BAI-Net: Individualized Anatomical Human Cerebral Cartography using Graph Convolutional Network

Abstract

Brain atlas is an important tool in the diagnosis and treatment of neurological disorders. However, due to large variations in the organizational principles of individual brains, many challenges remain in clinical applications. Brain atlas individualization network (BAI-Net) is an algorithm that subdivides individual cerebral cortex into segregated areas using brain morphology and connectomes. BAI-Net integrates topological priors derived from a group atlas, adjusts the areal probability using the connectivity context derived from diffusion tractography, and provides reliable and explainable individualized brain parcels across multiple sessions and scanners. We demonstrate that BAI-Net outperforms the conventional iterative clustering approach by capturing significantly heritable topographic variations in individualized cartographies. The topographic variability of BAI-Net cartographies shows strong associations with individual variability in brain morphology, connectivity fingerprints and cognitive behaviors. This study provides a new framework for individualized brain cartography and paves the way of atlas-based precision medicine in clinical practice.