File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Transitive inverse-consistent manifold registration.

TitleTransitive inverse-consistent manifold registration.
Authors
Issue Date2005
Citation
Information Processing In Medical Imaging : Proceedings Of The ... Conference, 2005, v. 19, p. 468-479 How to Cite?
AbstractThis paper presents a new registration method called Transitive Inverse-Consistent Manifold Registration (TICMR). The TICMR method jointly estimates correspondence maps between groups of three manifolds embedded in a higher dimensional image space while minimizing inverse consistency and transitivity errors. Registering three manifolds at once provides a means for minimizing the transitivity error which is not possible when registering only two manifolds. TICMR is an iterative method that uses the closest point projection operator to define correspondences between manifolds as they are non-rigidly registered. Examples of the TICMR method are presented for matching groups of three contours and groups of three surfaces. The contour registration is regularized by minimizing the change in bending energy of the curves while the surface registration is regularized by minimizing the change in elastic energy of the surfaces. The notions of inverse consistency error (ICE) and transitivity error (TE) are extended from volume registration to manifold registration by using a closest point projection operator. For the experiments in this paper, the TICMR method reduces the average ICE by 200 times (contour)/ 6 times (surface) and the average TE by 40 times (contour)/ 2-4 times (surface) compared to registering with a curvature constraint alone. Furthermore, the TICMR is shown to avoid some local minimum that are not avoided when registering with a curvature constraint alone.
Persistent Identifierhttp://hdl.handle.net/10722/169872
ISSN
2015 SCImago Journal Rankings: 0.611

 

DC FieldValueLanguage
dc.contributor.authorGeng, Xen_HK
dc.contributor.authorKumar, Den_HK
dc.contributor.authorChristensen, GEen_HK
dc.date.accessioned2012-10-25T04:57:25Z-
dc.date.available2012-10-25T04:57:25Z-
dc.date.issued2005en_HK
dc.identifier.citationInformation Processing In Medical Imaging : Proceedings Of The ... Conference, 2005, v. 19, p. 468-479en_HK
dc.identifier.issn1011-2499en_HK
dc.identifier.urihttp://hdl.handle.net/10722/169872-
dc.description.abstractThis paper presents a new registration method called Transitive Inverse-Consistent Manifold Registration (TICMR). The TICMR method jointly estimates correspondence maps between groups of three manifolds embedded in a higher dimensional image space while minimizing inverse consistency and transitivity errors. Registering three manifolds at once provides a means for minimizing the transitivity error which is not possible when registering only two manifolds. TICMR is an iterative method that uses the closest point projection operator to define correspondences between manifolds as they are non-rigidly registered. Examples of the TICMR method are presented for matching groups of three contours and groups of three surfaces. The contour registration is regularized by minimizing the change in bending energy of the curves while the surface registration is regularized by minimizing the change in elastic energy of the surfaces. The notions of inverse consistency error (ICE) and transitivity error (TE) are extended from volume registration to manifold registration by using a closest point projection operator. For the experiments in this paper, the TICMR method reduces the average ICE by 200 times (contour)/ 6 times (surface) and the average TE by 40 times (contour)/ 2-4 times (surface) compared to registering with a curvature constraint alone. Furthermore, the TICMR is shown to avoid some local minimum that are not avoided when registering with a curvature constraint alone.en_HK
dc.languageengen_US
dc.relation.ispartofInformation processing in medical imaging : proceedings of the ... conferenceen_HK
dc.subject.meshAlgorithmsen_US
dc.subject.meshArtificial Intelligenceen_US
dc.subject.meshHumansen_US
dc.subject.meshImaging, Three-Dimensional - Methodsen_US
dc.subject.meshLung - Radiographyen_US
dc.subject.meshPattern Recognition, Automated - Methodsen_US
dc.subject.meshRadiographic Image Enhancement - Methodsen_US
dc.subject.meshRadiographic Image Interpretation, Computer-Assisted - Methodsen_US
dc.subject.meshReproducibility Of Resultsen_US
dc.subject.meshSensitivity And Specificityen_US
dc.subject.meshSubtraction Techniqueen_US
dc.subject.meshTomography, X-Ray Computed - Methodsen_US
dc.titleTransitive inverse-consistent manifold registration.en_HK
dc.typeArticleen_HK
dc.identifier.emailGeng, X: gengx@hku.hken_HK
dc.identifier.authorityGeng, X=rp01678en_HK
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.pmid17354718-
dc.identifier.scopuseid_2-s2.0-34047220426en_HK
dc.identifier.volume19en_HK
dc.identifier.spage468en_HK
dc.identifier.epage479en_HK
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridGeng, X=34771310000en_HK
dc.identifier.scopusauthoridKumar, D=35595856800en_HK
dc.identifier.scopusauthoridChristensen, GE=7202944649en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats