Deformable registration of brain tumor images via a statistical model of tumor-induced deformation

Ashraf Mohamed; Evangelia I. Zacharaki; Dinggang Shen; Christos Davatzikos

doi:10.1016/j.media.2006.06.005

Deformable registration of brain tumor images via a statistical model of tumor-induced deformation

Ashraf Mohamed^*
, Evangelia I. Zacharaki
, Dinggang Shen
, Christos Davatzikos

^*Corresponding author for this work

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

81 Citations (Scopus)

Abstract

An approach to the deformable registration of three-dimensional brain tumor images to a normal brain atlas is presented. The approach involves the integration of three components: a biomechanical model of tumor mass-effect, a statistical approach to estimate the model's parameters, and a deformable image registration method. Statistical properties of the sought deformation map from the atlas to the image of a tumor patient are first obtained through tumor mass-effect simulations on normal brain images. This map is decomposed into the sum of two components in orthogonal subspaces, one representing inter-individual differences in brain shape, and the other representing tumor-induced deformation. For a new tumor case, a partial observation of the sought deformation map is obtained via deformable image registration and is decomposed into the aforementioned spaces in order to estimate the mass-effect model parameters. Using this estimate, a simulation of tumor mass-effect is performed on the atlas image in order to generate an image that is similar to tumor patient's image, thereby facilitating the atlas registration process. Results for a real tumor case and a number of simulated tumor cases indicate significant reduction in the registration error due to the presented approach as compared to the direct use of deformable image registration.

Original language	English
Pages (from-to)	752-763
Number of pages	12
Journal	Medical Image Analysis
Volume	10
Issue number	5
DOIs	https://doi.org/10.1016/j.media.2006.06.005
Publication status	Published - 2006 Oct

Bibliographical note

Funding Information:
The authors thank Dr. Nick Fox at the University College London, UK, for providing the tumor patient’s images. We also thank Xiaoying Wu at the Section of Biomedical Image Analysis at the University of Pennsylvania for her help in processing the used data. This work was supported in part by the National Science Foundation under Engineering Research Center Grant EEC9731478, and by the National Institutes of Health Grant R01NS42645.

Keywords

Atlas registration
Brain image registration
Brain tumor
Finite element model
Neurosurgical planning
Statistical deformation model

ASJC Scopus subject areas

Radiological and Ultrasound Technology
Radiology Nuclear Medicine and imaging
Computer Vision and Pattern Recognition
Health Informatics
Computer Graphics and Computer-Aided Design

Access to Document

10.1016/j.media.2006.06.005

Cite this

@article{b728fab3c1f84cf79d5dd489f5a24984,

title = "Deformable registration of brain tumor images via a statistical model of tumor-induced deformation",

abstract = "An approach to the deformable registration of three-dimensional brain tumor images to a normal brain atlas is presented. The approach involves the integration of three components: a biomechanical model of tumor mass-effect, a statistical approach to estimate the model's parameters, and a deformable image registration method. Statistical properties of the sought deformation map from the atlas to the image of a tumor patient are first obtained through tumor mass-effect simulations on normal brain images. This map is decomposed into the sum of two components in orthogonal subspaces, one representing inter-individual differences in brain shape, and the other representing tumor-induced deformation. For a new tumor case, a partial observation of the sought deformation map is obtained via deformable image registration and is decomposed into the aforementioned spaces in order to estimate the mass-effect model parameters. Using this estimate, a simulation of tumor mass-effect is performed on the atlas image in order to generate an image that is similar to tumor patient's image, thereby facilitating the atlas registration process. Results for a real tumor case and a number of simulated tumor cases indicate significant reduction in the registration error due to the presented approach as compared to the direct use of deformable image registration.",

keywords = "Atlas registration, Brain image registration, Brain tumor, Finite element model, Neurosurgical planning, Statistical deformation model",

author = "Ashraf Mohamed and Zacharaki, \{Evangelia I.\} and Dinggang Shen and Christos Davatzikos",

note = "Funding Information: The authors thank Dr. Nick Fox at the University College London, UK, for providing the tumor patient{\textquoteright}s images. We also thank Xiaoying Wu at the Section of Biomedical Image Analysis at the University of Pennsylvania for her help in processing the used data. This work was supported in part by the National Science Foundation under Engineering Research Center Grant EEC9731478, and by the National Institutes of Health Grant R01NS42645. ",

year = "2006",

month = oct,

doi = "10.1016/j.media.2006.06.005",

language = "English",

volume = "10",

pages = "752--763",

journal = "Medical Image Analysis",

issn = "1361-8415",

publisher = "Elsevier B.V.",

number = "5",

}

TY - JOUR

T1 - Deformable registration of brain tumor images via a statistical model of tumor-induced deformation

AU - Mohamed, Ashraf

AU - Zacharaki, Evangelia I.

AU - Shen, Dinggang

AU - Davatzikos, Christos

N1 - Funding Information: The authors thank Dr. Nick Fox at the University College London, UK, for providing the tumor patient’s images. We also thank Xiaoying Wu at the Section of Biomedical Image Analysis at the University of Pennsylvania for her help in processing the used data. This work was supported in part by the National Science Foundation under Engineering Research Center Grant EEC9731478, and by the National Institutes of Health Grant R01NS42645.

PY - 2006/10

Y1 - 2006/10

N2 - An approach to the deformable registration of three-dimensional brain tumor images to a normal brain atlas is presented. The approach involves the integration of three components: a biomechanical model of tumor mass-effect, a statistical approach to estimate the model's parameters, and a deformable image registration method. Statistical properties of the sought deformation map from the atlas to the image of a tumor patient are first obtained through tumor mass-effect simulations on normal brain images. This map is decomposed into the sum of two components in orthogonal subspaces, one representing inter-individual differences in brain shape, and the other representing tumor-induced deformation. For a new tumor case, a partial observation of the sought deformation map is obtained via deformable image registration and is decomposed into the aforementioned spaces in order to estimate the mass-effect model parameters. Using this estimate, a simulation of tumor mass-effect is performed on the atlas image in order to generate an image that is similar to tumor patient's image, thereby facilitating the atlas registration process. Results for a real tumor case and a number of simulated tumor cases indicate significant reduction in the registration error due to the presented approach as compared to the direct use of deformable image registration.

AB - An approach to the deformable registration of three-dimensional brain tumor images to a normal brain atlas is presented. The approach involves the integration of three components: a biomechanical model of tumor mass-effect, a statistical approach to estimate the model's parameters, and a deformable image registration method. Statistical properties of the sought deformation map from the atlas to the image of a tumor patient are first obtained through tumor mass-effect simulations on normal brain images. This map is decomposed into the sum of two components in orthogonal subspaces, one representing inter-individual differences in brain shape, and the other representing tumor-induced deformation. For a new tumor case, a partial observation of the sought deformation map is obtained via deformable image registration and is decomposed into the aforementioned spaces in order to estimate the mass-effect model parameters. Using this estimate, a simulation of tumor mass-effect is performed on the atlas image in order to generate an image that is similar to tumor patient's image, thereby facilitating the atlas registration process. Results for a real tumor case and a number of simulated tumor cases indicate significant reduction in the registration error due to the presented approach as compared to the direct use of deformable image registration.

KW - Atlas registration

KW - Brain image registration

KW - Brain tumor

KW - Finite element model

KW - Neurosurgical planning

KW - Statistical deformation model

UR - https://www.scopus.com/pages/publications/33748632924

U2 - 10.1016/j.media.2006.06.005

DO - 10.1016/j.media.2006.06.005

M3 - Article

C2 - 16860588

AN - SCOPUS:33748632924

SN - 1361-8415

VL - 10

SP - 752

EP - 763

JO - Medical Image Analysis

JF - Medical Image Analysis

IS - 5

ER -

Deformable registration of brain tumor images via a statistical model of tumor-induced deformation

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this