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

Ashraf Mohamed, Dinggang Shen, Christos Davatzikos

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

An approach to 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 desired deformation map 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, and the other involving tumor-induced deformation. For a new tumor case, a partial observation of the desired 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 to generate an image that is more similar to brain tumor image, thereby facilitating the atlas registration process. Results for a real and a simulated tumor case indicate significant reduction in the registration error due to the presented approach as compared to the direct use of deformable image registration.

Original languageEnglish
Title of host publicationMedical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Pages263-270
Number of pages8
Volume8
EditionPt 2
Publication statusPublished - 2005 Dec 1
Externally publishedYes

Fingerprint

Statistical Models
Brain Neoplasms
Atlases
Neoplasms
Brain
Individuality
Observation

Cite this

Mohamed, A., Shen, D., & Davatzikos, C. (2005). Deformable registration of brain tumor images via a statistical model of tumor-induced deformation. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention (Pt 2 ed., Vol. 8, pp. 263-270)

Deformable registration of brain tumor images via a statistical model of tumor-induced deformation. / Mohamed, Ashraf; Shen, Dinggang; Davatzikos, Christos.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 8 Pt 2. ed. 2005. p. 263-270.

Research output: Chapter in Book/Report/Conference proceedingChapter

Mohamed, A, Shen, D & Davatzikos, C 2005, Deformable registration of brain tumor images via a statistical model of tumor-induced deformation. in Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Pt 2 edn, vol. 8, pp. 263-270.
Mohamed A, Shen D, Davatzikos C. Deformable registration of brain tumor images via a statistical model of tumor-induced deformation. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Pt 2 ed. Vol. 8. 2005. p. 263-270
Mohamed, Ashraf ; Shen, Dinggang ; Davatzikos, Christos. / Deformable registration of brain tumor images via a statistical model of tumor-induced deformation. Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 8 Pt 2. ed. 2005. pp. 263-270
@inbook{f21172cc812a40a88f7dc89482be4eb5,
title = "Deformable registration of brain tumor images via a statistical model of tumor-induced deformation.",
abstract = "An approach to 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 desired deformation map 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, and the other involving tumor-induced deformation. For a new tumor case, a partial observation of the desired 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 to generate an image that is more similar to brain tumor image, thereby facilitating the atlas registration process. Results for a real and a simulated tumor case indicate significant reduction in the registration error due to the presented approach as compared to the direct use of deformable image registration.",
author = "Ashraf Mohamed and Dinggang Shen and Christos Davatzikos",
year = "2005",
month = "12",
day = "1",
language = "English",
volume = "8",
pages = "263--270",
booktitle = "Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention",
edition = "Pt 2",

}

TY - CHAP

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

AU - Mohamed, Ashraf

AU - Shen, Dinggang

AU - Davatzikos, Christos

PY - 2005/12/1

Y1 - 2005/12/1

N2 - An approach to 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 desired deformation map 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, and the other involving tumor-induced deformation. For a new tumor case, a partial observation of the desired 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 to generate an image that is more similar to brain tumor image, thereby facilitating the atlas registration process. Results for a real and a simulated tumor case 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 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 desired deformation map 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, and the other involving tumor-induced deformation. For a new tumor case, a partial observation of the desired 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 to generate an image that is more similar to brain tumor image, thereby facilitating the atlas registration process. Results for a real and a simulated tumor case indicate significant reduction in the registration error due to the presented approach as compared to the direct use of deformable image registration.

UR - http://www.scopus.com/inward/record.url?scp=84883842611&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883842611&partnerID=8YFLogxK

M3 - Chapter

C2 - 16685968

VL - 8

SP - 263

EP - 270

BT - Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

ER -