The value of CT radiomic in differentiating mycoplasma pneumoniae pneumonia from streptococcus pneumoniae pneumonia with similar consolidation in children under 5 years

Abstract

Objective: To investigate the value of CT radiomics in the differentiation of mycoplasma pneumoniae pneumonia (MPP) from streptococcus pneumoniae pneumonia (SPP) with similar CT manifestations in children under 5 years.

Methods: A total of 102 children with MPP (n = 52) or SPP (n = 50) with similar consolidation and surrounding halo on CT images in Qilu Hospital and Qilu Children's Hospital between January 2017 and March 2022 were enrolled in the retrospective study. Radiomic features of the both lesions on plain CT images were extracted including the consolidation part of the pneumonia or both consolidation and surrounding halo area which were respectively delineated at region of interest (ROI) areas on the maximum axial image. The training cohort (n = 71) and the validation cohort (n = 31) were established by stratified random sampling at a ratio of 7:3. By means of variance threshold, the effective radiomics features, SelectKBest and least absolute shrinkage and selection operator (LASSO) regression method were employed for feature selection and combined to calculate the radiomics score (Rad-score). Six classifiers, including k-nearest neighbor (KNN), support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), logistic regression (LR), and decision tree (DT) were used to construct the models based on radiomic features. The diagnostic performance of these models and the radiomic nomogram was estimated and compared using the area under the receiver operating characteristic (ROC) curve (AUC), and the decision curve analysis (DCA) was used to evaluate which model achieved the most net benefit.

Results: RF outperformed other classifiers and was selected as the backbone in the classifier with the consolidation + the surrounding halo was taken as ROI to differentiate MPP from SPP in validation cohort. The AUC value of MPP in validation cohort was 0.822, the sensitivity and specificity were 0.81 and 0.81, respectively.

Conclusion: The RF model has the best classification efficiency in the identification of MPP from SPP in children, and the ROI with both consolidation and surrounding halo is most suitable for the delineation.

Keywords: CT radiomics; mycoplasma pneumoniae pneumonia; nomogram; pneumonia; streptococcus pneumoniae pneumonia.

FIGURE 1

Flowchart of the whole radiomics study.

FIGURE 2

Manual delineation on lung window CT images in a 25-month female patient with mycoplasma pneumoniae pneumonia (A,B) and a 21-month male patient with streptococcus pneumoniae pneumonia (C,D). CT shows the similar appearances with consolidation and surrounding halo in middle lobe of right lung (A,C), and two ROIs (blue line and orange line) are delineated in each patient.

FIGURE 3

Workflow model construction and radiomics analysis. (A) A variance threshold on feature select. The blue bar represents the number of all the extracted radiomics features, and the pink bar represents the number of radiomics features screened by variance threshold method. The vertical axis is 15 kinds of filtering methods (variance threshold = 0.8). (B) SelectKBest on feature select. The abscissa is the P-value of the feature, and the ordinate is the feature whose P value < 0.05 is screened by SelectKBest method. (C–E) Schematic diagram of feature screening by Lasso method: (C) Lasso path, where the abscissa is the log value of α, and the ordinate is the coefficient of the feature. (D) The abscissa of the MSE path is the log value of α, and the ordinate is the mean square error. (E) Regression coefficient of Lasso model, where the abscissa represents the regression coefficient and the ordinate represents the selected features. (F) ROC curve of the RF model. Yellow curve is MPP cohort, blue curve is SPP cohort.

FIGURE 4

(A) The radiomic nomogram was built on the training group with the rad-score. (B) The calibration curve in the training cohort. (C) The decision curve analysis (DCA) curve of the radiomic nomogram in the training cohort.