Predictive Neuroimaging Features and Growth Characteristics of Pediatric Brain Tumors Using Pre-Diagnostic Neuroimaging

Abstract Purpose To evaluate for predictive neuroimaging features of pediatric brain tumor development and quantify tumor growth characteristics. Methods Retrospective review of 1098 consecutive pediatric patients at a single institution with newly diagnosed brain tumors from January 2009 to October 2021was performed. Pre-diagnostic and diagnostic neuroimaging features (e.g., tumor size, apparent diffusion coefficient (ADC) values), clinical presentations, and neuropathology were recorded. High- and low-grade tumor sizes were fit to linear and exponential growth regression models. Results Fourteen of 1098 patients (1%) had neuroimaging before diagnosis of a brain tumor (8 females, mean age 8.1 years, imaging interval 0.2-8.7 years). Tumor types included low-grade glioma (n = 4), embryonal tumors (n = 3), ependymoma (n = 3), and others (n = 4). Pre-diagnostic imaging of corresponding tumor growth sites were abnormal in four cases (28%) and demonstrated higher ADC values in diagnostically high-grade tumors (p = 0.05). Growth regression analyses demonstrated R2-values of 0.92 and 0.91 using a linear model and 0.64 and 0.89 using an exponential model for high- and low-grade tumors, respectively; estimated minimum velocity of diameter expansion was 2.4 cm/year for high-grade tumors and 0.4 cm/year for low-grade tumors. High-grade tumors demonstrated faster growth rate of diameter and solid tumor volume compared to low-grade tumors (p = 0.02, p = 0.03, respectively). Conclusions This is the first study to utilize pre-diagnostic neuroimaging to demonstrate that linear and exponential growth rate models can be used to estimate pediatric brain tumor growth velocity and should be validated in a larger cohort.