Title
Implicit surface registration with surface-oriented anisotropic deformation field smoothing
Abstract
This paper introduces a variant of the Demon's algorithm with an anisotropic smoothing term designed for the registration of surfaces with significant conformal differences. Because of the chosen implicit surface representation, the deformation field at each iteration can be easily defined with respect to the evolving surface. Anisotropic smoothing is performed preferentially in the tangent plane to the surface, preserving local, complex deformations. This method is applied to the registration of consecutive neonatal cortical surfaces from MR images acquired at 30 and 40 week gestational ages. Our method preserves the emergence of small, new folds, while greatly reducing noise in the resulting deformation field.
Year
DOI
Venue
2013
10.1109/ISBI.2013.6556516
Biomedical Imaging
Keywords
Field
DocType
biomedical MRI,deformation,image registration,medical image processing,paediatrics,Demon algorithm,MR image,consecutive neonatal cortical surface,gestational ages,implicit surface registration,noise reduction,surface-oriented anisotropic deformation field smoothing,time 30 week to 40 week,Demon's algorithm,anisotropic smoothing,cortical surfaces,registration,signed distance functions
Computer vision,Anisotropy,Computer science,Conformal map,Smoothing,Artificial intelligence,Deformation (mechanics),Geometry,Image registration,Tangent space
Conference
ISSN
ISBN
Citations 
1945-7928
978-1-4673-6456-0
0
PageRank 
References 
Authors
0.34
0
6
Name
Order
Citations
PageRank
Paul C. Pearlman172.23
Ivana Isgum276650.08
Karina J. Kersbergen3523.61
Manon J. N. L. Benders418011.51
Max A Viergever57946833.77
Josien P. W. Pluim62439178.67