Advertisement

Melanoma Recognition Using Representative and Discriminative Kernel Classifiers

  • Tatiana Tommasi
  • Elisabetta La Torre
  • Barbara Caputo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4241)

Abstract

Malignant melanoma is the most deadly form of skin lesion. Early diagnosis is of critical importance to patient survival. Existent visual recognition algorithms for skin lesions classification focus mostly on segmentation and feature extraction. In this paper instead we put the emphasis on the learning process by using two kernel-based classifiers. We chose a discriminative approach using support vector machines, and a probabilistic approach using spin glass-Markov random fields. We benchmarked these algorithms against the (to our knowledge) state-of-the-art method on melanoma recognition, exploring how performance changes by using color or textural features, and how it is affected by the quality of the segmentation mask. We show with extensive experiments that the support vector machine approach outperforms the existing method and, on two classes out of three, it achieves performances comparable to those obtained by expert clinicians.

Keywords

Support Vector Machine Recognition Rate Color Histogram Evidence Theory Dysplastic Lesion 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Amit, D.J.: Modeling Brain Function. Cambridge University Press, Cambridge, USA (1989)MATHGoogle Scholar
  2. 2.
    Caputo, B.: A new kernel method for object recognition: spin glass Markov random fields. PhD thesis, Stockholm (November 2004), Available at: http://www.nada.kth.se/~caputo
  3. 3.
    Caputo, B., La Torre, E., Bouattour, S., Gigante, G.E.: A New Kernel Method for Microcalcification Detection: Spin Glass- Markov Random Fields. In: Proc. of MIE 2002, Budapest (August 2002)Google Scholar
  4. 4.
    De Vries, E., Bray, F.I., Coebergh, J.W.W., Parkin, D.M.: Changing Epidemiology of Malignant Cutaneous Melanoma in Europe 1953-1997: Rising Trends in Incidence and Mortality but Recent Stabilizations in Western Europe and Decreases in Scandinavia. Int. J. Cancer 107, 119–126 (2003)CrossRefGoogle Scholar
  5. 5.
    Ganster, H., Pinz, A., Rhrer, R., Wildling, E., Binder, M., Kittler, H.: Automated Melanoma Recognition. IEEE Trans on MI 20(3) (March 2001)Google Scholar
  6. 6.
    Grana, C., Pellacani, G., Cucchiara, R., Seidenari, S.: A New Algorithm for Border Description of Polarized Light Surface Microscopic Images of Pigmented Skin Lesions. IEEE Trans on MI 22(8) (August 2003)Google Scholar
  7. 7.
    Grzymala-Busse, J.P., Grzymala-Busse, J.W., Hippe, Z.S.: Melanoma Prediction Using Data Mining System LERS. In: Proc COMPSAC 2001, pp. 615–620 (2001)Google Scholar
  8. 8.
    Lefevre, E., Colot, O., Vannoorenberghe, P., de Brucq, D.: Knowledge modeling methods in the framework of Evidence Theory An experimental comparison for melanoma detection. In: Proc. of Int. Conf. on Systems, Man, and Cybernetics, vol. 4, pp. 2806–2811Google Scholar
  9. 9.
    Rigel, D.S., Carucci, J.A.: Malignant Melanoma: Prevention, Early Detection, and Treatment in the 21st Century. CA Cancer J. Clin. 50, 215–236 (2000)CrossRefGoogle Scholar
  10. 10.
    Schiele, B., Crowley, J.L.: Recognition without correspondence using Multidimensional Receptive Field Hisograms. IJCV 36(1), 31–52 (2000)CrossRefGoogle Scholar
  11. 11.
    Scholkopf, B., Smola, A.J.: Learning with kernels. MIT Press, Cambridge (2001)Google Scholar
  12. 12.
    Vapnik, V.: Statistical learning theory. Wiley and Son, Chichester (1998)MATHGoogle Scholar
  13. 13.
    Wallraven, C., Caputo, B., Graf, A.: Recognition with Local features: the kernel recipe. In: Proc. ICCV 2003 (2003)Google Scholar
  14. 14.
    Wei, L., Yang, Y., Nishikawa, R.M., Jiang, Y.: A Study on Several Machine-Learning Methods for Classification od Malignant and Benign Clustered Microcalcifications. IEEE Trans. On MI 24(3) (March 2005)Google Scholar
  15. 15.
    Informations available at the World Healt Organization website: http://www.who.int

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tatiana Tommasi
    • 1
  • Elisabetta La Torre
    • 1
  • Barbara Caputo
    • 2
  1. 1.University of Rome La SapienzaRomeItaly
  2. 2.NADA/CVAP, KTHStockholmSweden

Personalised recommendations