In short, this publication applies a radiomic approach to computed tomography data of 1,019 patients with lung or head-and-neck cancer. Radiomics refers to the comprehensive quantification of tumour phenotypes by applying a large number of quantitative image features. In present analysis 440 features quantifying tumour image intensity, shape and texture, were extracted. We found that a large number of radiomic features have prognostic power in independent data sets, many of which were not identified as significant before. Radiogenomics analysis revealed that a prognostic radiomic signature, capturing intra-tumour heterogeneity, was associated with underlying gene-expression patterns. These data suggest that radiomics identifies a general prognostic phenotype existing in both lung and head-and-neck cancer. This may have a clinical impact as imaging is routinely used in clinical practice, providing an unprecedented opportunity to improve decision-support in cancer treatment at low cost.
The dataset described here (Lung1) was used to build a prognostic radiomic signature. The Lung3 dataset used to investigate the association of radiomic imaging features with gene-expression profiles consisting of 89 NSCLC CT scans with outcome data can be found here: NSCLC-Radiomics-Genomics.
Other data sets in the Cancer Imaging Archive that were used in the same study published in Nature Communications: Head-Neck-Radiomics-HN1, NSCLC-Radiomics-Interobserver1, RIDER Lung CT Segmentation Labels from: Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach.
For scientific inquiries about this dataset, please contact Dr Leonard Wee (firstname.lastname@example.org) and Prof Andre Dekker (email@example.com) at MAASTRO Clinic/Maastricht University Medical Centre+ and Maastricht University, The Netherlands.
We would like to acknowledge the individuals and institutions that have provided data for this collection:
- Leonard Wee, MAASTRO (Dept of Radiotherapy), Maastricht University Medical Centre+, Maastricht, Limburg, The Netherlands.
- Dirk de Ruysscher, MAASTRO (Dept of Radiotherapy), Maastricht University Medical Centre+, Maastricht, Limburg, The Netherlands.
- Andre Dekker, MAASTRO (Dept of Radiotherapy), Maastricht University Medical Centre+, Maastricht, Limburg, The Netherlands.
- Hugo Aerts, Computational Imaging and Bioinformatic Laboratory, Dana-Farber Cancer Institute & Harvard Medical School, Boston, Massachusetts, USA.
Click the Download button to save a ".tcia" manifest file to your computer, which you must open with the NBIA Data Retriever. Click the Search button to open our Data Portal, where you can browse the data collection and/or download a subset of its contents.
|Data Type||Download all or Query/Filter|
|Images, Segmentations, and Radiation Therapy Structures (DICOM, 29GB)|
|Lung1 clinical (CSV)|
Click the Versions tab for more info about data releases.
Third Party Analyses of this Dataset
TCIA encourages the community to publish your analyses of our datasets. Below is a list of such third party analyses published using this Collection:
CT, RTSTRUCT, SEG
Number of Participants
Number of Studies
Number of Series
Number of Images
|Image Size (GB)||29.3|
Radiation Oncologist Tumor Segmentations
The RTSTRUCT files in this data contain a manual delineation by a radiation oncologist of the 3D volume of the primary gross tumor volume ("GTV-1").
For viewing quickly we recommend Dicompyler (http://www.dicompyler.com/) which is an open source, cross-platform DICOM RT viewer. Slicer has a SlicerRT module (http://slicerrt.github.io/index.html) which enables use of this kind of data. The Radiotherapy DICOM toolkit may also be useful for working with this data (https://github.com/dicom/rtkit).
Corresponding clinical data can be found here: Lung1.clinical.csv.
Please note that survival time is measured in days from start of treatment. DICOM patients names are identical in TCIA and clinical data file.
Citations & Data Usage Policy
Users of this data must abide by the Creative Commons Attribution-NonCommercial 3.0 Unported License under which it has been published. Attribution should include references to the following citations:
Aerts, H. J. W. L., Wee, L., Rios Velazquez, E., Leijenaar, R. T. H., Parmar, C., Grossmann, P., … Lambin, P. (2019). Data From NSCLC-Radiomics [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/K9/TCIA.2015.PF0M9REI
Aerts, H. J. W. L., Velazquez, E. R., Leijenaar, R. T. H., Parmar, C., Grossmann, P., Cavalho, S., … Lambin, P. (2014, June 3). Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nature Communications. Nature Publishing Group. http://doi.org/10.1038/ncomms5006 (link)
Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, Moore S, Phillips S, Maffitt D, Pringle M, Tarbox L, Prior F. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository, Journal of Digital Imaging, Volume 26, Number 6, December, 2013, pp 1045-1057. (paper)
Questions may be directed to firstname.lastname@example.org.
Other Publications Using This Data
Version 3 (Current): Updated 2019/10/23
- Re-checked and updated the RTSTRUCT files to amend issues in the previous submission due to missing RTSTRUCTS or regions of interest that were not vertically aligned with the patient image.
- In 4 cases (LUNG1-083,LUNG1-095,LUNG1-137,LUNG1-246) re-submitted the correct CT images.
- The regions of interest now include the primary lung tumor labelled as “GTV-1”, as well as organs at risk.
- For one case (LUNG1-128) the subject does not have GTV-1 because it was actually a post-operative case; we retained the CT scan here for completeness.
- Added DICOM SEGMENTATION objects to the collection, which makes it easier to search and retrieve the GTV-1 binary mask for re-use in quantitative imaging research.
- Clinical data updated as follow-up time has been extended.
Version 2: Updated 2016/05/31
Added 318 RTSTRUCT files for existing subject imaging data