Background: This study aimed to evaluate the significance of MRI-based radiomics model derived from highresolution\nT2-weighted images (T2WIs) in predicting tumor pathological features of rectal cancer.\nMethods: A total of 152 patients with rectal cancer who underwent surgery without any neoadjuvant therapy\nbetween March 2017 and September 2018 were included retrospectively. The patients were scanned using a 3-T\nmagnetic resonance imaging, and high-resolution T2WIs were obtained. Lesions were delineated, and 1029\nradiomics features were extracted. Least absolute shrinkage and selection operator was used to select features, and\nmultilayer perceptron (MLP), logistic regression (LR), support vector machine (SVM), decision tree (DT), random\nforest (RF), and K-nearest neighbor (KNN) were trained using fivefold cross-validation to build a prediction model.\nThe diagnostic performance of the prediction models was assessed using the receiver operating characteristic\ncurves.\nResults: A total of 1029 features were extracted, and 15, 11, and 11 features were selected to predict the degree of\ndifferentiation, T stage, and N stage, respectively. The best performance of the radiomics model for the degree of\ndifferentiation, T stage, and N stage was obtained by SVM [area under the curve (AUC), 0.862; 95% confidence\ninterval (CI), 0.750â??0.967; sensitivity, 83.3%; specificity, 85.0%], MLP (AUC, 0.809; 95% CI, 0.690â??0.905; sensitivity,\n76.2%; specificity, 74.1%), and RF (AUC, 0.746; 95% CI, 0.622-0.872; sensitivity, 79.3%; specificity, 72.2%).\nConclusion: This study demonstrated that the high-resolution T2WIâ??based radiomics model could serve as\npretreatment biomarkers in predicting pathological features of rectal cancer.
Loading....