This study aimed to build a reliable radiomics model from magnetic resonance imaging (MRI) for pretreatment prediction of MGMT methylation status in Glioblastoma. High-throughput radiomics features were automatically extracted from multiparametric MRI, including location features, geometry features, intensity features and texture features. A machine learning method was used to select a minimal set of all-relevant features. Based on these selected features, a radiomics model were built by using a random forest classifier for MGMT methylation prediction from a primary cohort (133 patients) and tested on an independent validation cohort (60 patients). Predictive models combing radiomics features and clinical factors were built and evaluated. The radiomics model with 6 all-relevant features allowed pretreatment prediction of MGMT methylation (AUC = 0.88, accuracy = 80%). Combing clinical factors with radiomics features did not benefit the prediction performance. The proposed radiomics model could provide a tool to guide preoperative patient care and made a step forward radiomics-based precision medicine for GBM patients.
CITATION STYLE
Li, Z. C., Chen, Y., Sun, Q., Li, Q., Liu, L., Luo, R., … Liang, C. (2019). Multiregional radiomics phenotypes at MR imaging predict MGMT promoter methylation in glioblastoma. In IFMBE Proceedings (Vol. 68, pp. 143–146). Springer Verlag. https://doi.org/10.1007/978-981-10-9035-6_25
Mendeley helps you to discover research relevant for your work.