Machine Learning-Based MRI Texture Analysis to Predict the Histologic Grade of Oral Squamous Cell Carcinoma

OBJECTIVE. This study aimed to explore the performance of machine learning (ML)-based MRI texture analysis in discriminating between well-differentiated (WD) oral squamous cell carcinoma (OSCC) and moderately or poorly differentiated OSCC. MATERIALS AND METHODS. The study enrolled 80 patients with pathologically confirmed OSCC (18 WD OSCCs and 62 moderately or poorly differentiated OSCCs) who underwent pretreatment MRI. ROIs were manually delineated to cover the entire tumor to the greatest possible extent on T2-weighted imaging and contrast-enhanced T1-weighted imaging, and 1118 texture features were extracted. Dimension reduction was performed using reproducibility analysis by two radiologists, collinearity analysis, and feature selection with a minimum-redundancy maximum-relevance algorithm. Models were created using random forest (RF), artificial neural network, and logistic regression (LR) alone and with a synthetic minority oversampling technique (SMOTE). Classifier performance was assessed using 10-fold cross-validation. RESULTS. Dimension reduction steps yielded eight texture features, including four features from each sequence. None of the clinical variables was selected. Among the eight texture features, five and seven texture features showed significant differences between the two groups in the actual data and balanced data, respectively (p < 0.05). All classifiers with SMOTE achieved better performances than those alone. The RF classifier with SMOTE achieved the best performance with an area under the ROC curve of 0.936 and accuracy of 86.3%. CONCLUSION. ML-based MRI texture analysis provides a promising noninvasive approach for predicting the histologic grade of OSCC.