HGG-32. PNOC008: A PILOT TRIAL TESTING THE CLINICAL BENEFIT OF USING MOLECULAR PROFILING TO DETERMINE AN INDIVIDUALIZED TREATMENT PLAN IN CHILDREN AND YOUNG ADULTS WITH NEWLY DIAGNOSED HIGH-GRADE GLIOMA (EXCLUDING DIFFUSE INTRINSIC PONTINE GLIOMA)

Neuro-Oncology · 2024 · 2 citations

• Computer Science
• Medicine
• Oncology

Abstract BACKGROUND Children and young adults diagnosed with high-grade glioma (HGG) face extremely poor prognoses. Despite multiple clinical trials testing new treatments in this population, a survival advantage has yet to be achieved. Herein we assessed, in a single-arm, multi-center pilot trial, the feasibility of molecular profiling of primary HGG tumor tissue to create an individualized treatment plan with up to four FDA approved medications. METHODS Patients aged <21 years with newly diagnosed, localized, hemispheric HGG (Stratum A) or midline HGG (non-DIPG; Stratum B) were eligible. Tumor tissue underwent comprehensive molecular profiling (targeted gene panel, whole exome, and whole transcriptome sequencing). Based on detailed review of the molecular data by a dedicated tumor board, an individualized treatment plan that combined up to four FDA approved drugs was recommended. Circulating tumor DNA (ctDNA), imaging, and quality of life (QOL) measures were collected at multiple timepoints. RESULTS Fifty-five patients enrolled between 2018 and 2023 (median age 11 years [range 2-20], n=31 female, n=29 Stratum A). The most common integrated diagnoses included H3K27-altered diffuse midline glioma (n=17), H3/IDH-wildtype diffuse pediatric-type HGG (n=16), and H3G34-mutant diffuse hemispheric glioma (n=12). Median overall survival (OS) from the time of study enrollment was 26.5 months in Stratum A (lower 95% CI: 18.7) and 21.7 months in Stratum B (lower 95% CI: 16.8), with a median follow-up of 35.4 months for all patients (lower 95% CI: 32.5). The most common grade 3 or 4 treatment-related adverse events were decreased neutrophils (n=28), decreased platelets (n=22), and decreased white blood cells (n=16). As of December 2023, seven patients remain on therapy. Central imaging, ctDNA, and QOL analyses are underway. CONCLUSIONS A personalized treatment recommendation for children and young adults with HGG based on comprehensive transcriptomic and genomic analysis is feasible. Current survival data are encouraging, and molecular subgroup analyses are ongoing.

Automated tumor segmentation and brain tissue extraction from multiparametric MRI of pediatric brain tumors: A multi-institutional study

Neuro-Oncology Advances · 2023 · 50 citations

• Computer Science
• Artificial Intelligence
• Medicine

Background: Brain tumors are the most common solid tumors and the leading cause of cancer-related death among all childhood cancers. Tumor segmentation is essential in surgical and treatment planning, and response assessment and monitoring. However, manual segmentation is time-consuming and has high interoperator variability. We present a multi-institutional deep learning-based method for automated brain extraction and segmentation of pediatric brain tumors based on multi-parametric MRI scans. Methods: = 21) subsets. DeepMedic, a three-dimensional convolutional neural network, was trained and the model parameters were tuned. Finally, the network was evaluated on the withheld internal and external test cohorts. Results: Dice similarity score (median ± SD) was 0.91 ± 0.10/0.88 ± 0.16 for the whole tumor, 0.73 ± 0.27/0.84 ± 0.29 for ET, 0.79 ± 19/0.74 ± 0.27 for union of all non-enhancing components (i.e., NET, CC, ED), and 0.98 ± 0.02 for brain tissue in both internal/external test sets. Conclusions: Our proposed automated brain extraction and tumor subregion segmentation models demonstrated accurate performance on segmentation of the brain tissue and whole tumor regions in pediatric brain tumors and can facilitate detection of abnormal regions for further clinical measurements.

Integrated Proteogenomic Characterization across Major Histological Types of Pediatric Brain Cancer

Cell · 2020 · 337 citations

• Biology
• Computational biology
• Genetics