Development and Validation of a MRI-Based Radiomics Prognostic Classifier in Patients with Primary Glioblastoma Multiforme

Rationale and Objectives Glioblastoma multiforme (GBM) is the most common and deadly type of primary malignant tumor of the central nervous system. Accurate risk stratification is vital for a more personalized approach in GBM management. The purpose of this study is to develop and validate a MRI-based prognostic quantitative radiomics classifier in patients with newly diagnosed GBM and to evaluate whether the classifier allows stratification with improved accuracy over the clinical and qualitative imaging features risk models. Methods Clinical and MR imaging data of 127 GBM patients were obtained from the Cancer Genome Atlas and the Cancer Imaging Archive. Regions of interest corresponding to high signal intensity portions of tumor were drawn on postcontrast T1-weighted imaging (post-T1WI) on the 127 patients (allocated in a 2:1 ratio into a training [n = 85] or validation [n = 42] set), then 3824 radiomics features per patient were extracted. The dimension of these radiomics features were reduced using the minimum redundancy maximum relevance algorithm, then Cox proportional hazard regression model was used to build a radiomics classifier for predicting overall survival (OS). The value of the radiomics classifier beyond clinical (gender, age, Karnofsky performance status, radiation therapy, chemotherapy, and type of resection) and VASARI features for OS was assessed with multivariate Cox proportional hazards model. Time-dependent receiver operating characteristic curve analysis was used to assess the predictive accuracy. Results A classifier using four post-T1WI-MRI radiomics features built on the training dataset could successfully separate GBM patients into low- or high-risk group with a significantly different OS in training (HR, 6.307 [95% CI, 3.475-11.446]; p Conclusion A classifier using radiomics features allows preoperative prediction of survival and risk stratification of patients with GBM, and it shows improved performance compared to that of clinical and qualitative imaging features models.