Shape Registration in Implicit Spaces Using Information Theory and Free Form Deformations
IEEE Transactions on Pattern Analysis and Machine Intelligence
A methodology for analyzing curvature in the developing brain from preterm to adult
International Journal of Imaging Systems and Technology - Human Brain Imaging
Shape Analysis with Overcomplete Spherical Wavelets
MICCAI '08 Proceedings of the 11th international conference on Medical Image Computing and Computer-Assisted Intervention - Part I
International Journal of Computer Vision
Hi-index | 0.00 |
We present an approach for nonrigid registration of consecutive neonatal cortical surfaces from MR images acquired at 30 and 40 week corrected gestational ages. Surfaces are registered implicitly using a method based on the Demons algorithm. Our key innovation is removing the Gaussian smoothing term in Demons in favor of an elasticity constraint that simultaneously promotes more realistic deformations and smooths the deformation field. This is advantageous because the constraint smooths the deformation field along the surface rather than across it. Therefore, fine deformations, such as those necessary to characterize small, new cortical folds, are preserved. The estimated deformation fields are then used to characterize brain development.