A Deep Generative Model of Neonatal Cortical Surface Development
This work addresses the problem of understanding cortical changes in preterm infants for clinical applications, but it is incremental as it adapts existing methods to a specific domain.
The authors tackled the challenge of modeling neonatal cortical surface development using deep generative models on non-flat topologies by implementing a surface-based CycleGAN with MoNet to predict changes in cortical organization across gestation stages, validated against longitudinal data and a classifier with reliable results.
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.