Preoperative MRI-radiomics features improve prediction of survival in glioblastoma patients over MGMT methylation status alone

Abstract

BackgroundGlioblastoma (GBM) is the most common malignant central nervous system tumor, and MGMT promoter hypermethylation in this tumor has been shown to be associated with better prognosis. We evaluated the capacity of radiomics features to add complementary information to MGMT status, to improve the ability to predict prognosis.Methods159 patients with untreated GBM were included in this study and divided into training and independent test sets. 286 radiomics features were extracted from the magnetic resonance images acquired prior to any treatments. A least absolute shrinkage selection operator (LASSO) selection followed by Kaplan-Meier analysis was used to determine the prognostic value of radiomics features to predict overall survival (OS). The combination of MGMT status with radiomics was also investigated and all results were validated on the independent test set.ResultsLASSO analysis identified 8 out of the 286 radiomic features to be relevant which were then used for determining association to OS. One feature (edge descriptor) remained significant on the external validation cohort after multiple testing (p=0.04) and the combination with MGMT identified a group of patients with the best prognosis with a survival probability of 0.61 after 43 months (p=0.0005).ConclusionOur results suggest that combining radiomics with MGMT is more accurate in stratifying patients into groups of different survival risks when compared to with using these predictors in isolation. We identified two subgroups within patients who have methylated MGMT: one with a similar survival to unmethylated MGMT patients and the other with a significantly longer OS.

Reliability of tumor segmentation in glioblastoma: Impact on the robustness of MRI‐radiomic features

“…The segmentation was generated from FLAIR images and the segmented volumes were then utilized on T1WI CE . We chose to segment on FLAIR because we found that the inclusion of the FLAIR hyperintense tumoral and peritumoral lesion (usually larger than the contrast enhanced lesion) helps the radiomic features quantify the strength of tumor edges on T1WI CE . Moreover, texture matrices used for the extraction of radiomic features were computed using the 3DVOI as is commonly done with PET/CT images.…”

“…For instance, skewness of the Gabor edge maps was found to have a very low robustness in this study. Yet in a previous study, high negative skewness of Gabor edges was identified as a biomarker to differentiate patients with GBM by survival, and with a threshold of −0.49 it misclassified only <3% of the patients in this study, using I MC segmentation. Similarly, high robustness should not be used as a criterion to select features.…”

“…We chose to segment on FLAIR because we found that the inclusion of the FLAIR hyperintense tumoral and peritumoral lesion (usually larger than the contrast enhanced lesion) helps the radiomic features quantify the strength of tumor edges on T1WI CE . 11 Moreover, texture matrices used for the extraction of radiomic features were computed using the 3DVOI as is commonly done with PET/CT images. In our study, we identified that the I MC segmentation method led to more robust features compared with the semiautomatic method.…”

“…All investigated features were obtained using the CERR software, which is compliant with the Image Biomarkers Standardization Initiative (IBSI) . The choice of the investigated features was made using the most common radiomic feature categories and based on features that we used in a previous GBM study …”

“…1,[4][5][6] Recently, there has been an increased interest in performing radiomic studies using MR images. [7][8][9][10][11][12][13] Using radiomics with MRI is favorable for some tumor types, such as brain tumors, for which MRI is the standard-of-care imaging modality. Also, MRI provides unique characteristics that differ from PET or CT features, providing additional information for prognostication and outcome prediction.…”