ORBIT: A multiresolution framework for deformable registration of brain tumor images

Evangelia I. Zacharaki, Dinggang Shen, Seung Koo Lee, Christos Davatzikos

Research output: Contribution to journalArticle

70 Citations (Scopus)

Abstract

A deformable registration method is proposed for registering a normal brain atlas with images of brain tumor patients. The registration is facilitated by first simulating the tumor mass effect in the normal atlas in order to create an atlas image that is as similar as possible to the patient's image. An optimization framework is used to optimize the location of tumor seed as well as other parameters of the tumor growth model, based on the pattern of deformation around the tumor region. In particular, the optimization is implemented in a multiresolution and hierarchical scheme, and it is accelerated by using a principal component analysis (PCA)-based model of tumor growth and mass effect, trained on a computationally more expensive biomechanical model. Validation on simulated and real images shows that the proposed registration framework, referred to as ORBIT (optimization of tumor parameters and registration of brain images with tumors), outperforms other available registration methods particularly for the regions close to the tumor, and it has the potential to assist in constructing statistical atlases from tumor-diseased brain images.

Original languageEnglish
Article number4436040
Pages (from-to)1003-1017
Number of pages15
JournalIEEE Transactions on Medical Imaging
Volume27
Issue number8
DOIs
Publication statusPublished - 2008 Aug 1
Externally publishedYes

Fingerprint

Brain Neoplasms
Tumors
Brain
Atlases
Neoplasms
Brain Diseases
Growth
Principal Component Analysis
Seeds
Principal component analysis
Seed

Keywords

  • Atlas registration
  • Brain tumor
  • Deformable registration
  • Image attributes
  • Tumor growth model

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology
  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

ORBIT : A multiresolution framework for deformable registration of brain tumor images. / Zacharaki, Evangelia I.; Shen, Dinggang; Lee, Seung Koo; Davatzikos, Christos.

In: IEEE Transactions on Medical Imaging, Vol. 27, No. 8, 4436040, 01.08.2008, p. 1003-1017.

Research output: Contribution to journalArticle

Zacharaki, Evangelia I. ; Shen, Dinggang ; Lee, Seung Koo ; Davatzikos, Christos. / ORBIT : A multiresolution framework for deformable registration of brain tumor images. In: IEEE Transactions on Medical Imaging. 2008 ; Vol. 27, No. 8. pp. 1003-1017.
@article{abd446ad829347428f0ca18e49e5b3e6,
title = "ORBIT: A multiresolution framework for deformable registration of brain tumor images",
abstract = "A deformable registration method is proposed for registering a normal brain atlas with images of brain tumor patients. The registration is facilitated by first simulating the tumor mass effect in the normal atlas in order to create an atlas image that is as similar as possible to the patient's image. An optimization framework is used to optimize the location of tumor seed as well as other parameters of the tumor growth model, based on the pattern of deformation around the tumor region. In particular, the optimization is implemented in a multiresolution and hierarchical scheme, and it is accelerated by using a principal component analysis (PCA)-based model of tumor growth and mass effect, trained on a computationally more expensive biomechanical model. Validation on simulated and real images shows that the proposed registration framework, referred to as ORBIT (optimization of tumor parameters and registration of brain images with tumors), outperforms other available registration methods particularly for the regions close to the tumor, and it has the potential to assist in constructing statistical atlases from tumor-diseased brain images.",
keywords = "Atlas registration, Brain tumor, Deformable registration, Image attributes, Tumor growth model",
author = "Zacharaki, {Evangelia I.} and Dinggang Shen and Lee, {Seung Koo} and Christos Davatzikos",
year = "2008",
month = "8",
day = "1",
doi = "10.1109/TMI.2008.916954",
language = "English",
volume = "27",
pages = "1003--1017",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "8",

}

TY - JOUR

T1 - ORBIT

T2 - A multiresolution framework for deformable registration of brain tumor images

AU - Zacharaki, Evangelia I.

AU - Shen, Dinggang

AU - Lee, Seung Koo

AU - Davatzikos, Christos

PY - 2008/8/1

Y1 - 2008/8/1

N2 - A deformable registration method is proposed for registering a normal brain atlas with images of brain tumor patients. The registration is facilitated by first simulating the tumor mass effect in the normal atlas in order to create an atlas image that is as similar as possible to the patient's image. An optimization framework is used to optimize the location of tumor seed as well as other parameters of the tumor growth model, based on the pattern of deformation around the tumor region. In particular, the optimization is implemented in a multiresolution and hierarchical scheme, and it is accelerated by using a principal component analysis (PCA)-based model of tumor growth and mass effect, trained on a computationally more expensive biomechanical model. Validation on simulated and real images shows that the proposed registration framework, referred to as ORBIT (optimization of tumor parameters and registration of brain images with tumors), outperforms other available registration methods particularly for the regions close to the tumor, and it has the potential to assist in constructing statistical atlases from tumor-diseased brain images.

AB - A deformable registration method is proposed for registering a normal brain atlas with images of brain tumor patients. The registration is facilitated by first simulating the tumor mass effect in the normal atlas in order to create an atlas image that is as similar as possible to the patient's image. An optimization framework is used to optimize the location of tumor seed as well as other parameters of the tumor growth model, based on the pattern of deformation around the tumor region. In particular, the optimization is implemented in a multiresolution and hierarchical scheme, and it is accelerated by using a principal component analysis (PCA)-based model of tumor growth and mass effect, trained on a computationally more expensive biomechanical model. Validation on simulated and real images shows that the proposed registration framework, referred to as ORBIT (optimization of tumor parameters and registration of brain images with tumors), outperforms other available registration methods particularly for the regions close to the tumor, and it has the potential to assist in constructing statistical atlases from tumor-diseased brain images.

KW - Atlas registration

KW - Brain tumor

KW - Deformable registration

KW - Image attributes

KW - Tumor growth model

UR - http://www.scopus.com/inward/record.url?scp=43449092116&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=43449092116&partnerID=8YFLogxK

U2 - 10.1109/TMI.2008.916954

DO - 10.1109/TMI.2008.916954

M3 - Article

C2 - 18672419

AN - SCOPUS:43449092116

VL - 27

SP - 1003

EP - 1017

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 8

M1 - 4436040

ER -