Parallel optimization of tumor model parameters for fast registration of brain tumor images

Evangelia I. Zacharaki, Cosmina S. Hogea, Dinggang Shen, George Biros, Christos Davatzikos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

The motivation of this work is to register MR brain tumor images with a brain atlas. Such a registration method can make possible the pooling of data from different brain tumor patients into a common stereotaxic space, thereby enabling the construction of statistical brain tumor atlases. Moreover, it allows the mapping of neuroanatomical brain atlases into the patient's space, for segmenting brains and thus facilitating surgical or radiotherapy treatment planning. However, the methods developed for registration of normal brain images are not directly applicable to the registration of a normal atlas with a tumor-bearing image, due to substantial dissimilarity and lack of equivalent image content between the two images, as well as severe deformation or shift of anatomical structures around the tumor. Accordingly, a model that can simulate brain tissue death and deformation induced by the tumor is considered to facilitate the registration. Such tumor growth simulation models are usually initialized by placing a small seed in the normal atlas. The shape, size and location of the initial seed are critical for achieving topological equivalence between the atlas and patient's images. In this study, we focus on the automatic estimation of these parameters, pertaining to tumor simulation. In particular, we propose an objective function reflecting feature-based similarity and elastic stretching energy and optimize it with APPSPACK (Asynchronous Parallel Pattern Search), for achieving significant reduction of the computational cost. The results indicate that the registration accuracy is high in areas around the tumor, as well as in the healthy portion of the brain.

Original languageEnglish
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume6914
DOIs
Publication statusPublished - 2008 May 19
Externally publishedYes
EventMedical Imaging 2008: Image Processing - San Diego, CA, United States
Duration: 2008 Feb 172008 Feb 19

Other

OtherMedical Imaging 2008: Image Processing
CountryUnited States
CitySan Diego, CA
Period08/2/1708/2/19

Fingerprint

Tumors
Brain
Bearings (structural)
Radiotherapy
Stretching
Seed
Tissue
Planning
Costs

Keywords

  • APPSPACK
  • Atlas-based segmentation
  • Brain tumor
  • Deformable registration
  • Tumor simulation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Zacharaki, E. I., Hogea, C. S., Shen, D., Biros, G., & Davatzikos, C. (2008). Parallel optimization of tumor model parameters for fast registration of brain tumor images. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 6914). [69140K] https://doi.org/10.1117/12.767788

Parallel optimization of tumor model parameters for fast registration of brain tumor images. / Zacharaki, Evangelia I.; Hogea, Cosmina S.; Shen, Dinggang; Biros, George; Davatzikos, Christos.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6914 2008. 69140K.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zacharaki, EI, Hogea, CS, Shen, D, Biros, G & Davatzikos, C 2008, Parallel optimization of tumor model parameters for fast registration of brain tumor images. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 6914, 69140K, Medical Imaging 2008: Image Processing, San Diego, CA, United States, 08/2/17. https://doi.org/10.1117/12.767788
Zacharaki EI, Hogea CS, Shen D, Biros G, Davatzikos C. Parallel optimization of tumor model parameters for fast registration of brain tumor images. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6914. 2008. 69140K https://doi.org/10.1117/12.767788
Zacharaki, Evangelia I. ; Hogea, Cosmina S. ; Shen, Dinggang ; Biros, George ; Davatzikos, Christos. / Parallel optimization of tumor model parameters for fast registration of brain tumor images. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6914 2008.
@inproceedings{2efe8727b28e498986b847f76c50d1ea,
title = "Parallel optimization of tumor model parameters for fast registration of brain tumor images",
abstract = "The motivation of this work is to register MR brain tumor images with a brain atlas. Such a registration method can make possible the pooling of data from different brain tumor patients into a common stereotaxic space, thereby enabling the construction of statistical brain tumor atlases. Moreover, it allows the mapping of neuroanatomical brain atlases into the patient's space, for segmenting brains and thus facilitating surgical or radiotherapy treatment planning. However, the methods developed for registration of normal brain images are not directly applicable to the registration of a normal atlas with a tumor-bearing image, due to substantial dissimilarity and lack of equivalent image content between the two images, as well as severe deformation or shift of anatomical structures around the tumor. Accordingly, a model that can simulate brain tissue death and deformation induced by the tumor is considered to facilitate the registration. Such tumor growth simulation models are usually initialized by placing a small seed in the normal atlas. The shape, size and location of the initial seed are critical for achieving topological equivalence between the atlas and patient's images. In this study, we focus on the automatic estimation of these parameters, pertaining to tumor simulation. In particular, we propose an objective function reflecting feature-based similarity and elastic stretching energy and optimize it with APPSPACK (Asynchronous Parallel Pattern Search), for achieving significant reduction of the computational cost. The results indicate that the registration accuracy is high in areas around the tumor, as well as in the healthy portion of the brain.",
keywords = "APPSPACK, Atlas-based segmentation, Brain tumor, Deformable registration, Tumor simulation",
author = "Zacharaki, {Evangelia I.} and Hogea, {Cosmina S.} and Dinggang Shen and George Biros and Christos Davatzikos",
year = "2008",
month = "5",
day = "19",
doi = "10.1117/12.767788",
language = "English",
isbn = "9780819470980",
volume = "6914",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Parallel optimization of tumor model parameters for fast registration of brain tumor images

AU - Zacharaki, Evangelia I.

AU - Hogea, Cosmina S.

AU - Shen, Dinggang

AU - Biros, George

AU - Davatzikos, Christos

PY - 2008/5/19

Y1 - 2008/5/19

N2 - The motivation of this work is to register MR brain tumor images with a brain atlas. Such a registration method can make possible the pooling of data from different brain tumor patients into a common stereotaxic space, thereby enabling the construction of statistical brain tumor atlases. Moreover, it allows the mapping of neuroanatomical brain atlases into the patient's space, for segmenting brains and thus facilitating surgical or radiotherapy treatment planning. However, the methods developed for registration of normal brain images are not directly applicable to the registration of a normal atlas with a tumor-bearing image, due to substantial dissimilarity and lack of equivalent image content between the two images, as well as severe deformation or shift of anatomical structures around the tumor. Accordingly, a model that can simulate brain tissue death and deformation induced by the tumor is considered to facilitate the registration. Such tumor growth simulation models are usually initialized by placing a small seed in the normal atlas. The shape, size and location of the initial seed are critical for achieving topological equivalence between the atlas and patient's images. In this study, we focus on the automatic estimation of these parameters, pertaining to tumor simulation. In particular, we propose an objective function reflecting feature-based similarity and elastic stretching energy and optimize it with APPSPACK (Asynchronous Parallel Pattern Search), for achieving significant reduction of the computational cost. The results indicate that the registration accuracy is high in areas around the tumor, as well as in the healthy portion of the brain.

AB - The motivation of this work is to register MR brain tumor images with a brain atlas. Such a registration method can make possible the pooling of data from different brain tumor patients into a common stereotaxic space, thereby enabling the construction of statistical brain tumor atlases. Moreover, it allows the mapping of neuroanatomical brain atlases into the patient's space, for segmenting brains and thus facilitating surgical or radiotherapy treatment planning. However, the methods developed for registration of normal brain images are not directly applicable to the registration of a normal atlas with a tumor-bearing image, due to substantial dissimilarity and lack of equivalent image content between the two images, as well as severe deformation or shift of anatomical structures around the tumor. Accordingly, a model that can simulate brain tissue death and deformation induced by the tumor is considered to facilitate the registration. Such tumor growth simulation models are usually initialized by placing a small seed in the normal atlas. The shape, size and location of the initial seed are critical for achieving topological equivalence between the atlas and patient's images. In this study, we focus on the automatic estimation of these parameters, pertaining to tumor simulation. In particular, we propose an objective function reflecting feature-based similarity and elastic stretching energy and optimize it with APPSPACK (Asynchronous Parallel Pattern Search), for achieving significant reduction of the computational cost. The results indicate that the registration accuracy is high in areas around the tumor, as well as in the healthy portion of the brain.

KW - APPSPACK

KW - Atlas-based segmentation

KW - Brain tumor

KW - Deformable registration

KW - Tumor simulation

UR - http://www.scopus.com/inward/record.url?scp=43449112383&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=43449112383&partnerID=8YFLogxK

U2 - 10.1117/12.767788

DO - 10.1117/12.767788

M3 - Conference contribution

AN - SCOPUS:43449112383

SN - 9780819470980

VL - 6914

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -