Predicting Malignant Nodules from Screening CT Scans

• Published in: Journal of thoracic oncology Vol. 11; no. 12; pp. 2120 - 2128
• Main Authors: Hawkins, Samuel, Wang, Hua, Liu, Ying, Garcia, Alberto, Stringfield, Olya, Krewer, Henry, Li, Qian, Cherezov, Dmitry, Gatenby, Robert A., Balagurunathan, Yoganand, Goldgof, Dmitry, Schabath, Matthew B., Hall, Lawrence, Gillies, Robert J.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.12.2016; Copyright by the International Association for the Study of Lung Cancer
• Subjects: Aged; Computed tomography; Early Detection of Cancer - methods; Female; Humans; Lung cancer; Lung Neoplasms - diagnosis; Lung Neoplasms - diagnostic imaging; Lung Neoplasms - pathology; Machine learning; Male; Mass Screening - methods; Middle Aged; Prediction; Radiomics; Screening; Tomography, X-Ray Computed - methods; Screening; Computed tomography; Lung cancer; Prediction; Machine learning; Radiomics
• ISSN: 1556-0864; 1556-1380; 1556-1380
• DOI: 10.1016/j.jtho.2016.07.002

The aim of this study was to determine whether quantitative analyses (“radiomics”) of low-dose computed tomography lung cancer screening images at baseline can predict subsequent emergence of cancer. Public data from the National Lung Screening Trial (ACRIN 6684) were assembled into two cohorts of 104 and 92 patients with screen-detected lung cancer and then matched with cohorts of 208 and 196 screening subjects with benign pulmonary nodules. Image features were extracted from each nodule and used to predict the subsequent emergence of cancer. The best models used 23 stable features in a random forests classifier and could predict nodules that would become cancerous 1 and 2 years hence with accuracies of 80% (area under the curve 0.83) and 79% (area under the curve 0.75), respectively. Radiomics outperformed the Lung Imaging Reporting and Data System and volume-only approaches. The performance of the McWilliams risk assessment model was commensurate. The radiomics of lung cancer screening computed tomography scans at baseline can be used to assess risk for development of cancer.