Abstract OBJECTIVE To identify genetic predictors of neurocognition, CMBs, brain volume, and WM changes in pediatric brain tumor survivors. METHODS Patients were selected from an existing cohort (RadART) if they had: 1) at least one neurocognitive evaluation using computer-based CogState; 2) available DNA; 3) standard imaging. Candidate gene or genome-wide genotyping was performed on all patients. CMBs were identified using a semi-automated algorithm developed in MATLAB. Volume of T2/FLAIR WM signal abnormality was measured using a semi-automated method based on a convolutional neural network. Brain volume and cortical thickness were measured using FreeSurfer volumetric analysis. Logistic and linear regression were done to compare phenotypes with candidate genotypes. Genome-wide efficient mixed-model analysis was done to compare neurocognition and CMBs. Gene set analysis was done using https://fuma.ctglab.nl/. RESULTS APOE4 was a candidate variant associated with non-lobar, larger volume CMBs (p< 0.05). At the GWAS-level (n=225), specific genes trended with visual memory, psychomotor function, and CMB count (p< 5x10-8). Using gene set analyses, there were gene set trends seen with CMB count and psychomotor function. Small sample size and low mutant allele frequency limited reliability of these findings. Preliminary volumetric analysis show reduced volume within the right parietal, medial occipital and inferior temporal lobes with increased cortical thickness in the left occipital and medial parietal lobe in patients carrying the ApoE4 allele. WM signal assessments are ongoing. CONCLUSION Genetic markers may be associated with neurocognition, CMBs, brain volume and WM changes in pediatric brain tumor survivors; however, larger cohorts are needed to confirm specific gene relevance.