AUTHOR=Yu Qiang , Wang Anran , Gu Jinming , Li Quanjiang , Ning Youquan , Peng Juan , Lv Fajin , Zhang Xiaodi 

TITLE=Multiphasic CT-Based Radiomics Analysis for the Differentiation of Benign and Malignant Parotid Tumors

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.913898

DOI=10.3389/fonc.2022.913898

ISSN=2234-943X

ABSTRACT=Abstract
Objective: To investigate the value of machine learning models based on clinic-radiological features and multiphasic CT radiomics features in the differentiation of benign parotid tumors (BPT) and malignant parotid tumors (MPT).
Methods: This retrospective study included 312 patients (205 cases of BPT and 107 cases of MPT) who underwent multiphasic enhanced CT examination, which were randomly divided into training (N=218) and test (N=94) sets. The radiomics features were extracted from plain, arterial and venous phase. The synthetic minority oversampling technique was used to balance minority class samples in the training set. Feature selection methods were done using least absolute shrinkage and selection operator (LASSO), mutual information (MI) and recursive feature extraction (RFE). Then, two machine learning classifiers, support vector machine (SVM) and logistic regression (LR), were combined in pairs with three feature selection methods to build different radiomics models. Meanwhile, the prediction performances of different radiomics models based on single-phase (plain, arterial and venous phase) and multi-phase (three-phase combination) were compared to determine which model construction method and phase was more discriminative. In addition, clinical models based on clinic-radiological features and combined models integrating radiomics features and clinic-radiological features were established. The prediction performances of the different models were evaluated by the area under the receiver operating characteristic (ROC) curve (AUC) and the drawing of calibration curves.
Results: Among the 24 established radiomics models composed of four different phases, three feature selection methods and two machine learning classifiers, the LASSO-SVM model based on three-phase combination had the optimal prediction performance with AUC(0.936 [95% CI = 0.866, 0.976]), sensitivity(0.78), specificity(0.90) and accuracy(0.86) in the test set, and its prediction performance was significantly better than with the clinical model LR (AUC = 0.781, P = 0.012). In the test set, the combined model based on LR had a lower AUC than the optimal radiomics model (AUC = 0.933 vs 0.936), but no statistically significant difference (P = 0.888).
Conclusion: Multiphasic CT-based radiomics analysis showed machine learning model based on clinic-radiological features and radiomics features has potential to provide a valuable tool for discriminating benign from malignant parotid tumors.