Hybrid multiscale landmark and deformable image registration

An image registration technique is presented for the registration ofmedical images using a hybrid combination of coarse-scale landmark andB-splines deformable registration techniques. The technique isparticularly effective for registration problems in which the imagesto be registered contain large...

Full description

Saved in:
Bibliographic Details
Main Authors: Dana Paquin, Doron Levy, Lei Xing
Format: Article
Language:English
Published: AIMS Press 2007-07-01
Series:Mathematical Biosciences and Engineering
Subjects:
Online Access:https://www.aimspress.com/article/doi/10.3934/mbe.2007.4.711
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832590197042184192
author Dana Paquin
Doron Levy
Lei Xing
author_facet Dana Paquin
Doron Levy
Lei Xing
author_sort Dana Paquin
collection DOAJ
description An image registration technique is presented for the registration ofmedical images using a hybrid combination of coarse-scale landmark andB-splines deformable registration techniques. The technique isparticularly effective for registration problems in which the imagesto be registered contain large localized deformations. A briefoverview of landmark and deformable registration techniques ispresented. The hierarchical multiscale image decomposition of E.Tadmor, S. Nezzar, and L. Vese, A multiscale image representationusing hierarchical $(BV,L^2)$ decompositions, Multiscale Modeling andSimulations, vol. 2, no. 4, pp. 554--579, 2004, is reviewed, and animage registration algorithm is developed based on combining themultiscale decomposition with landmark and deformable techniques.Successful registration of medical images is achieved by firstobtaining a hierarchical multiscale decomposition of the images andthen using landmark-based registration to register the resultingcoarse scales. Corresponding bony structure landmarks are easilyidentified in the coarse scales, which contain only the large shapesand main features of the image. This registration is then fine tunedby using the resulting transformation as the starting point todeformably register the original images with each other using aniterated multiscale B-splines deformable registration technique. Theaccuracy and efficiency of the hybrid technique is demonstrated withseveral image registration case studies in two and three dimensions.Additionally, the hybrid technique is shown to be very robust withrespect to the location of landmarks and presence of noise.
format Article
id doaj-art-87bf2013e2b24d3895dd4927869a0ab2
institution Kabale University
issn 1551-0018
language English
publishDate 2007-07-01
publisher AIMS Press
record_format Article
series Mathematical Biosciences and Engineering
spelling doaj-art-87bf2013e2b24d3895dd4927869a0ab22025-01-24T01:54:07ZengAIMS PressMathematical Biosciences and Engineering1551-00182007-07-014471173710.3934/mbe.2007.4.711Hybrid multiscale landmark and deformable image registrationDana Paquin0Doron Levy1Lei Xing2Department of Mathematics, Stanford University, Stanford, CA 94305-2125Department of Mathematics, Stanford University, Stanford, CA 94305-2125Department of Mathematics, Stanford University, Stanford, CA 94305-2125An image registration technique is presented for the registration ofmedical images using a hybrid combination of coarse-scale landmark andB-splines deformable registration techniques. The technique isparticularly effective for registration problems in which the imagesto be registered contain large localized deformations. A briefoverview of landmark and deformable registration techniques ispresented. The hierarchical multiscale image decomposition of E.Tadmor, S. Nezzar, and L. Vese, A multiscale image representationusing hierarchical $(BV,L^2)$ decompositions, Multiscale Modeling andSimulations, vol. 2, no. 4, pp. 554--579, 2004, is reviewed, and animage registration algorithm is developed based on combining themultiscale decomposition with landmark and deformable techniques.Successful registration of medical images is achieved by firstobtaining a hierarchical multiscale decomposition of the images andthen using landmark-based registration to register the resultingcoarse scales. Corresponding bony structure landmarks are easilyidentified in the coarse scales, which contain only the large shapesand main features of the image. This registration is then fine tunedby using the resulting transformation as the starting point todeformably register the original images with each other using aniterated multiscale B-splines deformable registration technique. Theaccuracy and efficiency of the hybrid technique is demonstrated withseveral image registration case studies in two and three dimensions.Additionally, the hybrid technique is shown to be very robust withrespect to the location of landmarks and presence of noise.https://www.aimspress.com/article/doi/10.3934/mbe.2007.4.7114dctmultiscale analysisdeformable image registrationctnoise.land-mark registration
spellingShingle Dana Paquin
Doron Levy
Lei Xing
Hybrid multiscale landmark and deformable image registration
Mathematical Biosciences and Engineering
4dct
multiscale analysis
deformable image registration
ct
noise.
land-mark registration
title Hybrid multiscale landmark and deformable image registration
title_full Hybrid multiscale landmark and deformable image registration
title_fullStr Hybrid multiscale landmark and deformable image registration
title_full_unstemmed Hybrid multiscale landmark and deformable image registration
title_short Hybrid multiscale landmark and deformable image registration
title_sort hybrid multiscale landmark and deformable image registration
topic 4dct
multiscale analysis
deformable image registration
ct
noise.
land-mark registration
url https://www.aimspress.com/article/doi/10.3934/mbe.2007.4.711
work_keys_str_mv AT danapaquin hybridmultiscalelandmarkanddeformableimageregistration
AT doronlevy hybridmultiscalelandmarkanddeformableimageregistration
AT leixing hybridmultiscalelandmarkanddeformableimageregistration