Robust deformable image registration using prior shape information for atlas to patient registration

Lotta M. Ellingsen; Gouthami Chintalapani; Russell H. Taylor; Jerry L. Prince

doi:10.1016/j.compmedimag.2009.05.003

Robust deformable image registration using prior shape information for atlas to patient registration

Lotta M. Ellingsen, Gouthami Chintalapani, Russell H. Taylor, Jerry L. Prince

Faculty of Electrical and Computer Engineering

University of Iceland

Research output: Contribution to journal › Article › peer-review

Abstract

Statistical atlases enable the individualization of atlas information for patient specific applications such as surgical planning. In this paper, a statistical atlas comprising a point distribution model defined on the vertices of a tetrahedral mesh is registered to a subject's computed tomography scan of the human pelvis. The approach consists of a volumetric deformable registration method augmented to maintain the topology of the atlas mesh after deformation as well as incorporating the dominant three-dimensional shape modes in the atlas. Experimental results demonstrate that incorporation of the statistical shape atlas helps to stabilize the registration and improves robustness and registration accuracy.

Original language	English
Pages (from-to)	79-90
Number of pages	12
Journal	Computerized Medical Imaging and Graphics
Volume	34
Issue number	1
DOIs	https://doi.org/10.1016/j.compmedimag.2009.05.003
Publication status	Published - Jan 2010

Bibliographical note

Funding Information: This work was supported by NIH/NIBIB grant 5R21EB003616 and NSF EEC9731478. The authors would like to thank Ms. Pauline Pelletier for her assistance on manual processing of data.

Other keywords

Computed tomography-CT
Deformable image registration
Pelvis
Point distribution model
Principal component analysis-PCA
Prior shape information
Statistical atlas
Surgical planning
Tetrahedral mesh
Topology

Access to Document

10.1016/j.compmedimag.2009.05.003

Cite this

@article{0b13c7f6da5b4b12a4fe731e2f5867eb,

title = "Robust deformable image registration using prior shape information for atlas to patient registration",

abstract = "Statistical atlases enable the individualization of atlas information for patient specific applications such as surgical planning. In this paper, a statistical atlas comprising a point distribution model defined on the vertices of a tetrahedral mesh is registered to a subject's computed tomography scan of the human pelvis. The approach consists of a volumetric deformable registration method augmented to maintain the topology of the atlas mesh after deformation as well as incorporating the dominant three-dimensional shape modes in the atlas. Experimental results demonstrate that incorporation of the statistical shape atlas helps to stabilize the registration and improves robustness and registration accuracy.",

keywords = "Computed tomography-CT, Deformable image registration, Pelvis, Point distribution model, Principal component analysis-PCA, Prior shape information, Statistical atlas, Surgical planning, Tetrahedral mesh, Topology",

author = "Ellingsen, \{Lotta M.\} and Gouthami Chintalapani and Taylor, \{Russell H.\} and Prince, \{Jerry L.\}",

note = "Funding Information: This work was supported by NIH/NIBIB grant 5R21EB003616 and NSF EEC9731478. The authors would like to thank Ms. Pauline Pelletier for her assistance on manual processing of data.",

year = "2010",

month = jan,

doi = "10.1016/j.compmedimag.2009.05.003",

language = "English",

volume = "34",

pages = "79--90",

journal = "Computerized Medical Imaging and Graphics",

issn = "0895-6111",

publisher = "Elsevier Ltd.",

number = "1",

}

TY - JOUR

T1 - Robust deformable image registration using prior shape information for atlas to patient registration

AU - Ellingsen, Lotta M.

AU - Chintalapani, Gouthami

AU - Taylor, Russell H.

AU - Prince, Jerry L.

N1 - Funding Information: This work was supported by NIH/NIBIB grant 5R21EB003616 and NSF EEC9731478. The authors would like to thank Ms. Pauline Pelletier for her assistance on manual processing of data.

PY - 2010/1

Y1 - 2010/1

N2 - Statistical atlases enable the individualization of atlas information for patient specific applications such as surgical planning. In this paper, a statistical atlas comprising a point distribution model defined on the vertices of a tetrahedral mesh is registered to a subject's computed tomography scan of the human pelvis. The approach consists of a volumetric deformable registration method augmented to maintain the topology of the atlas mesh after deformation as well as incorporating the dominant three-dimensional shape modes in the atlas. Experimental results demonstrate that incorporation of the statistical shape atlas helps to stabilize the registration and improves robustness and registration accuracy.

AB - Statistical atlases enable the individualization of atlas information for patient specific applications such as surgical planning. In this paper, a statistical atlas comprising a point distribution model defined on the vertices of a tetrahedral mesh is registered to a subject's computed tomography scan of the human pelvis. The approach consists of a volumetric deformable registration method augmented to maintain the topology of the atlas mesh after deformation as well as incorporating the dominant three-dimensional shape modes in the atlas. Experimental results demonstrate that incorporation of the statistical shape atlas helps to stabilize the registration and improves robustness and registration accuracy.

KW - Computed tomography-CT

KW - Deformable image registration

KW - Pelvis

KW - Point distribution model

KW - Principal component analysis-PCA

KW - Prior shape information

KW - Statistical atlas

KW - Surgical planning

KW - Tetrahedral mesh

KW - Topology

UR - https://www.scopus.com/pages/publications/72049130843

U2 - 10.1016/j.compmedimag.2009.05.003

DO - 10.1016/j.compmedimag.2009.05.003

M3 - Article

C2 - 19515532

SN - 0895-6111

VL - 34

SP - 79

EP - 90

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

IS - 1

ER -

Robust deformable image registration using prior shape information for atlas to patient registration

Abstract

Bibliographical note

Other keywords

Access to Document

Fingerprint

Cite this