PATH-06. AN INTEGRATIVE MULTI-MODAL DIAGNOSTIC APPROACH TO PEDIATRIC CHOROID PLEXUS TUMORS

Abstract

Abstract BACKGROUND Choroid plexus tumors (CPTs) consist of a diverse group of neoplasms, more prevalent in children. They include choroid plexus papillomas (CPPs, grade 1), atypical choroid plexus papillomas (aCPPs, grade 2), and choroid plexus carcinomas (CPCs, grade 3). Traditional grading of CPTs relies on histologic assessment, but morphologic criteria for determining tumor grade are subjective. Evidence suggests incorporation of clinical, radiologic, and molecular characteristics may increase diagnostic accuracy. Here, we investigated the multi-modal associations of CPT subtypes to develop a classification system to aid in CPT subtype diagnostics. METHODS We aggregated an integrative dataset that consists of digitized whole-slide images, NGS sequencing panels, methylation arrays, and magnetic resonance spectroscopy (MRS) spectra from in-house and publicly available data sources (n=110). We tested for clinically significant associations and established multi-modal profiles of CPT subtypes, as well as a machine-learning classifier to predict multi-modal based CPT subtypes. RESULTS CPT subtypes exhibit distinct characteristics across modalities with consistent correlations across anatomy, molecular, and metabolic datasets. Computer-vision models achieved high accuracy (89.7%) in classifying CPT subtypes using H&E images. Ki-67 immunostaining displayed increased reactivity in CPC compared to CPP and aCPP (p = 0.007, ANOVA). Methylation-based classifications confidently predicted CPP and CPC subtypes, while aCPP tumors clustered with either CPP or CPC due to the lack of a defined subtype. Molecular variants (i.e. TP53, MYCN) were significantly associated with CPC (p = 0.007, ANOVA). Metabolites such as inositol (p = 0.031) and choline (p = 0.004) were associated with CPT grade based on MRS-spectra. CONCLUSION Multi-modal analysis reliably separates CPTs by grade. The study underscores the significance of integrating multi-modal datasets in refining the accuracy of diagnosis and prognosis of CPTs. Continued research will focus on a multi-modal approach to improve prediction of aggressive behavior and understanding of inherent metabolic heterogeneity of CPT subtypes.