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.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords