• B Feng, X Chen, Y Chen, Z Li, Y Hao, C Zhang, R Li, Y Liao, X Zhang, Y Huang, and W Long.
• The Department of Radiology, The Affiliated Jiangmen Hospital of Sun Yat-sen University, Jiangmen City, Guangdong Province, China; School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin City, Guangxi Province, China.
• Clin Radiol. 2019 Jul 1; 74 (7): 570.e1-570.e11.

AimTo evaluate the preoperative differentiation between the minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC) in patients with sub-solid pulmonary nodules using a radiomics nomogram.Materials And MethodsA total of 100 patients with sub-solid pulmonary nodules who had pathologically confirmed MIA (43 patients, 13 male and 30 female) or IAC (57 patients, 26 male and 31 female) were recruited retrospectively. Radiomics features were extracted from computed tomography (CT) images. A radiomics signature was constructed by the least absolute shrinkage and selection operator (LASSO) algorithm. Solid presence, lesion size, shape regularity, and margins of pulmonary nodules were assessed to construct a subjective finding model. An integrated model of radiomics signatures and CT-based subjective findings, which was presented as a radiomics nomogram, was developed based on a multivariate logistic regression. The nomogram performance was assessed by its calibration, discrimination, and clinical usefulness.ResultsThe radiomics signature, which consisted of 11 radiomics features, showed good discrimination accuracy. The radiomics nomogram showed good calibration and discrimination in the training set (AUC [area under the curve] 0.943; 95% confidence interval [CI]: 0.895-0.991) and validation set (AUC 0.912; 95% CI: 0.780-1.000). The radiomics nomogram was determined to be clinically useful in the decision curve analysis (DCA).ConclusionThe proposed radiomics nomogram has the potential to preoperatively differentiate MIA and IAC in patients with sub-solid pulmonary nodules.Copyright © 2019 The Royal College of Radiologists. Published by Elsevier Ltd. All rights reserved.

27 keywords...

hide…