This dataset contains images from 31 out of the 32 non-small cell lung cancer (NSCLC) patients in the RIDER Lung CT collection on TCIA. For these subjects a radiation oncologist was blinded to the all delineations of the 3D volume of the gross tumor volume. They were then asked to manually delineate the gross tumour volume in both the test image and the re-test image. The process was repeated using an in-house autosegmentation method. There is no clinical outcome data associated with this dataset.

This dataset refers to the RIDER dataset of the study published in Nature Communications (http://doi.org/10.1038/ncomms5006). In short, this publication used the dataset to select for repeatable radiomics features in a test-retest context. Radiomics refers to the comprehensive quantification of tumour phenotypes by applying a large number of quantitative image features. In the published 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.