Neural deformation fields for template-based reconstruction of cortical surfaces from MRI

arXiv:2401.12938v2 Announce Type: replace-cross
Abstract: The reconstruction of cortical surfaces is a prerequisite for quantitative analyses of the cerebral cortex in magnetic resonance imaging (MRI). Existing segmentation-based methods separate the surface registration from the surface extraction, which is computationally inefficient and prone to distortions. We introduce Vox2Cortex-Flow (V2C-Flow), a deep mesh-deformation technique that learns a deformation field from a brain template to the cortical surfaces of an MRI scan. To this end, we present a geometric neural network that models …

abstract arxiv cerebral cerebral cortex cortex cs.cv eess.iv extraction fields flow imaging mri quantitative registration segmentation surface template type