Background: Clinical TNM staging derived from computed tomography (CT) imaging is a key prognostic factor for lung cancer patients when making decisions about treatment, monitoring, and clinical trial eligibility. However, heterogeneity among patients, including by molecular subtypes, may result in variability of survival outcomes of patients with the same TNM stage that receive the same treatment. Artificial intelligence may offer additional, individualized prognostic information based on both known and unknown features present in CTs to facilitate more precise clinical decision making. We developed a novel deep learning-based technique to predict 2-year survival from pretreatment CTs of pathologically-confirmed lung cancer patients. Methods: A fully automated, end-to-end model was designed to localize the three-dimensional (3D) space comprising the lungs and heart, and to learn deep prognostic features using a 3D convolutional neural network (3DCNN). The 3DCNN was trained and validated using 1,841 CTs of 1,184 patients from five public datasets made available in The Cancer Imaging Archive. Spearman’s rank correlation (R) and concordance index (C-index) between the model output and survival status of each patient after 2-year follow-up from CT acquisition was assessed, in addition to sensitivity, specificity and accuracy stratified by staging. Results: 3DCNN showed an overall prediction accuracy of 75.0% (R = 0.32, C-index = 0.67, p < 0.0001), with higher performance achieved for stage I patients (Table) . 3DCNN showed better overall correlation with survival for 1,124 patients with available TNM staging, in comparison to TNM staging only (R = 0.19, C-index = 0.63, p < 0.0001); however, a weighted linear combination of both TNM staging and the 3DCNN yielded a superior correlation (R = 0.34, C-index = 0.73, p < 0.0001). Conclusions: Deep learning applied to pretreatment CT images provides personalized prognostic information that complements clinical staging and may help facilitate more precise prognostication of patients diagnosed with lung cancer.

*Includes 60 additional patients where staging was not available.