Background: Pediatric low-grade gliomas (PLGG) are the most frequent brain tumors in children. Up to 50% will be refractory to conventional chemotherapy. It is now known that the majority of PLGG have activation of the MAPK/ERK pathway. The same pathway is also activated in plexiform neurofibromas (PNs) which are low-grade tumors involving peripheral nerves in patients with neurofibromatosis type 1 (NF1). These lesions are known to be refractory to chemotherapy. Specific MEK inhibitors such as trametinib are now available and have been approved for other cancers harboring mutations in the MAPK/ERK pathway such as melanoma. We have observed significant responses to trametinib in patients with refractory PLGG in our institutions and results from the phase I study are promising. The treatment appears not only efficacious but is also usually well tolerated. We hypothesize that we will observe responses in the majority of refractory PLGG and PN treated with trametinib in this phase 2 study. Methods: The primary objective is to determine the objective response rate of trametinib as a single agent for treatment of progressing/refractory tumors with MAPK/ERK pathway activation. The TRAM-01 study is a phase II multicentric open-label basket trial including four groups. Group 1 includes NF1 patients with progressing/refractory glioma. Group 2 includes NF1 patients with plexiform neurofibroma. Group 3 includes patients with progressing/refractory glioma with KIAA1549-BRAF fusion. Group 4 includes other patients with progressing/refractory glioma with activation of the MAPK/ERK pathway. Eligible patients for a given study group will receive daily oral trametinib at full dose for a total of 18 cycles of 28 days. A total of 150 patients will be enrolled in seven Canadian centers. Secondary objectives include the assessment of progression-free survival, overall survival, safety and tolerability of trametinib, serum levels of trametinib and evaluation of quality of life during treatment. Discussion: Trametinib will allow us to target directly and specifically the MAPK/ERK pathway. We expect to observe a significant response in most patients. Following our study, trametinib could be integrated into standard treatment of PLGG and PN. Trial registration: ClinicalTrials.gov Identifier: NCT03363217 December 6, 2017.

BACKGROUND AND PURPOSE: Distinct molecular subgroups of pediatric medulloblastoma confer important differences in prognosis and therapy. Currently, tissue sampling is the only method to obtain information for classification. Our goal was to develop and validate radiomic and machine learning approaches for predicting molecular subgroups of pediatric medulloblastoma. MATERIALS AND METHODS: In this multi-institutional retrospective study, we evaluated MR imaging datasets of 109 pediatric patients with medulloblastoma from 3 children9s hospitals from January 2001 to January 2014. A computational framework was developed to extract MR imaging–based radiomic features from tumor segmentations, and we tested 2 predictive models: a double 10-fold cross-validation using a combined dataset consisting of all 3 patient cohorts and a 3-dataset cross-validation, in which training was performed on 2 cohorts and testing was performed on the third independent cohort. We used the Wilcoxon rank sum test for feature selection with assessment of area under the receiver operating characteristic curve to evaluate model performance. RESULTS: Of 590 MR imaging–derived radiomic features, including intensity-based histograms, tumor edge-sharpness, Gabor features, and local area integral invariant features, extracted from imaging-derived tumor segmentations, tumor edge-sharpness was most useful for predicting sonic hedgehog and group 4 tumors. Receiver operating characteristic analysis revealed superior performance of the double 10-fold cross-validation model for predicting sonic hedgehog, group 3, and group 4 tumors when using combined T1- and T2-weighted images (area under the curve = 0.79, 0.70, and 0.83, respectively). With the independent 3-dataset cross-validation strategy, select radiomic features were predictive of sonic hedgehog (area under the curve = 0.70–0.73) and group 4 (area under the curve = 0.76–0.80) medulloblastoma. CONCLUSIONS: This study provides proof-of-concept results for the application of radiomic and machine learning approaches to a multi-institutional dataset for the prediction of medulloblastoma subgroups.

MRI-based machine learning designed with sequential decision steps reliably differentiated four unique medulloblastoma molecular subgroups. Background Radiogenomics of pediatric medulloblastoma (MB) offers an opportunity for MB risk stratification, which may aid therapeutic decision making, family counseling, and selection of patient g...

Malignant brain tumors are the leading cause of cancer death in children.¹ High-grade gliomas (HGGs) are among the most lethal of cancers, with a median overall survival (OS) of 14 to 20 months after optimal multimodal therapy.^2-4 The current standard of care for HGGs in adults includes maximal safe resection, high-dose radiotherapy, and chemotherapy.⁵