IMG-06. RADIOMIC-BASED RISK STRATIFICATION OF PEDIATRIC LOW-GRADE GLIOMA REVEALS DIFFERENTIALLY EXPRESSED MOLECULAR PROCESSES CONTRIBUTING TO VARIABLE PATIENT PROGNOSIS

Abstract In pediatric low-grade gliomas (pLGG), prognosis and responses to treatments are heterogeneous. This heterogeneity may be explained by the differences in molecular composition of tumors same histology likely upstream alterations following administered radiation or systemic therapy. Integration radiomics clinical variables could generate a non-invasive biomarker that provides upfront prediction about patient’s risk progression. We show our proposed radiomic-based risk-stratification signature for pLGGs is associated with transcriptomic pathways. Standard multiparametric MRI sequences 134 pLGG patients from Children’s Brain Tumor Network (CBTN) were retrospectively collected 881 quantitative radiomic features extracted. A multivariate Cox proportional hazard’s (Cox-PH) regression model was fitted on (age, sex, tumor location, extent resection) along using 5-fold cross-validation, predict The Cox-PH showed excellent performance PFS scores, supported concordance index 0.78. Radiogenomic analysis performed determine pathways (1594 pathways, c2 MsigDb Reactome v2022.1) contribute risk, predicted signature. ElasticNet applied scores obtained gene set enrichment (GSEA) (in 70/134 subjects) scores. Increased corresponded upregulation DNA repair dysregulation lipophagy, fatty acid beta oxidation, vitamin D which tumor-promoting. BRAFfusion signaling inversely correlated consistent known favorable KIAA1549-BRAF fused pLGGs. Upregulation immune related Toll-Like Receptor (TLR) lower risk. study elucidates synergistic dynamics between biological processes promote progression used encourage targeted therapies increased