Advertisement

A New Shape Diffusion Descriptor for Brain Classification

  • Umberto Castellani
  • Pasquale Mirtuono
  • Vittorio Murino
  • Marcella Bellani
  • Gianluca Rambaldelli
  • Michele Tansella
  • Paolo Brambilla
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6892)

Abstract

In this paper, we exploit spectral shape analysis techniques to detect brain morphological abnormalities. We propose a new shape descriptor able to encode morphometric properties of a brain image or region using diffusion geometry techniques based on the local Heat Kernel. Using this approach, it is possible to design a versatile signature, employed in this case to classify between normal subjects and patients affected by schizophrenia. Several diffusion strategies are assessed to verify the robustness of the proposed descriptor under different deformation variations. A dataset consisting of MRI scans from 30 patients and 30 control subjects is utilized to test the proposed approach, which achieves promising classification accuracies, up to 83.33%. This constitutes a drastic improvement in comparison with other shape description techniques.

Keywords

Support Vector Machine Heat Kernel Shape Descriptor Magnetic Resonance Image Data Heat Kernel Signature 
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.
    Giuliani, N.R., Calhouna, V.D., Pearlson, G.D., Francis, A., Buchanan, R.W.: Voxel-based morphometry versus region of interest: a comparison of two methods for analyzing gray matter differences in schizophrenia. Schizophrenia Research 74(2-3), 135–147 (2005)CrossRefGoogle Scholar
  2. 2.
    Shenton, M.E., Dickey, C.C., Frumin, M., McCarley, R.W.: A review of MRI findings in schizophrenia. Schizophrenia Research 49(1-2), 1–52 (2001)CrossRefGoogle Scholar
  3. 3.
    Fan, Y., Shen, D., Gur, R.C., Gur, R.E., Davatzikos, C.: COMPARE: Classification of morphological patterns using adaptive regional elements. IEEE Transactions on Medical Imaging 26(1), 93–105 (2007)CrossRefGoogle Scholar
  4. 4.
    Reuter, M., Wolter, F.-E., Shenton, M., Niethammer, M.: Laplace-Beltrami eigenvalues and topological features on eigenfuntions for statistical shape analysis. In: Computed-Aided Design, vol. 41(10), pp. 739–755 (2009)Google Scholar
  5. 5.
    Gerig, G., Styner, M., Jones, D., Weinberger, D., Lieberman, J.: Shape analysis of brain ventricles using SPHARM. In: Proceedings of the IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, pp. 171–178. IEEE Computer Society, Washington, DC, USA (2001)Google Scholar
  6. 6.
    Toews, M., Wells, W., Collins, D., Arbel, T.: Feature-based morphometry. In: Yang, G. Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009. LNCS, vol. 5762, pp. 109–116. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  7. 7.
    Sun, J., Ovsjanikov, M., Guibas, L.: A concise and provably informative multi-scale signature based on heat diffusion. In: Proceedings of the Symposium on Geometry Processing, pp. 1383–1392. Eurographics Association, Berlin (2009)Google Scholar
  8. 8.
    Gebal, K., Baerentzen, J.A., Aanaes, H., Larsen, R.: Shape analysis using the auto diffusion function. In: Proceedings of the Symposium on Geometry Processing, pp. 1405–1413. Eurographics Association, Berlin (2009)Google Scholar
  9. 9.
    Raviv, D., Bronstein, A.M., Bronstein, M.M., Kimmel, R.: Volumetric heat kernel signatures. In: Workshop on 3D Object Retrieval, pp. 39–44. ACM, Firenze (2010)CrossRefGoogle Scholar
  10. 10.
    Bronstein, A.M., Bronstein, M.M., Ovsjanikov, M., Guibas, L.J.: Shape recognition with spectral distances. IEEE Trans. Pattern Analysis and Machine Intelligence 33(5), 1065–1071 (2011)CrossRefGoogle Scholar
  11. 11.
    Burges, C.: A tutorial on support vector machine for pattern recognition. Data Mining and Knowledge Discovery 2, 121–167 (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Umberto Castellani
    • 1
  • Pasquale Mirtuono
    • 1
  • Vittorio Murino
    • 1
    • 2
  • Marcella Bellani
    • 3
  • Gianluca Rambaldelli
    • 3
  • Michele Tansella
    • 3
  • Paolo Brambilla
    • 4
    • 5
  1. 1.VIPS labUniversity of VeronaItaly
  2. 2.Istituto Italiano di Tecnologia (IIT)Italy
  3. 3.Department of Public Health and Community Medicine, Inter-University Center for Behavioural Neurosciences (ICBN)University of VeronaItaly
  4. 4.Department of Experimental Clinical Medical Sciences (DISM), Inter-University Center for Behavioral NeurosciencesUniversity of UdineItaly
  5. 5.Scientific Institute IRCCS “E. Medea”UdineItaly

Personalised recommendations