Advertisement

Multimedia Tools and Applications

, Volume 77, Issue 7, pp 8001–8018 | Cite as

Segmentation of brain MR images using a proper combination of DCS based method with MRF

  • Ali Ahmadvand
  • Mohammad Reza Daliri
  • Sayyed Mohammadreza Zahiri
Article
  • 131 Downloads

Abstract

Manual segmentation of Magnetic Resonance Images (MRI) is a time-consuming process, thus automatic segmentation of brain MR images has attracted more attention in recent years. In this paper, we introduce Dynamic Classifier Selection Markov Random Field (DCSMRF) algorithm for supervised segmentation of brain MR images into three main tissues such as White Matter (WM), Gray Matter (GM) and Cerebrospinal Fluid (CSF). DCSMRF combines a novel ensemble method with the Markov Random Field (MRF) algorithm and tries to obtain the advantages of both algorithms. For the ensemble part of DCSMRF, we propose an ensemble method called Dynamic Classifier System-Weighted Local Accuracy (DCS-WLA) which is a type of Combination of Multiple Classifier (CMC) algorithm. Later, the MRF algorithm is utilized for incorporating spatial, contextual and textural information in this paper. For the MRF section, an energy function based on the output of the DCS-WLA algorithm is proposed, then maximum value for Maximum A Posterior (MAP) criterion is searched to obtain optimal segmentation. The MRF algorithm applies similar to a post processing step in which only a subset of pixels is selected for optimization step. Hence, a vast amount of search space is pruned. Consequently, the computational burden of the proposed algorithm is more tolerable than the conventional MRF-based methods. Moreover, by employing ensemble algorithms, the accuracy and reliability of final results are enhanced compared to the individual methods.

Keywords

MRI Ensemble methods Combination of multiple classifier MRF Dynamic classifier system Weighted local accuracy Segmentation 

Notes

Acknowledgements

The work has been supported by internal funding from IUST University. No external financial support has been obtained for this work.

Compliance with ethical standards

Conflict of Interest

The authors have no conflicts of interest to declare

References

  1. 1.
    Ahmadvand A, Daliri MR (2014) Brain MR image segmentation methods and applications. OMICS J Radiol (4):3, e130Google Scholar
  2. 2.
    Ahmadvand A, Daliri MR (2015) Improving the runtime of MRF based method for MRI brain segmentation. Appl Math Comput 256:808–818MathSciNetzbMATHGoogle Scholar
  3. 3.
    Ahmadvand A, Kabiri P (2014) Multispectral MRI image segmentation using Markov random field model. SIViP:1–8Google Scholar
  4. 4.
    Ahmadvand A, Sharififar M, Daliri MR (2015) Supervised segmentation of MRI brain images using combination of multiple classifiers. Australas Phys Eng Sci Med 38(2):241–253CrossRefGoogle Scholar
  5. 5.
    Ahmadvand A et al (2015) A novel CMC based method for MR! brain image segmentation. In 2015 2nd international conference on Knowledge-Based Engineering and Innovation (KBEI). IEEEGoogle Scholar
  6. 6.
    Bae MH et al (2009) Automated segmentation of mouse brain images using extended MRF. NeuroImage 46(3):717–725CrossRefGoogle Scholar
  7. 7.
    Bae MH, Wu T, Pan R (2010) Mix-ratio sampling: classifying multiclass imbalanced mouse brain images using support vector machine. Expert Syst Appl 37(7):4955–4965CrossRefGoogle Scholar
  8. 8.
    Balafar M (2012) Gaussian mixture model based segmentation methods for brain MRI images. Artif Intell Rev:1–11Google Scholar
  9. 9.
    Besag J (1975) Statistical analysis of non-lattice data. Journal of the Royal Statistical Society, Series D (The Statistician) 24(3):179–195Google Scholar
  10. 10.
    Caldairou B et al (2011) A non-local fuzzy segmentation method: application to brain MRI. Pattern Recogn 44(9):1916–1927CrossRefGoogle Scholar
  11. 11.
    Dubes R et al (1990) MRF model-based algorithms for image segmentation. In Pattern recognition, 1990. Proceedings., 10th international conference on. IEEEGoogle Scholar
  12. 12.
    Geman S, Geman D (1984) Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. Pattern Anal Mach Intell IEEE Trans 3(6):721–741CrossRefzbMATHGoogle Scholar
  13. 13.
    Greenspan H, Ruf A, Goldberger J (2006) Constrained Gaussian mixture model framework for automatic segmentation of MR brain images. Med Imaging IEEE Trans 25(9):1233–1245CrossRefGoogle Scholar
  14. 14.
    Hammersley JM, Clifford P (1971) Markov fields on finite graphs and lattices, (unpublished)Google Scholar
  15. 15.
    Hashemi RH, Bradley WG, Lisanti CJ (2012) MRI: the basics. Wolters Kluwer Health, PhiladelphiaGoogle Scholar
  16. 16.
    Jiménez-Alaniz JR, Medina-Bañuelos V, Yáñez-Suárez O (2006) Data-driven brain MRI segmentation supported on edge confidence and a priori tissue information. Med Imaging IEEE Trans 25(1):74–83CrossRefGoogle Scholar
  17. 17.
    Kim W, Lee KM (2011) A hybrid approach for MRF optimization problems: combination of stochastic sampling and deterministic algorithms. Comput Vis Image Underst 115(12):1623–1637CrossRefGoogle Scholar
  18. 18.
    Liu Y-T, Zhang H-X, Li P-H (2011) Research on SVM-based MRI image segmentation. J China Univ Posts Telecommun 18:129–132CrossRefGoogle Scholar
  19. 19.
    Marroquín JL et al (2002) An accurate and efficient Bayesian method for automatic segmentation of brain MRI. Med Imaging IEEE Trans 21(8):934–945CrossRefGoogle Scholar
  20. 20.
    Mayer A, Greenspan H (2009) An adaptive mean-shift framework for MRI brain segmentation. Med Imaging IEEE Trans 28(8):1238–1250CrossRefGoogle Scholar
  21. 21.
    Ortiz A et al (2011) MRI brain image segmentation with supervised SOM and probability-based clustering method. In New challenges on bioinspired applications. Springer. p 49–58Google Scholar
  22. 22.
    Ortiz A et al (2012) Unsupervised neural techniques applied to MR brain image segmentation. AdvArtif Neural Syst 2012:1CrossRefGoogle Scholar
  23. 23.
    Ortiz A et al (2013) Improving MRI segmentation with probabilistic GHSOM and multiobjective optimization. Neurocomputing 114:118–131CrossRefGoogle Scholar
  24. 24.
    Ouadfel S, Batouche M (2003) MRF-based image segmentation using ant colony system. Electron Lett Comput Vision Image Anal 2(2):12–24CrossRefGoogle Scholar
  25. 25.
    Pham D et al (1997) An automated technique for statistical characterization of brain tissues in magnetic resonance imaging. Int J Pattern Recognit Artif Intell 11(08):1189–1211CrossRefGoogle Scholar
  26. 26.
    Platt J (1999) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv Large Margin Classif 10(3):61–74Google Scholar
  27. 27.
    Prakash RM, Kumari RSS (2016) Gaussian mixture model with the inclusion of spatial factor and pixel re-labelling: application to MR brain image segmentation. Arab J Sci Eng:1–11Google Scholar
  28. 28.
    Qian H, Wu X, Xu Y (2011) Dynamic analysis of crowd behavior. In Intelligent surveillance systems. Springer. p 119–154Google Scholar
  29. 29.
    Rajapakse JC, Giedd JN, Rapoport JL (1997) Statistical approach to segmentation of single-channel cerebral MR images. Med Imaging IEEE Trans 16(2):176–186CrossRefGoogle Scholar
  30. 30.
    Rivest-Hénault D, Cheriet M (2011) Unsupervised MRI segmentation of brain tissues using a local linear model and level set. Magn Reson Imaging 29(2):243–259CrossRefGoogle Scholar
  31. 31.
    da Silva Ferreira AR (2007) A Dirichlet process mixture model for brain MRI tissue classification. Med Image Anal 11(2):169–182CrossRefGoogle Scholar
  32. 32.
    Siyal MY, Yu L (2005) An intelligent modified fuzzy c-means based algorithm for bias estimation and segmentation of brain MRI. Pattern Recogn Lett 26(13):2052–2062CrossRefGoogle Scholar
  33. 33.
    Tohka J et al (2005) Genetic algorithms for finite mixture model based tissue classification in brain MRI. In Proc. of European medical and biological engineering conference, IFMBE proceedingsGoogle Scholar
  34. 34.
    Tohka J et al (2007) Genetic algorithms for finite mixture model based voxel classification in neuroimaging. Med Imaging IEEE Trans 26(5):696–711CrossRefGoogle Scholar
  35. 35.
    Vaidyanathan M et al (1995) Comparison of supervised MRI segmentation methods for tumor volume determination during therapy. Magn Reson Imaging 13(5):719–728CrossRefGoogle Scholar
  36. 36.
    Wolpert DH, Macready WG (1997) No free lunch theorems for optimization. IEEE Trans Evol Comput 1:67–82CrossRefGoogle Scholar
  37. 37.
    Woods K, Bowyer K, Kegelmeyer WP Jr (1996) Combination of multiple classifiers using local accuracy estimates. In Computer vision and pattern recognition, 1996. Proceedings CVPR'96, 1996 I.E. computer society conference on. IEEEGoogle Scholar
  38. 38.
    Worth AJ (1996)The Internet brain segmentation repository (IBSR), http://www.cma.mgh.Harvard.edu/ibsr
  39. 39.
    Wu T et al (2012) A prior feature SVM-MRF based method for mouse brain segmentation. NeuroImage 59(3):2298–2306CrossRefGoogle Scholar
  40. 40.
    Yousefi S, Azmi R, Zahedi M (2012) Brain tissue segmentation in MR images based on a hybrid of MRF and social algorithms. Med Image Anal 16(4):840–848CrossRefGoogle Scholar
  41. 41.
    Zhang Y, Brady M, Smith S (2001) Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. Med Imaging IEEE Trans 20(1):45–57CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  • Ali Ahmadvand
    • 1
    • 2
  • Mohammad Reza Daliri
    • 3
  • Sayyed Mohammadreza Zahiri
    • 4
  1. 1.School of Computer EngineeringIran University of Science and Technology (IUST)TehranIran
  2. 2.Mathematics and Computer Science DepartmentEmory UniversityAtlantaUSA
  3. 3.Neuroscience and Neuroengineering Research Lab., Biomedical Engineering Department, School of Electrical EngineeringIran University of Science and Technology (IUST)TehranIran
  4. 4.Department of Electrical and Computer EngineeringGeorgia Institute of TechnologyAtlantaUSA

Personalised recommendations