Glioblastoma is characterized by its remarkable heterogeneity and dismal prognosis. Histogram features of MRI modality show potential in measuring the intratumoral heterogeneity. We integrate multi-parametric and multi-regional MRI histogram features to divide patients into groups and assess the relevance to treatment outcome. The results demonstrated that integrating multi-parametric and multi-regional MRI histogram features may help to stratify patients. The feature selected in this process also displayed prognostic values in the multivariate survival analysis. The histogram features selected from the proposed approach may be used as potential imaging markers in personalized treatment strategy and response determination.