Atlas-independent brain connectome analysis at voxel-level granularity: graph convolutional networks for etiology classification in newborns

Abstract

Early identification of altered brain networks in neonates at risk for neurodevelopmental impairments is critical for timely intervention and improving outcomes. This study explores the potential of graph convolutional networks (GCNs) applied to structural brain connectomes at the voxel level granularity to classify neonatal connectomes by their underlying etiology: 51 children with congenital heart disease (CHD), 100 children born very preterm (PB), and 43 children with spina bifida aperta (SBA). Leveraging the flexibility of voxel-level parcellation, we captured fine-grained connectomic differences that improved classification performance (F1 = 0.78) compared to both atlas-based methods (F1 = 0.62) and a multilayer perceptron baseline model (F1 = 0.69). This approach enables subject-specific parcellation without the need for predefined anatomical templates, facilitating the analysis of diverse brain morphologies and age ranges. Attribution analysis using integrated gradients provided interpretable insights into etiology-specific connectomic patterns, highlighting regions of potential neurodevelopmental importance, such as the Rolandic operculum, inferior parietal lobule, and inferior frontal gyrus. Lateralized attribution patterns in PB reflected known neurodevelopmental alterations, underscoring the value of interpretable graph learning for understanding etiology-specific connectomic features. This work represents an important step toward atlas-independent connectome analysis, offering a novel framework for studying diverse neonatal populations and advancing our understanding of early brain development.