BACKGROUND: Astrocytoma is the most common neuroepithelial neoplasm, and its grading greatly affects treatment and prognosis. OBJECTIVE: According to relevant factors of astrocytoma, this study developed a support vector machine (SVM) model to predict the astrocytoma grades and compared the SVM prediction with the clinician's diagnostic performance. PATIENTS AND METHODS: Patients were recruited from a cohort of astrocytoma patients in our hospital between January 2008 and April 2009. Among all astrocytoma patients, nine had grade I, 25 had grade II, 12 had grade III, and 60 had grade IV astrocytoma. An SVM model was constructed using radial basis kernel. The SVM model was trained with nine magnetic resonance (MR) features and one clinical parameter by fivefold cross-validation and differentiated astrocytomas of grades I-IV at two levels, respectively. The clinician also predicted the grade of astrocytoma. According to the two prediction methods above, the areas under receiving operating characteristics (ROC) curves to discriminate low- and high-grade groups, accuracies of high-grade grouping, overall accuracy, and overall kappa values were compared. RESULTS: For SVM, the overall accuracy was 0.821 and the overall kappa value was 0.679; for clinicians, the overall accuracy was 0.651 and the overall kappa value was 0.466. The diagnostic performance of SVM is significantly better than clinician performance, with the exception of the low-grade group. CONCLUSIONS: The SVM model can provide useful information to help clinicians improve diagnostic performance when predicting astrocytoma grade based on MR images.
BACKGROUND:Astrocytoma is the most common neuroepithelial neoplasm, and its grading greatly affects treatment and prognosis. OBJECTIVE: According to relevant factors of astrocytoma, this study developed a support vector machine (SVM) model to predict the astrocytoma grades and compared the SVM prediction with the clinician's diagnostic performance. PATIENTS AND METHODS: Patients were recruited from a cohort of astrocytomapatients in our hospital between January 2008 and April 2009. Among all astrocytomapatients, nine had grade I, 25 had grade II, 12 had grade III, and 60 had grade IV astrocytoma. An SVM model was constructed using radial basis kernel. The SVM model was trained with nine magnetic resonance (MR) features and one clinical parameter by fivefold cross-validation and differentiated astrocytomas of grades I-IV at two levels, respectively. The clinician also predicted the grade of astrocytoma. According to the two prediction methods above, the areas under receiving operating characteristics (ROC) curves to discriminate low- and high-grade groups, accuracies of high-grade grouping, overall accuracy, and overall kappa values were compared. RESULTS: For SVM, the overall accuracy was 0.821 and the overall kappa value was 0.679; for clinicians, the overall accuracy was 0.651 and the overall kappa value was 0.466. The diagnostic performance of SVM is significantly better than clinician performance, with the exception of the low-grade group. CONCLUSIONS: The SVM model can provide useful information to help clinicians improve diagnostic performance when predicting astrocytoma grade based on MR images.