MDB-40. DEFORMATION-HETEROGENEITY RADIOMIC MEASURES TO RISK-STRATIFY PEDIATRIC MEDULLOBLASTOMA PATIENTS: A PRELIMINARY ANALYSIS

Abstract

Abstract BACKGROUND A significant challenge in medulloblastoma (MB), the most frequent malignant brain tumor in children, is to accurately identify ‘average-risk’ patients who may benefit from therapy de-escalation without affecting treatment outcomes, from ‘high-risk’ patients. Unfortunately, the current clinical risk-assessment approaches (Chang/molecular stratification) are sub-optimal in reliable risk-stratification in MB. This work evaluates the hypothesis that infiltration in aggressive tumors manifests as deformations (shifts) with larger magnitudes and positive orientations (angles) in the surrounding healthy tissue, on MRI scans, compared to average-risk tumors (smaller shift magnitudes and negative orientations). The proposed imaging marker, complementary with current approaches, may allow for more reliable risk-stratification. METHODS T1-weighted MRI scans of MB patients (2–18 years) were collected from Cincinnati Children’s Hospital Medical Center (Site1-training) (n=42) and Children’s Hospital Los Angeles (Site2-testing) (n=45). Preprocessing and annotations for the edema sub-compartment were performed. Scans were mapped to age-specific atlases using diffeomorphic registration and inverse transformations were employed to obtain the deformations. Deformation magnitudes (DefMag) were extracted within equidistant bands outside the edema by calculating the Euclidean norm of deformations, generating a magnitude statistics vector (median, skewness, kurtosis, mean, standard-deviation). Angles/Orientations (Defθ) were computed between deformation vectors and vectors connecting each voxel to the tumor’s centroid, then quantized to 6 intervals, creating an orientation vector per band. Deformation magnitudes and angles (DefMag+θ) were employed with Chang and molecular stratification within regression models for risk-stratification. RESULTS Our analysis demonstrated that deformation features, complementing molecular and Chang’s stratification, yielded best results for risk-stratification. Employing DefMag+θ+Chang+molecular on training yielded Concordance-index (CI) of 0.56, p=0.0014 (CI=0.6,p=0.03 testing). DefMag+θ+Chang’s yielded CI=0.64, p<0.0001 on training (CI=0.54,p=0.04 testing). Results were not significant when employing Chang’s or molecular classification alone. CONCLUSIONS Our results suggest that radiomic deformation features, complementing clinical and molecular approaches, may enable reliable risk-stratification in pediatric MB.