The purpose of this work was to evaluate the relative contributions of MR contrasts to tumor tissue classification. Seventeen (17) glioma patient datasets (WHO grade II-IV) containing T1, T1+gad, T2, FLAIR, and ADC were studied using multinomial logistic regression. T2 images had the highest individual classification accuracy (78.1%). Classification accuracy improved with each additional contrast, leading to an overall accuracy of 84.1% for all 5 contrasts. The multinomial logistic regression showed that together the 5 contrasts had greater tumor tissue classification accuracy than individually, but that the improvement in accuracy was not linear and decreased as more MR data was included. Lower grade gliomas and GBM could be predicted by the percentage of voxels classified as suspicious by the regression model, but not by any other class. These results may aid in clinical protocol development and optimization for neuro-oncologic imaging, especially in situations where overall scan time is limited.