Stratified analysis showed that the performance was not affected by different scanners or slice thicknesses. DCA showed that the model would obtain more benefit when the threshold probability was between 30% and 90% in the test set. The Hosmer-Lemeshow test showed that the P value was > 0.05, indicating good calibration, and the calibration curves showed good agreement between the classifications and actual observations. Result: Among the six machine learning methods, the logistic regression model with the eight strongest features showed a significant association with mediastinal LN status and the satisfactory diagnostic performance for distinguishing malignant LNs from benign LNs. Stratified analysis was performed for different scanners and slice thicknesses. Decision curve analysis (DCA) was used to assess the clinical usefulness of the logistic regression model in both the training and test sets. Calibration curves and Hosmer-Lemeshow tests were used to assess the calibration degree. The performance of the model was assessed and compared to that of five other machine learning algorithms (support vector machine, naive Bayes, random forest, decision tree, K-nearest neighbor) using receiver operating characteristic (ROC) curves. A model was fitted to associate mediastinal LN malignancy with selected features. Multivariate logistic regression was performed with the backward stepwise elimination. Feature selection was performed with least absolute shrinkage and selection operator (LASSO) binary logistic regression. Radiomics features were extracted from the region of interest (ROI) delineated on venous-phase CT imaging of LN. Method: In total, 201 pathologically confirmed mediastinal LNs from 129 patients were enrolled and assigned to training and test sets. Purpose: To establish and validate a radiomics model to estimate the malignancy of mediastinal lymph nodes (LNs) based on contrast-enhanced CT imaging. 2Institute of Respiratory Disease, The First Affiliated Hospital of China Medical University, Shenyang, China.1Department of Radiology, The First Affiliated Hospital of China Medical University, Shenyang, China.Mengshi Dong 1, Gang Hou 2, Shu Li 1, Nan Li 1, Lina Zhang 1* and Ke Xu 1*
0 Comments
Leave a Reply. |