Advertisement

Comparative Diagnostic Accuracy of Linear and Nonlinear Feature Extraction Methods in a Neuro-oncology Problem

  • Raúl Cruz-Barbosa
  • David Bautista-Villavicencio
  • Alfredo Vellido
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6718)

Abstract

The diagnostic classification of human brain tumours on the basis of magnetic resonance spectra is a non-trivial problem in which dimensionality reduction is almost mandatory. This may take the form of feature selection or feature extraction. In feature extraction using manifold learning models, multivariate data are described through a low-dimensional manifold embedded in data space. Similarities between points along this manifold are best expressed as geodesic distances or their approximations. These approximations can be computationally intensive, and several alternative software implementations have been recently compared in terms of computation times. The current brief paper extends this research to investigate the comparative ability of dimensionality-reduced data descriptions to accurately classify several types of human brain tumours. The results suggest that the way in which the underlying data manifold is constructed in nonlinear dimensionality reduction methods strongly influences the classification results.

Keywords

Linear Discriminant Analysis Geodesic Distance Human Brain Tumour Short Path Algorithm Nonlinear Dimensionality Reduction 
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.
    Vellido, A., Romero, E., González-Navarro, F., Belanche-Muñoz, L., Julià-Sapé, M., Arús, C.: Outlier exploration and diagnostic classification of a multi-centre 1 H-MRS brain tumour database. Neurocomputing 72(13-15), 3085–3097 (2009)CrossRefGoogle Scholar
  2. 2.
    González-Navarro, F., Belanche-Muñoz, L., Romero, E., Vellido, A., Julià-Sapé, M., Arús, C.: Feature and model selection with discriminatory visualization for diagnostic classification of brain tumours. Neurocomputing 73(4-6), 622–632 (2010)CrossRefGoogle Scholar
  3. 3.
    Lee, J.A., Verleysen, M.: Nonlinear Dimensionality Reduction. Springer, Heidelberg (2007)CrossRefzbMATHGoogle Scholar
  4. 4.
    Tenenbaum, J.B., de Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)CrossRefGoogle Scholar
  5. 5.
    Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation 15(6), 1373–1396 (2003)CrossRefzbMATHGoogle Scholar
  6. 6.
    Roweis, S.T., Lawrence, K.S.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)CrossRefGoogle Scholar
  7. 7.
    Cruz-Barbosa, R., Vellido, A.: Semi-supervised geodesic generative topographic mapping. Pattern Recognition Letters 31(3), 202–209 (2010)CrossRefGoogle Scholar
  8. 8.
    Bautista-Villavicencio, D., Cruz-Barbosa, R.: On geodesic distance computation: An experimental study. Advances in Computer Science and Applications, Research in Computing Science 53, 115–124 (2011)Google Scholar
  9. 9.
    Bernstein, M., de Silva, V., Langford, J.C., Tenenbaum, J.B.: Graph approximations to geodesics on embedded manifolds. Technical report, Stanford University, CA, U.S.A (2000)Google Scholar
  10. 10.
    Dijkstra, E.W.: A note on two problems in connexion with graphs. Numerische Mathematik 1, 269–271 (1959)MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Fredman, M.L., Tarjan, R.E.: Fibonacci heaps and their uses in improved network optimization algorithms. J. ACM 34(3), 596–615 (1987)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Julià-Sapé, M., et al.: A multi-centre, web-accessible and quality control-checked database of in vivo MR spectra of brain tumour patients. Magn. Reson. Mater. Phys. MAGMA 19, 22–33 (2006)CrossRefGoogle Scholar
  13. 13.
    Tate, A.R., Majós, C., Moreno, A., Howe, F.A., Griffiths, J.R., Arús, C.: Automated classification of short echo time in In Vivo 1 H brain tumor spectra: a multicenter study. Magnetic Resonance in Medicine 49, 29–36 (2003)CrossRefGoogle Scholar
  14. 14.
    García-Gómez, J.M., Tortajada, S., Vidal, C., Julià-Sapé, M., Luts, J., Moreno-Torres, A., Van-Huffel, S., Arús, C., Robles, M.: The effect of combining two echo times in automatic brain tumor classification by MRS. NMR in Biomedicine 21(10), 1112–1125 (2008)CrossRefGoogle Scholar
  15. 15.
    Lisboa, P.J.G., Vellido, A., Tagliaferri, R., Napolitano, F., Ceccarelli, M., Martin-Guerrero, J.D., Biganzoli, E.: Data mining in cancer research. IEEE Computational Intelligence Magazine 5(1), 14–18 (2010)CrossRefGoogle Scholar
  16. 16.
    Vellido, A., Lisboa, P.J.G.: Neural networks and other machine learning methods in cancer research. In: Sandoval, F., Prieto, A.G., Cabestany, J., Graña, M. (eds.) IWANN 2007. LNCS, vol. 4507, pp. 964–971. Springer, Heidelberg (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Raúl Cruz-Barbosa
    • 1
  • David Bautista-Villavicencio
    • 1
  • Alfredo Vellido
    • 2
  1. 1.Universidad Tecnológica de la MixtecaHuajuapanMéxico
  2. 2.Universitat Politècnica de CatalunyaBarcelonaSpain

Personalised recommendations