Radiation Oncologist Tumor Segmentations

The DICOM Radiotherapy Structure Sets (RTSTRUCT) and DICOM Segmentation (SEG) files in this data contain a manual delineation by a radiation oncologist of the 3D volume of the primary gross tumor volume (“GTV-1”) and selected anatomical structures (i.e., lung, heart and esophagus). Of note, DICOM SEG objects contain a subset of annotations available in RTSTRUCT.

For viewing the annotations the authors recommend 3D Slicer that can be used to view both RTSTRUCT and SEG annotations (make sure you install the SlicerRT and QuantitativeReporting extensions first!). Visualization of the DICOM annotations is also supported by the OHIF Viewer.

Other tools include:

• Dicompyler is an open source, cross-platform DICOM RT viewer.
• The Radiotherapy DICOM toolkit, which may also be useful for working with this data.
• dcmqi and Plastimatch libraries can be used to support conversion of the DICOM SEG and RTSTRUCT representations, respectively, into the popular research formats, such as NIfTI or NRRD.

Clinical Data

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.

The deadstatus.event follows the standard epidemiological / biomedical definition for time to event survival modelling whereby :

1 == “death has occurred at the time interval value stated on the next column”, hence

0 == “death has NOT occurred up until the time interval value stated in the next column, and is therefore right-censored”.

Note:

Some CT ( LUNG1-014 ,  LUNG1-021 ,  LUNG1-085)  are missing some slices from the complete volume, unfortunately not detected until recently. The skipped CT slice did not cut through the Gross Tumour Volume which was the principal focus of this Collection. We understand the user may have a different principal focus for re-using this collection, but perhaps some other workaround like interpolation may be timely and feasible for those affected volumes.

Publications by the Dataset Authors

The authors recommended this paper as the best source of additional information about this dataset:

• Aerts, H. J. W. L., Velazquez, E. R., Leijenaar, R. T. H., Parmar, C., Grossmann, P., Carvalho, S., Bussink, J., Monshouwer, R., Haibe-Kains, B., Rietveld, D., Hoebers, F., Rietbergen, M. M., Leemans, C. R., Dekker, A., Quackenbush, J., Gillies, R. J., Lambin, P. (2014, June 3). Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nature Communications. Nature Publishing Group. https://doi.org/10.1038/ncomms5006  (link)

No publications by dataset authors were found.

Research Community Publications

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

Version 3: 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. (NOTE: version 2 removed as RTSTRUCTs or regions of interest were not vertically aligned with patient images. See version 3 for updated files).

Version 1: Updated 2014/07/02