Cargando…

Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation

This paper presents a nonlinear image registration algorithm based on the setting of Large Deformation Diffeomorphic Metric Mapping (LDDMM), but with a more efficient optimisation scheme — both in terms of memory required and the number of iterations required to reach convergence. Rather than perfor...

Descripción completa

Detalles Bibliográficos
Autores principales: Ashburner, John, Friston, Karl J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Academic Press 2011
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3221052/
https://www.ncbi.nlm.nih.gov/pubmed/21216294
http://dx.doi.org/10.1016/j.neuroimage.2010.12.049
_version_ 1782217027360915456
author Ashburner, John
Friston, Karl J.
author_facet Ashburner, John
Friston, Karl J.
author_sort Ashburner, John
collection PubMed
description This paper presents a nonlinear image registration algorithm based on the setting of Large Deformation Diffeomorphic Metric Mapping (LDDMM), but with a more efficient optimisation scheme — both in terms of memory required and the number of iterations required to reach convergence. Rather than perform a variational optimisation on a series of velocity fields, the algorithm is formulated to use a geodesic shooting procedure, so that only an initial velocity is estimated. A Gauss–Newton optimisation strategy is used to achieve faster convergence. The algorithm was evaluated using freely available manually labelled datasets, and found to compare favourably with other inter-subject registration algorithms evaluated using the same data.
format Online
Article
Text
id pubmed-3221052
institution National Center for Biotechnology Information
language English
publishDate 2011
publisher Academic Press
record_format MEDLINE/PubMed
spelling pubmed-32210522011-12-28 Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation Ashburner, John Friston, Karl J. Neuroimage Technical Note This paper presents a nonlinear image registration algorithm based on the setting of Large Deformation Diffeomorphic Metric Mapping (LDDMM), but with a more efficient optimisation scheme — both in terms of memory required and the number of iterations required to reach convergence. Rather than perform a variational optimisation on a series of velocity fields, the algorithm is formulated to use a geodesic shooting procedure, so that only an initial velocity is estimated. A Gauss–Newton optimisation strategy is used to achieve faster convergence. The algorithm was evaluated using freely available manually labelled datasets, and found to compare favourably with other inter-subject registration algorithms evaluated using the same data. Academic Press 2011-04-01 /pmc/articles/PMC3221052/ /pubmed/21216294 http://dx.doi.org/10.1016/j.neuroimage.2010.12.049 Text en © 2011 Elsevier Inc. https://creativecommons.org/licenses/by/3.0/ Open Access under CC BY 3.0 (https://creativecommons.org/licenses/by/3.0/) license
spellingShingle Technical Note
Ashburner, John
Friston, Karl J.
Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation
title Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation
title_full Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation
title_fullStr Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation
title_full_unstemmed Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation
title_short Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation
title_sort diffeomorphic registration using geodesic shooting and gauss–newton optimisation
topic Technical Note
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3221052/
https://www.ncbi.nlm.nih.gov/pubmed/21216294
http://dx.doi.org/10.1016/j.neuroimage.2010.12.049
work_keys_str_mv AT ashburnerjohn diffeomorphicregistrationusinggeodesicshootingandgaussnewtonoptimisation
AT fristonkarlj diffeomorphicregistrationusinggeodesicshootingandgaussnewtonoptimisation