Soft Tissue Sarcomas: Preoperative Predictive Histopathological Grading Based on Radiomics of MRI

Abstract

The purpose of this study is to develop a radiomics model for predicting the histopathological grades of soft tissue sarcomas preoperatively through magnetic resonance imaging (MRI). Thirty-five patients who were pathologically diagnosed with soft tissue sarcomas and their histological grades were recruited. All patients had undergone MRI before surgery on a 3.0T MRI scanner. Radiomics features were extracted from fat-suppressed T2-weighted imaging. We used the least absolute shrinkage and selection operator (LASSO) regression method to select features. Then three machine learning classification methods, including random forests, k-nearest neighbor, and support vector machine algorithm were trained using the 5-fold cross validation strategy to separate the soft tissue sarcomas with low- and high-histopathological grades. The radiomics features were significantly associated with the histopathological grades. Quantitative imaging features (n = 1049) were extracted from fat-suppressed T2-weighted imaging, and five features were selected to construct the radiomics model. The model that used support vector machine classification method achieved the best performance among the three methods, with areas under the receiver operating characteristic curves Area Under Curve (AUC) values of 0.92 ± 0.07, accuracy of 0.88. Good accuracy and AUC could be obtained using only five radiomic features. Therefore, we proposed that three-dimensional imaging features from fat-suppressed T2-weighted imaging could be used as candidate biomarkers for preoperative prediction of histopathological grades of soft tissue sarcomas noninvasively.