Accession Number : AD1048797

Title :   Noninvasive Characterization of Indeterminate Pulmonary Nodules Detected on Chest High-Resolution Computed Tomography

Descriptive Note : Technical Report,30 Sep 2016,29 Sep 2017

Corporate Author : Vanderbilt University Medical Center Nashville United States

Personal Author(s) : Maldonado, Fabien

Full Text :

Report Date : 01 Oct 2017

Pagination or Media Count : 31

Abstract : Purpose: In the National Lung Screening Trial (NLST), indeterminate pulmonary nodules were detected in 40% of high-risk individuals screened by low dose high-resolution computed tomography (HRCT). However, 96% of these nodules were benign, indicating that false positive findings represent a major challenge for the clinical adoption of CT-based lung cancer screening. While current clinical-radiological risk prediction models are very valuable, optimization of the clinicalmanagement strategies for larger ( 7 mm) screen-detected nodules is needed to avoid unnecessary diagnostic interventions including futile thoracotomies. In this project, we explore the utility of a novel radiomics-based approach for the classification of screen-detected indeterminate nodules. Material and methods: Independent quantitative variables assessing various radiologic nodule features such as sphericity, flatness, elongation, spiculation, lobulation and curvature were developed from the NLST dataset (using all 726 nodules 7 mm; benign, n=318 and malignant, n=408). Multivariate analysis was performed using least absolute shrinkage and selection operator (LASSO) method for variable selection and regularization in order to enhance the prediction accuracy and interpretability of the multivariate model. To increase the stability of the modeling, LASSO was run 1,000 times and the variables that were selected in at least 50% of the runs were included into the final multivariate model. The bootstrapping method was then applied for the internal validation and the optimism-corrected AUC was reported for the final model (model 1: radiologic model). Relevant clinical variables (patient age and smoking history in pack-years) were then added to the model in an attempt to improve its diagnostic test characteristics (model 2: clinical-radiologic model).

Descriptors :   carcinoma , high resolution , Computerized Tomography , lung , cancer screening , biological markers , multivariate analysis , radiology

Subject Categories : Medicine and Medical Research
      Anatomy and Physiology
      Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE