Advertisement

Modified Expectation Maximization Algorithm for MRI Segmentation

  • Ramiro Donoso
  • Alejandro Veloz
  • Héctor Allende
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6419)

Abstract

Magnetic Resonance Image segmentation is a fundamental task in a wide variety of computed-based medical applications that support therapy, diagnostic and medical applications. In this work, spatial information is included for estimating paramaters of a finite mixture model, with gaussian distribution assumption, using a modified version of the well-know Expectation Maximization algorithm proposed in [3]. Our approach is based on aggregating a transition step between E-step and M-step, that includes the information of spatial dependences between neighboring pixels.

Our proposal is compared with other approaches proposed in the image segmentation literature using the size and shape test, obtaining accurate and robust results in the presence of noise.

Keywords

Expectation Maximization algorithm Finite Mixture models spatial information Magnetic Resonance Imaging segmentation 

References

  1. 1.
    Gering, D., Nabavi, A., Kikinis, R., Hata, N., O’Donnell, L., Grimson, W., Jolesz, F., Black, P., Wells, W.: An Integrated Visualization System for Surgical Planning and Guidance Using Image Fusion and an Open MR. Journal of Magnetic Resonance Imaging 13, 967–975 (2001)CrossRefGoogle Scholar
  2. 2.
    Ambroise, C., Govaert, G.: Spatial Clustering and the EM Algorithm, Tech. report, Université de technologie de Compiègne, France (1996)Google Scholar
  3. 3.
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. Journal of The Royal Statistical Society, Series B 39(1), 1–38 (1977)MathSciNetzbMATHGoogle Scholar
  4. 4.
    Gil, P., Torres, F., Ortiz, F.G.: Detección de objetos por segmentación multinivel combinada de espacios de color, Tech. report, Dpto. Física, Ingeniería de Sistemas y Teoría de la Señal. Universidad de Alicate (Septiembre 2004)Google Scholar
  5. 5.
    Hu, T., Sung, S.Y.: Clustering Spatial Data with a Hybrid EM Approach, Tech. report, Department of Computer Science, National University of Singapore (2005)Google Scholar
  6. 6.
    Kaus, M.: Contributions to the Automated Segmentation of Brain Tumors in Magnetic Resonance Images, Ph.D. thesis, Der Technischen Fakultat der Universitat Erlangen-Nurnberg (1999)Google Scholar
  7. 7.
    Mostafa, M.G., Tolba, M.F., Gharib, T.F., Megeed, M.A.: Medical Image Segmentation Using a Wavelet-Based Multiresolution EM Algorithm. In: IEEE International Conference on Industrial Electronics, Technology and Automation, December 19-21 (2001)Google Scholar
  8. 8.
    Veloz, A., Chabert, S., Salas, R., Orellana, A., Vielma, J.: Fuzzy Spatial Growing for Glioblastoma Multiforme Segmentation on Brain Magnetic Resonance Imaging. In: Rueda, L., Mery, D., Kittler, J. (eds.) CIARP 2007. LNCS, vol. 4756, pp. 861–870. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  9. 9.
    Yang, Z., Chung, F.-L., Shitong, W.: Robust fuzzy clustering based image segmentation. Applied Soft Computing 9, 80–84 (2008)CrossRefGoogle Scholar
  10. 10.
    Zhang, Y., Brady, M., Smith, S.: Segmentation of Brain MR Images Through a Hidden Markov Random Field Model and the Expectation-Maximization Algorithm. IEEE Transactions on Medical Imaging 20(1), 45–57 (2001)CrossRefGoogle Scholar
  11. 11.
    Zhang, Y., Gerbrands, J.: Segmentation Evaluation Using Ultimate Measurament Accuracy. Image Processing Algorithms and Techniques III 1657, 449–460 (1996)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Ramiro Donoso
    • 1
  • Alejandro Veloz
    • 1
  • Héctor Allende
    • 1
  1. 1.Departamento de InformáticaUniversidad Técnica Federico Santa MaríaValparaísoChile

Personalised recommendations