A Deep Generative Model of Neonatal Cortical Surface Development

TL;DR

This paper introduces a surface-based CycleGAN model using MoNet to predict and translate neonatal cortical surface development, enabling better understanding of preterm birth effects on brain maturation.

Contribution

It presents a novel deep generative model tailored for non-flat cortical surface data, improving interpretation of developmental changes in neonatal brains.

Findings

Successfully predicts individual cortical development patterns

Translates cortical features between preterm and term stages

Results align with existing neurodevelopmental literature

Abstract

The neonatal cortical surface is known to be affected by preterm birth, and the subsequent changes to cortical organisation have been associated with poorer neurodevelopmental outcomes. Deep Generative models have the potential to lead to clinically interpretable models of disease, but developing these on the cortical surface is challenging since established techniques for learning convolutional filters are inappropriate on non-flat topologies. To close this gap, we implement a surface-based CycleGAN using mixture model CNNs (MoNet) to translate sphericalised neonatal cortical surface features (curvature and T1w/T2w cortical myelin) between different stages of cortical maturity. Results show our method is able to reliably predict changes in individual patterns of cortical organisation at later stages of gestation, validated by comparison to longitudinal data; and translate appearance between preterm and term gestation (> 37 weeks gestation), validated through comparison with a trained term/preterm classifier. Simulated differences in cortical maturation are consistent with observations in the literature.