Advertisement

Pulsative Flow Segmentation in MRA Image Series by AR Modeling and EM Algorithm

  • Ali Gooya
  • Hongen Liao
  • Kiyoshi Matsumiya
  • Ken Masamune
  • Takeyoshi Dohi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4091)

Abstract

Segmentation of CSF and pulsative blood flow, based on a single phase contrast MRA (PC-MRA) image can lead to imperfect classifications. In this paper, we present a novel automated flow segmentation method by using PC-MRA image series. The intensity time series of each pixel is modeled as an autoregressive (AR) process and features including the Linear Prediction Coefficients (LPC), covariance matrix of LPC and variance of prediction error are extracted from each profile. Bayesian classification of the feature space is then achieved using a non-Gaussian likelihood probability function and unknown parameters of the likelihood function are estimated by a generalized Expectation-Maximization (EM) algorithm. The efficiency of the method evaluated on both synthetic and real retrospective gated PC-MRA images indicate that robust segmentation of CSF and vessels can be achieved by using this method.

Keywords

Initial Segmentation Linear Prediction Coefficient Acardiac Twin Optimal Feature Selection Intensity Time Series 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baledent, O., Feugeas, M.C.H., Peretti, I.I., Jones, C.D., Roberts, E.F.: Cerebrospinal Fluid Dynamics and Relation with Blood Flow. Invest. Radiol. 36(7), 368–377 (2001)CrossRefGoogle Scholar
  2. 2.
    Chung, A.C.S., Noble, J.A., Summers, P.: Vascular segmentation of phase contrast magnetic resonance angiograms based on statistical mixture modeling and local phase coherence. IEEE Trans. Med. Imaging 23(12), 1490–1507 (2004)CrossRefGoogle Scholar
  3. 3.
    Gan, R., Wong, W.C.K., Chung, A.C.S.: Statistical cerebrovascular segmentation in three-dimensional rotational angiography based on maximum intensity projections. Med. Phys. 32(9), 3017–3028 (2005)CrossRefGoogle Scholar
  4. 4.
    Alperin, N., Lee, S.H.: PUBS: Pulsatility-Based Segmentation of Lumens Conducting Non-steady Flow. Magnetic Resonance in Medicine 49, 934–944 (2003)CrossRefGoogle Scholar
  5. 5.
    Hata, N., Wada, T., Kashima, K., Okada, Y., Kitagawa, M., Chiba, T.: Non-gated fetal MRI of umbilical blood flow in an acardiac twin. Pediatr Radiol. 35(8), 826–829 (2005)CrossRefGoogle Scholar
  6. 6.
    Kashyap, R.L.: Optimal Feature Selection and Decision Rules in Classification Problems with Time Series. IEEE Trans. Info. Theory 24(3), 281–288 (1978)MATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc. Series B 39, 1–38 (1977)MATHMathSciNetGoogle Scholar
  8. 8.
    Seber, G.A.F.: Multivariate Observations. Wiley, New York (1984)MATHCrossRefGoogle Scholar
  9. 9.
    Coleman, T.F., Li, Y.: An Interior, Trust Region Approach for Nonlinear Minimization Subject to Bounds. SIAM Journal on Optimization 6, 418–445 (1996)MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ali Gooya
    • 1
  • Hongen Liao
    • 1
  • Kiyoshi Matsumiya
    • 1
  • Ken Masamune
    • 1
  • Takeyoshi Dohi
    • 1
  1. 1.Graduate School of Information Science and Technologythe University of TokyoTokyoJapan

Personalised recommendations