Advertisement

Fast Fully Automatic Segmentation of the Myocardium in 2D Cine MR Images

  • Sandro Queirós
  • Daniel Barbosa
  • Brecht Heyde
  • Pedro Morais
  • Denis Friboulet
  • Piet Claus
  • Olivier Bernard
  • Jan D’hooge
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7945)

Abstract

A novel automatic initialization procedure for left ventricle (LV) cardiac magnetic resonance (CMR) segmentation is proposed through the combination of a LV localization method based on multilevel Otsu thresholding and an elliptical annular template matching algorithm. We then propose to adapt the recent B-spline Explicit Active Surfaces (BEAS) framework to the properties of CMR images by integrating two dedicated energy terms: a weighted localized Chan-Vese region-based energy to explicitly control the equilibrium point between the two regions around each interface and a combined local and global region-based formulation for the myocardial region. The proposed method has been validated on 45 mid-ventricular images taken from the 2009 MICCAI LV segmentation challenge. Results show the efficiency of our method both in terms of shape accuracy and computational times.

Keywords

Fast segmentation cardiac magnetic resonance (CMR) imaging automatic initialization 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Miller, C., Pearce, K., Jordan, P., Argyle, R., Clark, D., Stout, M., Ray, S., Schmitt, M.: Comparison of real-time three-dimensional echocardiography with cardiovascular magnetic resonance for left ventricular volumetric assessment in unselected patients. Eur. Heart J. Cardiovasc. Imag. 13(2), 187–195 (2012)CrossRefGoogle Scholar
  2. 2.
    Petitjean, C., Dacher, J.: A review of segmentation methods in short axis cardiac MR images. Medical Image Analysis 15(2), 169–184 (2011)CrossRefGoogle Scholar
  3. 3.
    Barbosa, D., Dietenbeck, T., Schaerer, J., D’hooge, J., Friboulet, D., Bernard, O.: B-spline explicit active surfaces: An efficient framework for real-time 3-D region-based segmentation. IEEE T. Image. Process. 21(1), 241–251 (2012)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Chen, T., Babb, J., Kellman, P., Axel, L., Kim, D.: Semiautomated segmentation of myocardial contours for fast strain analysis in cine displacement-encoded MRI. IEEE T. Med. Imaging 27(8), 1084–1094 (2008)CrossRefGoogle Scholar
  5. 5.
    Lankton, S., Tannenbaum, A.: Localizing region-based active contours. IEEE T. Image. Process. 17(11), 2029–2039 (2008)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Barbosa, D., Bernard, O., Savu, O., Dietenbeck, T., Heyde, B., Claus, P., Friboulet, D., D’hooge, J.: Coupled B-spline active geometric functions for myocardial segmentation: A localized region-based approach. In: IEEE IUS, pp. 1648–1651 (2010)Google Scholar
  7. 7.
    Lu, Y., Radau, P., Connelly, K., Dick, A., Wright, G.A.: Segmentation of left ventricle in cardiac cine MRI: An automatic image-driven method. In: Ayache, N., Delingette, H., Sermesant, M. (eds.) FIMH 2009. LNCS, vol. 5528, pp. 339–347. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  8. 8.
    Ciofolo, C., Fradkin, M., Mory, B., Hautvast, G., Breeuwer, M.: Automatic myocardium segmentation in late-enhancement MRI. In: IEEE ISBI, pp. 225–228 (2008)Google Scholar
  9. 9.
    Otsu, N.: A threshold selection method from gray-level histograms. Automatica 11(285-296), 23–27 (1975)Google Scholar
  10. 10.
    Radau, P., Lu, Y., Connelly, K., Paul, G., Dick, A., Wright, G.: Evaluation framework for algorithms segmenting short axis cardiac MRI. MIDAS Journal (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Sandro Queirós
    • 1
  • Daniel Barbosa
    • 1
    • 2
    • 3
  • Brecht Heyde
    • 1
  • Pedro Morais
    • 1
  • Denis Friboulet
    • 2
    • 3
  • Piet Claus
    • 1
  • Olivier Bernard
    • 2
    • 3
  • Jan D’hooge
    • 1
  1. 1.Cardiovascular Imaging and DynamicsUniversity of LeuvenLeuvenBelgium
  2. 2.CREATIS, CNRS UMR5220, INSERM U630Université de LyonFrance
  3. 3.INSA-LYONUniversité Lyon 1France

Personalised recommendations