10.1371/journal.pone.0196910.s001 Tobias Peikert Tobias Peikert Fenghai Duan Fenghai Duan Srinivasan Rajagopalan Srinivasan Rajagopalan Ronald A. Karwoski Ronald A. Karwoski Ryan Clay Ryan Clay Richard A. Robb Richard A. Robb Ziling Qin Ziling Qin JoRean Sicks JoRean Sicks Brian J. Bartholmai Brian J. Bartholmai Fabien Maldonado Fabien Maldonado S1 File - Public Library of Science 2018 screen-detected lung nodules NLST novel radiomics-based approach Minimum method 8 features SILA curvature novel radiomic LDCT-based approach LASSO multivariate modeling screen-detected nodule characterization surface National Lung Screening Trial Purpose Optimization flatness radiologic nodule features optimism-corrected AUC Average variable Maximum shape index analysis tomography-based radiomic classifier validation 2018-05-14 17:45:32 Journal contribution https://plos.figshare.com/articles/journal_contribution/Novel_high-resolution_computed_tomography-based_radiomic_classifier_for_screen-identified_pulmonary_nodules_in_the_National_Lung_Screening_Trial/6266501 <p><b>Figure A.</b> Analysis of the CALIPER texture features within the lung nodules. The texture features within the shaded region do not appear within the lung nodules.</p> <p><b>Figure B</b> Three dimensional scatter plot showing the pairwise Dice Similarity Coefficient (DSC) between the nodules segmented by the Radiologist (Rx), Pulmonologist (Px) and Image Analyst (IA).</p> <p><b>Table A</b> Algorithmic components of nodule surface characterization and the strategy used during the pilot study and current improvements.</p> <p><b>Table B.</b> List of quantitative metrics used in the discrimination of benign and malignant nodules. The pval, 95% CI and the probability plot correlation coefficient (PPCC) are given in the last column for benign (N = 319) and malignant (N = 338) nodules.</p> <p><b>Figure C</b> Mosaic showing the glyphs (<b>A</b>, <b>D</b>), the nodule distribution within the upper, middle, lower left and right lung (<b>B</b>, <b>E</b>) and the Score Indicative of Lesion Abnormality (SILA) for the NLST malignant and benign nodules used in this study. The glyphs are ordered in Panels <b>A</b> and <b>D</b> based on the nodule-specific SILA values; the SILA values in Panels <b>C</b> and <b>F</b> are color coded in green, yellow and red based on the previously developed CANARY categorization.</p> <p><b>Figure D</b> Three dimensional scatter plot showing the variations in the SILA (Score Indicative of Lung Abnormality) between the nodules segmented by 3 operators. Panels A and B respectively show the SILA values for the nodule texture and surface. The nodules (N = 266) described in section 2.2.1 were used for this analysis.</p> <p>(DOCX)</p>