A wavelet features derived radiomics nomogram for prediction of malignant and benign early-stage lung nodules

• DOI: 10.1038/s41598-021-01470-5
• Publication Date: 2021-11-16T11:06:37Z
• Authors: Rui Jing; Jingtao Wang; Jiangbing Li; Xiaojuan Wang; Baijie Li; Fuzhong Xue; Guangrui Shao; Hao Xue
• Keywords: Nomogram; Lasso

Abstract This study was to develop a radiomics nomogram mainly using wavelet features for identifying malignant and benign early-stage lung nodules high-risk screening. A total of 116 patients with solitary pulmonary (SPNs) (≤ 3 cm) were divided into training set (N = 70) validation 46). Radiomics extracted from plain LDCT images each patient. signature then constructed the LASSO set. Combined independent risk factors, built multivariate logistic regression model. signature, consisting one original nine features, achieved favorable predictive efficacy than Mayo Clinic Model. The age also showed good calibration discrimination in (AUC 0.9406; 95% CI 0.8831–0.9982) 0.8454; 0.7196–0.9712). decision curve indicated clinical usefulness our nomogram. presented shows accuracy is much better