Search

Objectives: To evaluate the methodological quality and diagnostic accuracy of MRI-based radiomic studies predicting O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status in gliomas. Methods: PubMed Medline, EMBASE, and Web of Science were searched to identify MRI-based radiomic studies on MGMT methylation in gliomas published until December 31, 2022. Three raters evaluated the study methodological quality with Radiomics Quality Score (RQS, 16 components) and Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis Or Diagnosis (TRIPOD, 22 items) scales. Risk of bias and applicability concerns were assessed with QUADAS-2 tool. A meta-analysis was performed to estimate the pooled area under the curve (AUC) and to assess inter-study heterogeneity. Results: We included 26 studies, published from 2016. The median RQS total score was 8 out of 36 (22%, range 8–44%). Thirteen studies performed external validation. All studies reported AUC or accuracy, but only 4 (15%) performed calibration and decision curve analysis. No studies performed phantom analysis, cost-effectiveness analysis, and prospective validation. The overall TRIPOD adherence score was between 50% and 70% in 16 studies and below 50% in 10 studies. The pooled AUC was 0.78 (95% CI, 0.73–0.83, I2 = 94.1%) with a high inter-study heterogeneity. Studies with external validation and including only WHO-grade IV gliomas had significantly lower AUC values (0.65; 95% CI, 0.57–0.73, p < 0.01). Conclusions: Study RQS and adherence to TRIPOD guidelines was generally low. Radiomic prediction of MGMT methylation status showed great heterogeneity of results and lower performances in grade IV gliomas, which hinders its current implementation in clinical practice. Clinical relevance statement: MGMT promoter methylation status appears to be variably correlated with MRI radiomic features; radiomic models are not sufficiently robust to be integrated into clinical practice to accurately predict MGMT promoter methylation status in patients with glioma before surgery. Key Points: • Adherence to the indications of TRIPOD guidelines was generally low, as was RQS total score. • MGMT promoter methylation status prediction with MRI radiomic features provided heterogeneous diagnostic accuracy results across studies. • Studies that included grade IV glioma only and performed external validation had significantly lower diagnostic accuracy than others. [ABSTRACT FROM AUTHOR]

The methylation of the O6-methylguanine-DNA methyltransferase (MGMT) promoter is a molecular marker associated with a better response to chemotherapy in patients with glioblastoma (GB). Standard pre-operative magnetic resonance imaging (MRI) analysis is not adequate to detect MGMT promoter methylation. This study aims to evaluate whether the radiomic features extracted from multiple tumor subregions using multiparametric MRI can predict MGMT promoter methylation status in GB patients. This retrospective single-institution study included a cohort of 277 GB patients whose 3D post-contrast T1-weighted images and 3D fluid-attenuated inversion recovery (FLAIR) images were acquired using two MRI scanners. Three separate regions of interest (ROIs) showing tumor enhancement, necrosis, and FLAIR hyperintensities were manually segmented for each patient. Two machine learning algorithms (support vector machine (SVM) and random forest) were built for MGMT promoter methylation prediction from a training cohort (196 patients) and tested on a separate validation cohort (81 patients), based on a set of automatically selected radiomic features, with and without demographic variables (i.e., patients' age and sex). In the training set, SVM based on the selected radiomic features of the three separate ROIs achieved the best performances, with an average of 83.0% (standard deviation: 5.7%) for accuracy and 0.894 (0.056) for the area under the curve (AUC) computed through cross-validation. In the test set, all classification performances dropped: the best was obtained by SVM based on the selected features extracted from the whole tumor lesion constructed by merging the three ROIs, with 64.2% (95% confidence interval: 52.8–74.6%) accuracy and 0.572 (0.439–0.705) for AUC. The performances did not change when the patients' age and sex were included with the radiomic features into the models. Our study confirms the presence of a subtle association between imaging characteristics and MGMT promoter methylation status. However, further verification of the strength of this association is needed, as the low diagnostic performance obtained in this validation cohort is not sufficiently robust to allow clinically meaningful predictions. [ABSTRACT FROM AUTHOR]

Purpose: to predict vestibular schwannoma (VS) response to radiosurgery by applying machine learning (ML) algorithms on radiomic features extracted from pre-treatment magnetic resonance (MR) images. Methods: patients with VS treated with radiosurgery in two Centers from 2004 to 2016 were retrospectively evaluated. Brain T1-weighted contrast-enhanced MR images were acquired before and at 24 and 36 months after treatment. Clinical and treatment data were collected contextually. Treatment responses were assessed considering the VS volume variation based on pre- and post-radiosurgery MR images at both time points. Tumors were semi-automatically segmented and radiomic features were extracted. Four ML algorithms (Random Forest, Support Vector Machine, Neural Network, and extreme Gradient Boosting) were trained and tested for treatment response (i.e., increased or non-increased tumor volume) using nested cross-validation. For training, feature selection was performed using the Least Absolute Shrinkage and Selection Operator, and the selected features were used as input to separately build the four ML classification algorithms. To overcome class imbalance during training, Synthetic Minority Oversampling Technique was used. Finally, trained models were tested on the corresponding held out set of patients to evaluate balanced accuracy, sensitivity, and specificity. Results: 108 patients treated with Cyberknife® were retrieved; an increased tumor volume was observed at 24 months in 12 patients, and at 36 months in another group of 12 patients. The Neural Network was the best predictive algorithm for response at 24 (balanced accuracy 73% ± 18%, specificity 85% ± 12%, sensitivity 60% ± 42%) and 36 months (balanced accuracy 65% ± 12%, specificity 83% ± 9%, sensitivity 47% ± 27%). Conclusions: radiomics may predict VS response to radiosurgery avoiding long-term follow-up as well as unnecessary treatment. [ABSTRACT FROM AUTHOR]

Materials: Patients with acoustic neuroma and treated with radiosurgery (12Gy/1 fraction or 18Gy/3 fractions) in our two institutes from 2004 to 2016 were retrospectively evaluated. Inclusion criteria were having contrastenhanced T1-weighted MR images available before and at 24 and 36 months after treatment. Clinical, audiometric and treatment data were collected at the same time points. Lesions were classified as stable, reduced or increased according to the volume variation assessed on the preand post-radiosurgery MR images. Tumours were semiautomatically segmented on the pre-treatment MR images using the level tracing effect of the 3DSlicer software. Pretreatment images were pre-processed in three steps: i) uniformity correction; ii) deskulling to isolate brain voxels; iii) Z-score transformation to standardize voxel intensities within the brain. For each patient 851 radiomic features were extracted on the 3D segmented regions from the processed images and after wavelet transformation, using PyRadiomics. We trained and tested ML methods to predict the lesion increase at 24 and, separately, 36 months after radiosurgery, using a nested cross-validation (CV) scheme (outer loop: 5 folds; inner loop: 3 folds). On the training set of each outer loop feature selection was performed using Least Absolute Shrinkage Selector Operator (LASSO) and the selected features were used as input to separately build four ML classification methods. Parameters oLASSO and ML methods were tuned in the inner loops. To overcome class imbalance during training Synthetic Minority Oversampling Technique (SMOTE) was used. Finally trained models were tested on the corresponding held-out patients in each outer loop to evaluate balanced accuracy, sensitivity and specificity. Results: We included 95 patients (age 62±12 years, 42 males [44%]) treated with Cyberknife® at our institutes. All results are summarized in Table 1. The Neural Network was the best algorithm for predicting the response at 24 months (average test set accuracy 71%, sensitivity 60%, specificity 82%) and 36 months (accuracy 66%, sensitivity 50%, specificity 83%). Features selected for each experiment are reported in Table 2. Conclusions: These preliminary results indicate that the proposed methods have great potential in distinguishing, before radiosurgery, patients with tumour volume increase from patients with stable or reduced lesions. Subsequent studies are ongoing to assess the robustness and reproducibility of these results. Radiomics-based ML methods may be useful for improving the management of patients with acoustic neuroma. [ABSTRACT FROM AUTHOR]