Advertisement

Automated Quantification of Myocardial Infarction Using a Hidden Markov Random Field Model and the EM Algorithm

  • M. Viallon
  • Joel Spaltenstein
  • C. de Bourguignon
  • C. Vandroux
  • A. Ammor
  • W. Romero
  • O. Bernard
  • P. Croisille
  • P. ClarysseEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9126)

Abstract

Infarct size has been recognized as a good indicator of the functional status of the ischemic heart and to evaluate the impact of myocardial infarction therapies. Its assessment can be performed from late gadolinium enhancement magnetic resonance images. A number of methods have been proposed for the semi-automatic and automatic quantification of necrosis. We developed an automatic method based on a Markov random field framework and a region growing approach within an EM optimization, which enables segmentation of both necrosis and microvascular obstructions. The method has been evaluated on both synthetic data and 10 clinical cases in 3D and lead to the best results as compared to other conventional approaches and expertise.

Keywords

Late Gadolinium Enhancement Gaussian Mixture Model Markov Random Field Expectation Maximization Algorithm Microvascular Obstruction 
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.

References

  1. 1.
    Arai, A.: The cardiac magnetic resonance approach to assessing myocardial viability. J. Nucl. Cardiol. 18(6), 1095–1102 (2011)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Wu, K.C.: CMR of microvascular obstruction and hemorrhage in myocardial infarction. J. Cardiovasc. Magn. Reson. 14, 68 (2012)CrossRefGoogle Scholar
  3. 3.
    Kachenoura, N., Redheuil, A., Herment, A., Mousseaux, E., Frouin, F.: Robust assessment of the transmural extent of myocardial infarction in late gadolinium-enhanced MRI studies using appropriate angular and circumferential subdivision of the myocardium. Eur. Radiol. 18(10), 2140–2147 (2008)CrossRefGoogle Scholar
  4. 4.
    Positano, V., Pingitore, A., Giorgetti, A., Favilli, B., Santarelli, M.F., Landini, L., Marzullo, P., Lombardi, M.: A fast and effective method to assess myocardial necrosis by means of contrast magnetic resonance imaging. J. Cardiovasc. Magn. Reson. 7(2), 487–494 (2005)CrossRefGoogle Scholar
  5. 5.
    Hsu, L.-Y., Natanzon, A., Kellman, P., Hirsch, G.A., Aletras, A.H., Arai, A.E.: Quantitative myocardial infarction on delayed enhancement MRI. Part I: animal validation of an automated feature analysis and combined thresholding infarct sizing algorithm. J. Magn. Reson. Imaging 23(3), 298–308 (2006)CrossRefGoogle Scholar
  6. 6.
    Hsu, L.-Y., Ingkanisorn, W.P., Kellman, P., Aletras, A.H., Arai, A.E.: Quantitative myocardial infarction on delayed enhancement MRI. Part II: clinical application of an automated feature analysis and combined thresholding infarct sizing algorithm. J. Magn. Reson. Imaging 23(3), 309–314 (2006)CrossRefGoogle Scholar
  7. 7.
    Valindria, V. V., Angue, M., Vignon, N., Walker, P. M., Cochet, A., Lalande, A.: Automatic quantification of myocardial infarction from delayed enhancement MRI. In: 2012 Eighth International Conference on Signal Image Technology and Internet Based Systems, pp. 277–283 (2011)Google Scholar
  8. 8.
    Zhang, Y., Brady, M., Smith, S.: Segmentation of brain MR images through a hidden markov random field model and the expectation-maximization algorithm. IEEE Trans. Med. Imaging 20(1), 45–57 (2001)CrossRefGoogle Scholar
  9. 9.
    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 Trans. Image Process. 21(1), 241–251 (2012)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • M. Viallon
    • 1
    • 2
  • Joel Spaltenstein
    • 3
  • C. de Bourguignon
    • 2
  • C. Vandroux
    • 1
  • A. Ammor
    • 1
  • W. Romero
    • 1
  • O. Bernard
    • 1
  • P. Croisille
    • 1
    • 2
  • P. Clarysse
    • 1
    Email author
  1. 1.Université de Lyon, CREATIS, CNRS UMR5220, Inserm U1044, INSA-Lyon, Université Lyon 1LyonFrance
  2. 2.CHU Saint EtienneUniversité Jean MonnetSaint-ÉtienneFrance
  3. 3.Spaltenstein Natural ImageGenevaSwitzerland

Personalised recommendations