Hong Lu,1,2 Jongphil Kim,3 Jin Qi,1,2 Qian Li,1 Ying Liu,1 Matthew B Schabath,4 Zhaoxiang Ye,1 Robert J Gillies,2 Yoganand Balagurunathan2,5 1Department of Radiology, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin, People’s Republic of China; 2Department of Cancer Physiology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, USA; 3Department of Biostatistics and Bioinformatics, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, USA; 4Department of Cancer Epidemiology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, USA; 5Department of Machine Language, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, USACorrespondence: Yoganand Balagurunathan; Robert J GilliesH. Lee Moffitt Cancer Center and Research Institute, 12902 Magnolia Drive, Tampa, FL 33612, USAEmail Yoganand.Balagurunathan@moffitt.org; Robert.Gillies@moffitt.orgRationale and Objectives: Evaluate ability of radiological semantic traits assessed on multi-window computed tomography (CT) to predict lung cancer risk.Materials and Methods: A total of 199 participants were investigated, including 60 incident lung cancers and 139 benign positive controls. Twenty lung window features and 2 mediastinal window features were extracted and scored on a point scale in three screening rounds. Multivariate logistic regression analysis was used to explore the association of these radiological traits with the risk of developing lung cancer. The areas under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and positive predictive value (PPV) were computed to evaluate the best predictive model.Results: Combining mediastinal window-specific features with the lung window features-based model significantly improves performance compared to individual window features. Model performance is consistent both at baseline and the first follow-up scan, with an AUROC increased from 0.822 to 0.871 (p = 0.009) and from 0.877 to 0.917 (p = 0.008), respectively, for single to multi-window feature models. We also find that the multi-window CT based model showed better specificity and PPV, with PPV at the second follow-up scan improved to 0.953.Conclusion: We find combining window semantic features improves model performance in identifying cancerous nodules. We also find that lung window features are more informative compared to mediastinal features in predicting malignancy.Keywords: multi-window, radiological, CT, lung cancer, screening
