Tissue Classification from Brain Perfusion MR Images Using Expectation-Maximization Algorithm Initialized by Hierarchical Clustering on Whitened Data: 13th International Conference on Biomedical Engineering, ICBME 2008

Yu-Te Wu, Yen-Chun Chou, Chia-Feng Lu, Shang-Ran Huang, Wan-Yuo Guo, AMTI; BES Technology; DELSYS; VICON; INSTRON; et al

Research output: Contribution to conferenceOther

3 Citations (Scopus)

Abstract

Classification of different perfusion compartments in the brain is important to the profound analysis of brain perfusion. We presents a method based on a mixture of multivariate Gaussians (MoMG) and the expectation-maximization (EM) algorithm initialized by the results of hierarchical clustering (HC) on the whitened data to automatically dissect various perfusion compartments from dynamic susceptibility contrast (DSC) MR images so that each compartment comprises pixels of similar signal-time curves. Monte Carlo simulations have been designed and executed to assess the performance of the proposed method under various signal-to-noise ratios (SNRs). The results of simulations showed that using EM initialized by HC on whitened data produce the best accuracy of segmentation. Five healthy volunteers participated in this study for the validation of this method. The averaged ratios of gray matter to white matter for relative cerebral blood volume (rCBV), relative cerebral blood flow (rCBF) and mean transition time (MTT) derived from 5 normal subjects were 2.196±0.097, 2.259±0.119, and 0.968±0.023 which are in good agreement with those reported in the literature. The proposed method can subserve the diagnosis and assessment of various diseases involving the changes of cerebral blood distribution.
Original languageEnglish
Pages714-717
Number of pages4
DOIs
Publication statusPublished - 2009
Externally publishedYes

Fingerprint

Biomedical engineering
Brain
Blood
Tissue
Signal to noise ratio
Pixels

Keywords

  • Expectation-maximization algorithm
  • Hierarchical clustering
  • MR perfusion
  • Segmentation
  • Whitening
  • Cerebral blood flow
  • Cerebral blood volume
  • Dynamic susceptibility Contrast
  • Expectation-maximization algorithms
  • Hier-archical clustering
  • Tissue classification
  • Biomedical engineering
  • Diagnosis
  • Image segmentation
  • Magnetic resonance imaging
  • Magnetic susceptibility
  • Monte Carlo methods
  • Algorithms

Cite this

Tissue Classification from Brain Perfusion MR Images Using Expectation-Maximization Algorithm Initialized by Hierarchical Clustering on Whitened Data : 13th International Conference on Biomedical Engineering, ICBME 2008. / Wu, Yu-Te; Chou, Yen-Chun; Lu, Chia-Feng; Huang, Shang-Ran; Guo, Wan-Yuo; al, AMTI; BES Technology; DELSYS; VICON; INSTRON; et.

2009. 714-717.

Research output: Contribution to conferenceOther

@conference{8a4a43784132414abcf0157f3b5a4b03,
title = "Tissue Classification from Brain Perfusion MR Images Using Expectation-Maximization Algorithm Initialized by Hierarchical Clustering on Whitened Data: 13th International Conference on Biomedical Engineering, ICBME 2008",
abstract = "Classification of different perfusion compartments in the brain is important to the profound analysis of brain perfusion. We presents a method based on a mixture of multivariate Gaussians (MoMG) and the expectation-maximization (EM) algorithm initialized by the results of hierarchical clustering (HC) on the whitened data to automatically dissect various perfusion compartments from dynamic susceptibility contrast (DSC) MR images so that each compartment comprises pixels of similar signal-time curves. Monte Carlo simulations have been designed and executed to assess the performance of the proposed method under various signal-to-noise ratios (SNRs). The results of simulations showed that using EM initialized by HC on whitened data produce the best accuracy of segmentation. Five healthy volunteers participated in this study for the validation of this method. The averaged ratios of gray matter to white matter for relative cerebral blood volume (rCBV), relative cerebral blood flow (rCBF) and mean transition time (MTT) derived from 5 normal subjects were 2.196±0.097, 2.259±0.119, and 0.968±0.023 which are in good agreement with those reported in the literature. The proposed method can subserve the diagnosis and assessment of various diseases involving the changes of cerebral blood distribution.",
keywords = "Expectation-maximization algorithm, Hierarchical clustering, MR perfusion, Segmentation, Whitening, Cerebral blood flow, Cerebral blood volume, Dynamic susceptibility Contrast, Expectation-maximization algorithms, Hier-archical clustering, Tissue classification, Biomedical engineering, Diagnosis, Image segmentation, Magnetic resonance imaging, Magnetic susceptibility, Monte Carlo methods, Algorithms",
author = "Yu-Te Wu and Yen-Chun Chou and Chia-Feng Lu and Shang-Ran Huang and Wan-Yuo Guo and al, {AMTI; BES Technology; DELSYS; VICON; INSTRON; et}",
note = "會議代碼: 101867 Export Date: 31 March 2016 通訊地址: Department of Biomedical Imaging and Radiological Sciences, National Yang-Ming University, No.155, Sec.2, Linong Street, Taipei, Taiwan 參考文獻: Zierler, K.L., Theoretical basis of indicator-dilution methods for measuring flow and volume (1962) Circulation Research, 10, pp. 393-407; Hyvarinen, A., Oja, E., A fast fixed-point algorithm for independent component analysis (1997) Neural Computation, 9 (7), pp. 1483-1492; Bishop, C.M., (1995) Neural networks for pattern recognition, , Oxford University Press, Oxford, UK; Wishart, D., An algorithm for hierarchical classifications (1969) Biometrics, 25, pp. 165-170; Schwarz, G., Estimating the dimension of a model (1978) Ann. Stat., 6, pp. 461-464; Wu, Y.T., Chou, Y.C., Guo, W.Y., Classification of spatiotemporal hemodynamics from brain perfusion MR images using expectation-maximization estimation with finite mixture of multivariate Gaussian distrubutions (2007) Magn. Reson. Med., 57 (1), pp. 181-191; Otsu, N., A threshold selection method froim gray-level histograms (1979) IEEE Trans. Syst. Man Cybern., 9 (1), pp. 62-66; Ostergaard, L., Weisskoff, R.M., Chesler, D.A., High resolution measurement of cerebral blood flow using intravascular tracer bolus passages (1996) Part I: Mathematical approach and statistical analysis. Magn. Reson. Med., 36 (5), pp. 715-725; Calamante, F., Thomas, D.L., Pell, G.S., Measuring cerebral blood flow using magnetic resonance imaging techniques (1999) J. Cereb. Blood Flow Metab., 19 (7), pp. 701-735",
year = "2009",
doi = "10.1007/978-3-540-92841-6_175",
language = "English",
pages = "714--717",

}

TY - CONF

T1 - Tissue Classification from Brain Perfusion MR Images Using Expectation-Maximization Algorithm Initialized by Hierarchical Clustering on Whitened Data

T2 - 13th International Conference on Biomedical Engineering, ICBME 2008

AU - Wu, Yu-Te

AU - Chou, Yen-Chun

AU - Lu, Chia-Feng

AU - Huang, Shang-Ran

AU - Guo, Wan-Yuo

AU - al, AMTI; BES Technology; DELSYS; VICON; INSTRON; et

N1 - 會議代碼: 101867 Export Date: 31 March 2016 通訊地址: Department of Biomedical Imaging and Radiological Sciences, National Yang-Ming University, No.155, Sec.2, Linong Street, Taipei, Taiwan 參考文獻: Zierler, K.L., Theoretical basis of indicator-dilution methods for measuring flow and volume (1962) Circulation Research, 10, pp. 393-407; Hyvarinen, A., Oja, E., A fast fixed-point algorithm for independent component analysis (1997) Neural Computation, 9 (7), pp. 1483-1492; Bishop, C.M., (1995) Neural networks for pattern recognition, , Oxford University Press, Oxford, UK; Wishart, D., An algorithm for hierarchical classifications (1969) Biometrics, 25, pp. 165-170; Schwarz, G., Estimating the dimension of a model (1978) Ann. Stat., 6, pp. 461-464; Wu, Y.T., Chou, Y.C., Guo, W.Y., Classification of spatiotemporal hemodynamics from brain perfusion MR images using expectation-maximization estimation with finite mixture of multivariate Gaussian distrubutions (2007) Magn. Reson. Med., 57 (1), pp. 181-191; Otsu, N., A threshold selection method froim gray-level histograms (1979) IEEE Trans. Syst. Man Cybern., 9 (1), pp. 62-66; Ostergaard, L., Weisskoff, R.M., Chesler, D.A., High resolution measurement of cerebral blood flow using intravascular tracer bolus passages (1996) Part I: Mathematical approach and statistical analysis. Magn. Reson. Med., 36 (5), pp. 715-725; Calamante, F., Thomas, D.L., Pell, G.S., Measuring cerebral blood flow using magnetic resonance imaging techniques (1999) J. Cereb. Blood Flow Metab., 19 (7), pp. 701-735

PY - 2009

Y1 - 2009

N2 - Classification of different perfusion compartments in the brain is important to the profound analysis of brain perfusion. We presents a method based on a mixture of multivariate Gaussians (MoMG) and the expectation-maximization (EM) algorithm initialized by the results of hierarchical clustering (HC) on the whitened data to automatically dissect various perfusion compartments from dynamic susceptibility contrast (DSC) MR images so that each compartment comprises pixels of similar signal-time curves. Monte Carlo simulations have been designed and executed to assess the performance of the proposed method under various signal-to-noise ratios (SNRs). The results of simulations showed that using EM initialized by HC on whitened data produce the best accuracy of segmentation. Five healthy volunteers participated in this study for the validation of this method. The averaged ratios of gray matter to white matter for relative cerebral blood volume (rCBV), relative cerebral blood flow (rCBF) and mean transition time (MTT) derived from 5 normal subjects were 2.196±0.097, 2.259±0.119, and 0.968±0.023 which are in good agreement with those reported in the literature. The proposed method can subserve the diagnosis and assessment of various diseases involving the changes of cerebral blood distribution.

AB - Classification of different perfusion compartments in the brain is important to the profound analysis of brain perfusion. We presents a method based on a mixture of multivariate Gaussians (MoMG) and the expectation-maximization (EM) algorithm initialized by the results of hierarchical clustering (HC) on the whitened data to automatically dissect various perfusion compartments from dynamic susceptibility contrast (DSC) MR images so that each compartment comprises pixels of similar signal-time curves. Monte Carlo simulations have been designed and executed to assess the performance of the proposed method under various signal-to-noise ratios (SNRs). The results of simulations showed that using EM initialized by HC on whitened data produce the best accuracy of segmentation. Five healthy volunteers participated in this study for the validation of this method. The averaged ratios of gray matter to white matter for relative cerebral blood volume (rCBV), relative cerebral blood flow (rCBF) and mean transition time (MTT) derived from 5 normal subjects were 2.196±0.097, 2.259±0.119, and 0.968±0.023 which are in good agreement with those reported in the literature. The proposed method can subserve the diagnosis and assessment of various diseases involving the changes of cerebral blood distribution.

KW - Expectation-maximization algorithm

KW - Hierarchical clustering

KW - MR perfusion

KW - Segmentation

KW - Whitening

KW - Cerebral blood flow

KW - Cerebral blood volume

KW - Dynamic susceptibility Contrast

KW - Expectation-maximization algorithms

KW - Hier-archical clustering

KW - Tissue classification

KW - Biomedical engineering

KW - Diagnosis

KW - Image segmentation

KW - Magnetic resonance imaging

KW - Magnetic susceptibility

KW - Monte Carlo methods

KW - Algorithms

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-84891953660&partnerID=40&md5=dfad6b8c65550d5889f2f1fe4f5baa2f

UR - https://www.scopus.com/results/citedbyresults.uri?sort=plf-f&cite=2-s2.0-84891953660&src=s&imp=t&sid=b542b4d3771056a429a48ced5ae4f8bb&sot=cite&sdt=a&sl=0&origin=recordpage&editSaveSearch=&txGid=d565b908b7f775c82513ecec4632d2d3

U2 - 10.1007/978-3-540-92841-6_175

DO - 10.1007/978-3-540-92841-6_175

M3 - Other

SP - 714

EP - 717

ER -