 The study explores the application of deep learning in medical imaging for the automated quantification of radiographic characteristics, which may improve patient stratification for non-small cell lung cancer, NSCLC, patients. The study used an integrative analysis on seven independent datasets across five institutions totaling 1,194 NSCLC patients. The researchers identified prognostic signatures using a 3D convolutional neural network, CNN, for patients treated with radiotherapy and surgery. They found that the CNN predictions were significantly associated with two-year overall survival from the start of respective treatment for radiotherapy and surgery patients, and the CNN was able to significantly stratify patients into low and high mortality risk groups in both the radiotherapy and surgery datasets. The study also demonstrated the high robustness of the CNN against test retest, intra-class correlation coefficient, and inter-reader, Spearman's rank order correlation, variations. Additionally, the researchers identified regions with the most contribution towards predictions and highlighted the importance of tumor surrounding tissue in patient stratification. The study provides evidence that deep learning networks may be used for mortality risk stratification based on standard of care CT images from NSCLC patients, motivating future research into better deciphering the clinical and biological basis of deep learning networks as well as validation in prospective data. However, the study has limitations such as its retrospective nature and the opaque black box nature of deep. This article was authored by Ahmed Hosni, Chintan Parmer, Thibauti Korler, and others. We are article.tv, links in the description below.