Prediction of TERTp-mutation status in IDH-wildtype high-grade gliomas using pre-treatment dynamic [18F]FET PET radiomics

Abstract

Purpose To evaluate radiomic features extracted from standard static images (20–40 min p.i.), early summation images (5–15 min p.i.), and dynamic [18F]FET PET images for the prediction of TERTp-mutation status in patients with IDH-wildtype high-grade glioma. Methods A total of 159 patients (median age 60.2 years, range 19–82 years) with newly diagnosed IDH-wildtype diffuse astrocytic glioma (WHO grade III or IV) and dynamic [18F]FET PET prior to surgical intervention were enrolled and divided into a training (n = 112) and a testing cohort (n = 47) randomly. First-order, shape, and texture radiomic features were extracted from standard static (20–40 min summation images; TBR20–40), early static (5–15 min summation images; TBR5–15), and dynamic (time-to-peak; TTP) images, respectively. Recursive feature elimination was used for feature selection by 10-fold cross-validation in the training cohort after normalization, and logistic regression models were generated using the radiomic features extracted from each image to differentiate TERTp-mutation status. The areas under the ROC curve (AUC), accuracy, sensitivity, specificity, and positive and negative predictive value were calculated to illustrate diagnostic power in both the training and testing cohort. Results The TTP model comprised nine selected features and achieved highest predictability of TERTp-mutation with an AUC of 0.82 (95% confidence interval 0.71–0.92) and sensitivity of 92.1% in the independent testing cohort. Weak predictive capability was obtained in the TBR5–15 model, with an AUC of 0.61 (95% CI 0.42–0.80) in the testing cohort, while no predictive power was observed in the TBR20–40 model. Conclusions Radiomics based on TTP images extracted from dynamic [18F]FET PET can predict the TERTp-mutation status of IDH-wildtype diffuse astrocytic high-grade gliomas with high accuracy preoperatively.

Dynamic amino-acid PET in neuro-oncology: a prognostic tool becomes essential

“…The Li et al publication [31], in the current issue of EJN-MMI, confirms the high prognostic value of dynamic aminoacid PET parameters at the initial diagnosis by focusing on a specific molecular parameter included in the new cIMPACT-NOW future central nervous system tumour classification [32], the telomerase reverse transcriptase promoter (TERTp) mutation. TERTp mutations in IDH-wildtype gliomas are reported to be associated with poor overall survival [33].…”

“…Instead of using volumes of interest to extract dynamic parameters of the tumour area, these authors use a voxel-wise analysis. They report that TTP dynamic parametric images non-invasively predict TERTp mutations with an accuracy of 85% [31]. This foreshadows the novel insights that could be applied to further develop the promise of dynamic acquisitions.…”

“…TERTp mutations in IDH-wildtype gliomas are reported to be associated with poor overall survival [33]. In addition to confirming the prognostic value of dynamic PET acquisitions, Li et al also provide a novel approach for studying dynamic parameters [31]. Instead of using volumes of interest to extract dynamic parameters of the tumour area, these authors use a voxel-wise analysis.…”

“…But the Li et al study differs from these previous investigations because it evaluates the textural features of TTP parametric images, i.e. by attributing one value of TTP per voxel in the tumour area [31]. This allows to evaluate the heterogeneity of dynamic images and is a similar approach to that used to investigate textural features in static images [18,19], i.e.…”

“…The same authors previously reported no significant predictive value of dynamic parameters for identifying TERTp mutations in newly diagnosed gliomas by using an approach based on volume of interest [37]. Since almost all dynamic PET studies are based on a volume of interest approach, the latest Li et al study therefore paves the way to improve predictive performances more generally [31]. The voxel-wise analysis, however, requires kinetic parameters to be fitted, which necessitates long computation times and increases the impact of data noise.…”