Personalized functional network topographic mapping in human neonates

Motivation: The neonatal brain already possesses rich functional layouts that are crucial for future behavior development. However, how the individualized functional topography refines at birth, supports neurodevelopmental outcomes, and is impacted by prematurity remain largely unclear. Goal(s): We aim to delineate the typical and atypical refining pattern of functional topography in the neonatal brain. Approach: We leveraged advances in machine learning and large fMRI datasets covering term neonatal, preterm and adult population. Results: Boundaries of primary networks could significantly predict neonatal brain maturity and neurodevelopmental outcomes at 18 months. Association networks could significantly identified preterm brain and reflect accelerated maturation in preterm. Impact: Our results highlight how neonatal brain function architecture organizes, develops and supports the emerge of diverse behaviors.