations & Data Usage Policy

Data Citation Required: Users must abide by the TCIA Data Usage Policy and Restrictions. Attribution must include the following citation, including the Digital Object Identifier:

Data Citation

Kirk, S., Lee, Y., Kumar, P., Filippini, J., Albertina, B., Watson, M., Rieger-Christ, K., & Lemmerman, J. (2016). The Cancer Genome Atlas Lung Squamous Cell Carcinoma Collection (TCGA-LUSC) (Version 4) [Data set]. The Cancer Imaging Archive.

Detailed Description

GDC Data Portal – Clinical and Genomic Data

The GDC Data Portal has extensive clinical and genomic data, which can be matched to the patient identifiers on the images here in TCIA.  Below is a snapshot of clinical data extracted on 1/5/2016.

Explanations of the clinical data can be found on the Biospecimen Core Resource Clinical Data Forms linked below:

Subject Identifiers: a subject with radiology images stored in TCIA is identified with a Patient ID that is identical to the Patient ID of the same subject with demographic, clinical, pathological, and/or genomic data stored in TCGA. For each TCGA case, the baseline TCGA imaging studies found on TCIA are pre-surgical.

Dates: TCIA and TCGA handle dates differently, and there are no immediate plans to reconcile:

  • TCIA Dates: dates (be they birth dates, imaging study dates, etc.) in the Digital Imaging and Communications in Medicine (DICOM) headers of TCIA radiology images have been offset by a random number of days. The offset is a number of days between 3 and 10 years prior to the real date that is consistent for each TCIA image-submitting site and collection, but that varies among sites and among collections from the same site. Thus, the number of days between a subject’s longitudinal imaging studies are accurately preserved when more than one study has been archived while still meeting HIPAA requirements.
  • TCGA Dates: the patient demographic and clinical event dates are all the number of days from the index date, which is the actual date of pathologic diagnosis. So all the dates in the data are relative negative or positive integers, except for the “days_to_pathologic_diagnosis” value, which is 0 – the index date. The years of birth and diagnosis are maintained in the distributed clinical data file. The NCI retains a copy of the data with complete dates, but those data are not made available.With regard to other TCGA dates, if a date comes from a HIPAA “covered entity’s” medical record, it is turned into the relative day count from the index date. Dates like the date TCGA received the specimen or when the TCGA case report form was filled out are not such covered dates, and they will appear as real dates (month, day, and year).


We would like to acknowledge the individuals and institutions that have provided data for this collection:

  • University of North Carolina, Chapel Hill, NC - Special thanks to J. Keith SmithMD, Ph.D. and Shanah Kirk from the Department of Radiology.
  • Roswell Park, Buffalo, NY - Special thanks to Prasanna Kumar, MD and Joe Filippini from the Department of Diagnostic Radiology 
  • Washington University, Saint Louis, MO - Special thanks to Ramaswamy Govindan, MD. and Kalin Guebert from the Department of Internal Medicine - Medical Oncology.
  • Lahey Hospital & Medical Center, Burlington, MA - Special thanks to John Lemmerman, RT and Kimberly Reiger-Christ, PhD, Cancer Research, Sophia Gordon Cancer Center.

Other Publications Using this Data

TCIA maintains a list of publications which leverage our data. If you have a manuscript you’d like to add please contact TCIA’s Helpdesk.

  • ALAYUE, L. T., GOSHU, B. S., & TAJU, E. (2022). FEATURE EXTRACTION OF LUNG CANCER USING IMAGE ANALYSIS TECHNIQUES. Romanian Journal of Biophysics, 32, 18. Retrieved from
  • Al-Tashi, Q., Saad, M. B., Sheshadri, A., Wu, C. C., Chang, J. Y., Al-Lazikani, B., . . . Wu, J. (2023). SwarmDeepSurv: swarm intelligence advances deep survival network for prognostic radiomics signatures in four solid cancers. Patterns. doi:
  • Aswolinskiy, W., Tellez, D., Raya, G., van der Woude, L., Looijen-Salamon, M., van der Laak, J., . . . Ciompi, F. (2021). Neural image compression for non-small cell lung cancer subtype classification in H&E stained whole-slide images. Paper presented at the Medical Imaging 2021: Digital Pathology.
  • Bóbeda, J., García-González, M. J., Pérez-Herrera, L. V., & López-Linares, K. (2023). Unsupervised Data Drift Detection Using Convolutional Autoencoders: A Breast Cancer Imaging Scenario. Paper presented at the KES InMed: International KES Conference on Innovation in Medicine and Healthcare, Rome, Italy.
  • Choi, J., Cho, H. H., Kwon, J., Lee, H. Y., & Park, H. (2021). A Cascaded Neural Network for Staging in Non-Small Cell Lung Cancer Using Pre-Treatment CT. Diagnostics (Basel), 11(6). doi:10.3390/diagnostics11061047
  • Du, R., & Vardhanabhuti, V. (2020, 06-08 July 2020). 3D-RADNet: Extracting labels from DICOM metadata for training general medical domain deep 3D convolution neural networks. Paper presented at the Third Conference on Medical Imaging with Deep Learning (MIDL 2020), Montréal, QC, Canada.
  • Kanavati, F., Toyokawa, G., Momosaki, S., Rambeau, M., Kozuma, Y., Shoji, F., . . . Tsuneki, M. (2020). Weakly-supervised learning for lung carcinoma classification using deep learning. Sci Rep, 10(1), 1-11. doi:10.1038/s41598-020-66333-x
  • Leitner, B. P., Givechian, K. B., Ospanova, S., Beisenbayeva, A., Politi, K., & Perry, R. J. (2022). Multimodal analysis suggests differential immuno-metabolic crosstalk in lung squamous cell carcinoma and adenocarcinoma. NPJ Precis Oncol, 6(1), 8. doi:10.1038/s41698-021-00248-2
  • Leitner, B. P., & Perry, R. J. (2020). The Impact of Obesity on Tumor Glucose Uptake in Breast and Lung Cancer. JNCI Cancer Spectrum. doi:10.1093/jncics/pkaa007
  • Matsuyama, E., & Tsai, D.-Y. (2018). Automated Classification of Lung Diseases in Computed Tomography Images Using a Wavelet Based Convolutional Neural Network. Journal of Biomedical Science and Engineering, 11(10), 263. doi:10.4236/jbise.2018.1110022
  • Na, K. J., Choi, H., Oh, H. R., Kim, Y. H., Lee, S. B., Jung, Y. J., . . . Kim, Y. T. (2020). Reciprocal change in Glucose metabolism of Cancer and Immune Cells mediated by different Glucose Transporters predicts Immunotherapy response. THERANOSTICS, 10(21), 9579-9590. doi:10.7150/thno.48954
  • Saltz, J., Almeida, J., Gao, Y., Sharma, A., Bremer, E., DiPrima, T., . . . Kurc, T. (2017). Towards Generation, Management, and Exploration of Combined Radiomics and Pathomics Datasets for Cancer Research. AMIA Summits on Translational Science Proceedings, 2017, 85-94.
  • Singh, A., Goyal, S., Rao, Y. J., & Loew, M. (2019). A Novel Imaging-Genomic Approach to Predict Outcomes of Radiation Therapy. (MS). George Washington University.
  • Thomas, R., Schalck, E., Fourure, D., Bonnefoy, A., & Cervera-Marzal, I. (2021). 2Be3-Net: Combining 2D and 3D Convolutional Neural Networks for 3D PET Scans Predictions. Paper presented at the International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2021).
  • Torres, F. S., Akbar, S., Raman, S., Yasufuku, K., Schmidt, C., Hosny, A., . . . Leighl, N. B. (2021). End-to-End Non-Small-Cell Lung Cancer Prognostication Using Deep Learning Applied to Pretreatment Computed Tomography. JCO Clin Cancer Inform, 5, 1141-1150. doi:10.1200/cci.21.00096
  • Walter, R., Rozynek, P., Casjens, S., Werner, R., Mairinger, F., Speel, E., . . . Theegarten, D. (2018). Methylation of L1RE1, RARB, and RASSF1 function as possible biomarkers for the differential diagnosis of lung cancer. PLoS One, 13(5), e0195716. doi:10.1371/journal.pone.0195716
  • Woo, M. (2021). Deep Learning Frameworks to Improve Inter-Observer Variability in CT Measurement of Solid Tumor. (Ph.D. Dissertation). Clemson University, Retrieved from  (28413785)
  • Yu, L., Tao, G., Zhu, L., Wang, G., Li, Z., Ye, J., & Chen, Q. (2019). Prediction of pathologic stage in non-small cell lung cancer using machine learning algorithm based on CT image feature analysis. BMC Cancer, 19(1), 464. doi:10.1186/s12885-019-5646-9
  • Yu, Z. (2016). Co-Segmentation Methods for Improving Tumor Target Delineation in PET-CT Images. (Master of Science (M.Sc.)). University of Saskatchewan, Saskatoon, Saskatchewan, Canada. Retrieved from

TCIA Citation

Clark, K., Vendt, B., Smith, K., Freymann, J., Kirby, J., Koppel, P., Moore, S., Phillips, S., Maffitt, D., Pringle, M., Tarbox, L., & Prior, F. (2013). The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. In Journal of Digital Imaging (Vol. 26, Issue 6, pp. 1045–1057). Springer Science and Business Media LLC.


“The results <published or shown> here are in whole or part based upon data generated by the TCGA Research Network:”

Previous Versions

Version 3: Updated 2017/01/30

Added image data for one subject.

Title Data Type Format Access Points Studies Series Images License
Images DICOM
Clinical Data TXT
Genomics WEB

Version 2: Updated 2016/01/05

Extracted latest release of clinical data (TXT) from the GDC Data Portal.

Title Data Type Format Access Points Studies Series Images License
Images DICOM
Clinical Data TXT
Genomics WEB

Version 1: Updated 2015/04/29

Title Data Type Format Access Points Studies Series Images License
Images DICOM
Clinical Data TXT
Genomics WEB
Analysis Results Using This Collection