Multivariate segmentation of brain tissues by fusion of MRI and DTI data

Suyash P. Awate, Hui Zhang, Tony J Simon, James C. Gee

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

7 Citations (Scopus)

Abstract

This paper proposes a method to improve brain-tissue segmentation, especially in subcortical region, by fusing the information in structural magnetic resonance (MR) images and diffusion tensor (DT) images in a sound statistical framework. The proposed method incorporates the information in DT images by parameterizing the space of diffusion tensors, in a principled and efficient manner, based on a set of independent orthogonal invariants. The proposed method couples the Markov tissue statistics of the structural-MR intensities with the tissue statistics of the DT invariants to define multivariate/joint probability density functions (PDFs) that differentiate brain tissues. The paper shows that while the information in DT images can allow improved differentiation between tissues in the subcortical region, which comprises anatomical structures having smooth (blob-like) shapes, it can produce unreliable results in the cortical regions that depict convoluted sulci/gyri. The proposed method exploits these characteristics of the images by introducing an appropriate anisotropic distance metric in the multivariate feature space.

Original languageEnglish (US)
Title of host publication2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI
Pages213-216
Number of pages4
DOIs
StatePublished - 2008
Event2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI - Paris, France
Duration: May 14 2008May 17 2008

Other

Other2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI
CountryFrance
CityParis
Period5/14/085/17/08

Fingerprint

Magnetic resonance imaging
Tensors
Brain
Fusion reactions
Tissue
Magnetic resonance
Statistics
Probability density function
Acoustic waves

Keywords

  • DTI
  • MRI
  • Multivariate statistical analysis
  • Subcortical brain tissue segmentation

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Awate, S. P., Zhang, H., Simon, T. J., & Gee, J. C. (2008). Multivariate segmentation of brain tissues by fusion of MRI and DTI data. In 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI (pp. 213-216). [4540970] https://doi.org/10.1109/ISBI.2008.4540970

Multivariate segmentation of brain tissues by fusion of MRI and DTI data. / Awate, Suyash P.; Zhang, Hui; Simon, Tony J; Gee, James C.

2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. 2008. p. 213-216 4540970.

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

Awate, SP, Zhang, H, Simon, TJ & Gee, JC 2008, Multivariate segmentation of brain tissues by fusion of MRI and DTI data. in 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI., 4540970, pp. 213-216, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI, Paris, France, 5/14/08. https://doi.org/10.1109/ISBI.2008.4540970
Awate SP, Zhang H, Simon TJ, Gee JC. Multivariate segmentation of brain tissues by fusion of MRI and DTI data. In 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. 2008. p. 213-216. 4540970 https://doi.org/10.1109/ISBI.2008.4540970
Awate, Suyash P. ; Zhang, Hui ; Simon, Tony J ; Gee, James C. / Multivariate segmentation of brain tissues by fusion of MRI and DTI data. 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. 2008. pp. 213-216
@inproceedings{17db4ced242744d5878657836bb06568,
title = "Multivariate segmentation of brain tissues by fusion of MRI and DTI data",
abstract = "This paper proposes a method to improve brain-tissue segmentation, especially in subcortical region, by fusing the information in structural magnetic resonance (MR) images and diffusion tensor (DT) images in a sound statistical framework. The proposed method incorporates the information in DT images by parameterizing the space of diffusion tensors, in a principled and efficient manner, based on a set of independent orthogonal invariants. The proposed method couples the Markov tissue statistics of the structural-MR intensities with the tissue statistics of the DT invariants to define multivariate/joint probability density functions (PDFs) that differentiate brain tissues. The paper shows that while the information in DT images can allow improved differentiation between tissues in the subcortical region, which comprises anatomical structures having smooth (blob-like) shapes, it can produce unreliable results in the cortical regions that depict convoluted sulci/gyri. The proposed method exploits these characteristics of the images by introducing an appropriate anisotropic distance metric in the multivariate feature space.",
keywords = "DTI, MRI, Multivariate statistical analysis, Subcortical brain tissue segmentation",
author = "Awate, {Suyash P.} and Hui Zhang and Simon, {Tony J} and Gee, {James C.}",
year = "2008",
doi = "10.1109/ISBI.2008.4540970",
language = "English (US)",
isbn = "9781424420032",
pages = "213--216",
booktitle = "2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI",

}

TY - GEN

T1 - Multivariate segmentation of brain tissues by fusion of MRI and DTI data

AU - Awate, Suyash P.

AU - Zhang, Hui

AU - Simon, Tony J

AU - Gee, James C.

PY - 2008

Y1 - 2008

N2 - This paper proposes a method to improve brain-tissue segmentation, especially in subcortical region, by fusing the information in structural magnetic resonance (MR) images and diffusion tensor (DT) images in a sound statistical framework. The proposed method incorporates the information in DT images by parameterizing the space of diffusion tensors, in a principled and efficient manner, based on a set of independent orthogonal invariants. The proposed method couples the Markov tissue statistics of the structural-MR intensities with the tissue statistics of the DT invariants to define multivariate/joint probability density functions (PDFs) that differentiate brain tissues. The paper shows that while the information in DT images can allow improved differentiation between tissues in the subcortical region, which comprises anatomical structures having smooth (blob-like) shapes, it can produce unreliable results in the cortical regions that depict convoluted sulci/gyri. The proposed method exploits these characteristics of the images by introducing an appropriate anisotropic distance metric in the multivariate feature space.

AB - This paper proposes a method to improve brain-tissue segmentation, especially in subcortical region, by fusing the information in structural magnetic resonance (MR) images and diffusion tensor (DT) images in a sound statistical framework. The proposed method incorporates the information in DT images by parameterizing the space of diffusion tensors, in a principled and efficient manner, based on a set of independent orthogonal invariants. The proposed method couples the Markov tissue statistics of the structural-MR intensities with the tissue statistics of the DT invariants to define multivariate/joint probability density functions (PDFs) that differentiate brain tissues. The paper shows that while the information in DT images can allow improved differentiation between tissues in the subcortical region, which comprises anatomical structures having smooth (blob-like) shapes, it can produce unreliable results in the cortical regions that depict convoluted sulci/gyri. The proposed method exploits these characteristics of the images by introducing an appropriate anisotropic distance metric in the multivariate feature space.

KW - DTI

KW - MRI

KW - Multivariate statistical analysis

KW - Subcortical brain tissue segmentation

UR - http://www.scopus.com/inward/record.url?scp=51049121151&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51049121151&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2008.4540970

DO - 10.1109/ISBI.2008.4540970

M3 - Conference contribution

SN - 9781424420032

SP - 213

EP - 216

BT - 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI

ER -