Infant brain development

Infant brain development prediction from baseline

Motivation: Learning to predict 4D brain development from baseline brain shape (i.e. neonatal timepoint) can help predict biomarkers for neurodevelopmental disorders.

Innovation: Devising learning-based models for predicting (e.g., cortical surface, cortical surface and white matter fiber tracts, MR image) development from baseline.

Brain connectomics

Shape-to-shape brain connectivity network (morphome) and growth-to-growth connectivity network (kinectome)

Shape-growth brain connectivity networks: morpho-kinectomes

Motivation: The development of in vivo brain connectomics field has heavily relied on using functional and diffusion Magnetic Resonance Imaging (MRI) modalities, which have fundamentally focused on studying the functional and structural relationships between pairs of anatomical regions in the brain. However, works on brain morphological (i.e., shape-to-shape) connections, which can be derived from T1 and T2 MR images, in both typical and atypical development or ageing are almost absent. Furthermore, the brain cannot be only regarded as a static shape, since it is a dynamic complex system that changes at functional, structural and morphological levels. Hence, examining the ‘connection’ between brain shape and its changes with time (e.g., growth or atrophy) may help advance our understanding of brain dynamics as well as disorders that may affect it.

Innovation: We introduce in this work three population-based shape-growth connectivity analysis tools that further extend the field of connectomics to brain morphology and dynamics: the morphome, kinectome and morpho-kinectome.

Brain network atlas estimation

The developmental functional baby network atlas

Motivation: Many methods have been developed to spatially normalize a population of brain images for estimating a mean image as a population- average atlas. However, methods for deriving a network atlas from a set of brain networks sitting on a complex manifold are still absent.

Innovation: We propose a novel network atlas estimation framework from a population of brain networks estimated from a single neuroimaging modality (e.g., functional MRI).