Efficient Probabilistic and Geometric Anatomical Mapping Using Particle Mesh Approximation on GPUs

Deformable image registration in the presence of considerable contrast differences and large size and shape changes presents significant research challenges. First, it requires a robust registration framework that does not depend on intensity measurements and can handle large nonlinear shape variati...

Full description

Bibliographic Details
Main Authors:	Ha, Linh, Prastawa, Marcel, Gerig, Guido, Gilmore, John H., Silva, Cláudio T., Joshi, Sarang
Format:	Online
Language:	English
Published:	Hindawi Publishing Corporation 2011
Online Access:	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3166611/

id	pubmed-3166611
recordtype	oai_dc
spelling	pubmed-31666112011-09-22 Efficient Probabilistic and Geometric Anatomical Mapping Using Particle Mesh Approximation on GPUs Ha, Linh Prastawa, Marcel Gerig, Guido Gilmore, John H. Silva, Cláudio T. Joshi, Sarang Research Article Deformable image registration in the presence of considerable contrast differences and large size and shape changes presents significant research challenges. First, it requires a robust registration framework that does not depend on intensity measurements and can handle large nonlinear shape variations. Second, it involves the expensive computation of nonlinear deformations with high degrees of freedom. Often it takes a significant amount of computation time and thus becomes infeasible for practical purposes. In this paper, we present a solution based on two key ideas: a new registration method that generates a mapping between anatomies represented as a multicompartment model of class posterior images and geometries and an implementation of the algorithm using particle mesh approximation on Graphical Processing Units (GPUs) to fulfill the computational requirements. We show results on the registrations of neonatal to 2-year old infant MRIs. Quantitative validation demonstrates that our proposed method generates registrations that better maintain the consistency of anatomical structures over time and provides transformations that better preserve structures undergoing large deformations than transformations obtained by standard intensity-only registration. We also achieve the speedup of three orders of magnitudes compared to a CPU reference implementation, making it possible to use the technique in time-critical applications. Hindawi Publishing Corporation 2011 2011-08-17 /pmc/articles/PMC3166611/ /pubmed/21941523 http://dx.doi.org/10.1155/2011/572187 Text en Copyright © 2011 Linh Ha et al. https://creativecommons.org/licenses/by/3.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
repository_type	Open Access Journal
institution_category	Foreign Institution
institution	US National Center for Biotechnology Information
building	NCBI PubMed
collection	Online Access
language	English
format	Online
author	Ha, Linh Prastawa, Marcel Gerig, Guido Gilmore, John H. Silva, Cláudio T. Joshi, Sarang
spellingShingle	Ha, Linh Prastawa, Marcel Gerig, Guido Gilmore, John H. Silva, Cláudio T. Joshi, Sarang Efficient Probabilistic and Geometric Anatomical Mapping Using Particle Mesh Approximation on GPUs
author_facet	Ha, Linh Prastawa, Marcel Gerig, Guido Gilmore, John H. Silva, Cláudio T. Joshi, Sarang
author_sort	Ha, Linh
title	Efficient Probabilistic and Geometric Anatomical Mapping Using Particle Mesh Approximation on GPUs
title_short	Efficient Probabilistic and Geometric Anatomical Mapping Using Particle Mesh Approximation on GPUs
title_full	Efficient Probabilistic and Geometric Anatomical Mapping Using Particle Mesh Approximation on GPUs
title_fullStr	Efficient Probabilistic and Geometric Anatomical Mapping Using Particle Mesh Approximation on GPUs
title_full_unstemmed	Efficient Probabilistic and Geometric Anatomical Mapping Using Particle Mesh Approximation on GPUs
title_sort	efficient probabilistic and geometric anatomical mapping using particle mesh approximation on gpus
description	Deformable image registration in the presence of considerable contrast differences and large size and shape changes presents significant research challenges. First, it requires a robust registration framework that does not depend on intensity measurements and can handle large nonlinear shape variations. Second, it involves the expensive computation of nonlinear deformations with high degrees of freedom. Often it takes a significant amount of computation time and thus becomes infeasible for practical purposes. In this paper, we present a solution based on two key ideas: a new registration method that generates a mapping between anatomies represented as a multicompartment model of class posterior images and geometries and an implementation of the algorithm using particle mesh approximation on Graphical Processing Units (GPUs) to fulfill the computational requirements. We show results on the registrations of neonatal to 2-year old infant MRIs. Quantitative validation demonstrates that our proposed method generates registrations that better maintain the consistency of anatomical structures over time and provides transformations that better preserve structures undergoing large deformations than transformations obtained by standard intensity-only registration. We also achieve the speedup of three orders of magnitudes compared to a CPU reference implementation, making it possible to use the technique in time-critical applications.
publisher	Hindawi Publishing Corporation
publishDate	2011
url	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3166611/
_version_	1611473587796967424

Efficient Probabilistic and Geometric Anatomical Mapping Using Particle Mesh Approximation on GPUs

Similar Items