Patrice Grehten

This paper uses graph convolutional networks to classify neonatal brain connectomes by etiology at voxel-level granularity, achieving higher classification performance than atlas-based methods and a multilayer perceptron baseline.

This study examines structural brain connectome differences in newborns at risk for cognitive developmental delay across multiple etiologies, finding altered network topology features associated with poorer cognitive outcomes.

The paper introduces OSBA, an open neuroimaging atlas for spina bifida aperta, providing standardized templates for spatial normalization and anatomical analysis in neonatal brains.