Hierarchical Probabilistic Gabor and MRF Segmentation of Brain Tumours in MRI Volumes

  • Nagesh K. Subbanna
  • Doina Precup
  • D. Louis Collins
  • Tal Arbel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8149)


In this paper, we present a fully automated hierarchical probabilistic framework for segmenting brain tumours from multispectral human brain magnetic resonance images (MRIs) using multiwindow Gabor filters and an adapted Markov Random Field (MRF) framework. In the first stage, a customised Gabor decomposition is developed, based on the combined-space characteristics of the two classes (tumour and non-tumour) in multispectral brain MRIs in order to optimally separate tumour (including edema) from healthy brain tissues. A Bayesian framework then provides a coarse probabilistic texture-based segmentation of tumours (including edema) whose boundaries are then refined at the voxel level through a modified MRF framework that carefully separates the edema from the main tumour. This customised MRF is not only built on the voxel intensities and class labels as in traditional MRFs, but also models the intensity differences between neighbouring voxels in the likelihood model, along with employing a prior based on local tissue class transition probabilities. The second inference stage is shown to resolve local inhomogeneities and impose a smoothing constraint, while also maintaining the appropriate boundaries as supported by the local intensity difference observations. The method was trained and tested on the publicly available MICCAI 2012 Brain Tumour Segmentation Challenge (BRATS) Database [1] on both synthetic and clinical volumes (low grade and high grade tumours). Our method performs well compared to state-of-the-art techniques, outperforming the results of the top methods in cases of clinical high grade and low grade tumour core segmentation by 40% and 45% respectively.


Gaussian Mixture Model Markov Random Field Gabor Frame Tumour Core Markov Random Field Model 
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.


  1. 1.
  2. 2.
    Ferlay, J., et al.: Estimates of worldside burden of cancer in 2008. In: GLOBOCAN 2008 (2008)Google Scholar
  3. 3.
    Corso, J., et al.: Efficient Multilevel Brain Tumour Segmentation with Integrated Bayesian Model Classification. IEEE Trans. Med. Imag. 27(5), 629–640 (2008)CrossRefGoogle Scholar
  4. 4.
    Kaus, M., et al.: Adaptive Template Moderated Brain Tumour Segmentation in MRI. In: Workshop Fuer Bildverarbeitung Fur Die Medizin, pp. 102–105 (1999)Google Scholar
  5. 5.
    Prastawa, M., et al.: A brain tumor segmentation framework based on outlier detection. Med. Image Ana. 8(3), 275–283 (2004)CrossRefGoogle Scholar
  6. 6.
    Menze, B.H., van Leemput, K., Lashkari, D., Weber, M.-A., Ayache, N., Golland, P.: A generative model for brain tumor segmentation in multi-modal images. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010, Part II. LNCS, vol. 6362, pp. 151–159. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  7. 7.
    Zikic, D., Glocker, B., Konukoglu, E., Criminisi, A., Demiralp, C., Shotton, J., Thomas, O.M., Das, T., Jena, R., Price, S.J.: Decision forests for tissue-specific segmentation of high-grade gliomas in multi-channel MR. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part III. LNCS, vol. 7512, pp. 369–376. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  8. 8.
    Wels, M., Carneiro, G., Aplas, A., Huber, M., Hornegger, J., Comaniciu, D.: A discriminative model-constrained graph-cuts approach to fully automated pediatric brain tumor segmentation in 3D MRI. In: Metaxas, D., Axel, L., Fichtinger, G., Székely, G. (eds.) MICCAI 2008, Part I. LNCS, vol. 5241, pp. 67–75. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  9. 9.
    Moon, N., et al.: Model based brain and tumor segmentation. In: ICPR, vol. 1, pp. 528–531 (2002)Google Scholar
  10. 10.
    Bauer, S., et al.: Segmentation of Brain Tumour Images Based on Integrated Hierarchical Classification and Regularisation. In: BRATS MICCAI (2012)Google Scholar
  11. 11.
    Parisot, S.: Graph-based Detection, Segmentation and Characterisation of Brain Tumours. In: CVPR, pp. 988–995 (2012)Google Scholar
  12. 12.
    Mishra, R.: MRI based brain tumor detection using wavelet packet feature and Artificial Neural Networks. In: Int. Conf. and Work. on Emerging Trends in Tech., pp. 656–659 (2010)Google Scholar
  13. 13.
    Bauer, S., et al.: Atlas-Based Segmentation of Brain Tumor Images Using a Markov Random Field-Based Tumor Growth Model and Non-Rigid Registration. In: IEEE EMBS, pp. 4080–4083 (2010)Google Scholar
  14. 14.
    Farias, G., et al.: Brain Tumour Diagnosis with Wavelets and Support Vector Machines. In: Int. Conf. Intell. Systems and Knowledge Engg., pp. 1453–1459 (2008)Google Scholar
  15. 15.
    Subbanna, N., et al.: Probabilistic Gabor and Markov Random Fields Segmentation of Brain Tumours in MRI Volumes. In: BRATS MICCAI (2012)Google Scholar
  16. 16.
    Zibulski, M.: Discrete multiwindow Gabor-type transforms. IEEE Trans. Sig. Proc. 45(6), 1428–1442 (1997)CrossRefzbMATHGoogle Scholar
  17. 17.
    Jain, A., et al.: Unsupervised Texture segmentation using Gabor filters. Patt. Rcgn. 24(12), 1167–1186 (1991)CrossRefGoogle Scholar
  18. 18.
    Subbanna, N., et al.: Existence Conditions for Non-Canonical Discrete Multiwindow Gabor Frames. IEEE Trans. Sig. Proc. 55(10), 5113–5117 (2007)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Duda, R., et al.: Pattern Classification. John Wiley and Sons (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Nagesh K. Subbanna
    • 1
  • Doina Precup
    • 2
  • D. Louis Collins
    • 3
  • Tal Arbel
    • 1
  1. 1.Centre for Intelligent MachinesMcGill UniversityCanada
  2. 2.School of Computer ScienceMcGill UniversityCanada
  3. 3.McConnell Brain Imaging CentreMcGill UniversityCanada

Personalised recommendations