Pigmented Skin Lesions Classification Using Dermatoscopic Images

  • Germán Capdehourat
  • Andrés Corez
  • Anabella Bazzano
  • Pablo Musé
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5856)

Abstract

In this paper we propose a machine learning approach to classify melanocytic lesions in malignant and benign from dermatoscopic images. The image database is composed of 433 benign lesions and 80 malignant melanoma. After an image pre-processing stage that includes hair removal filtering, each image is automatically segmented using well known image segmentation algorithms. Then, each lesion is characterized by a feature vector that contains shape, color and texture information, as well as local and global parameters that try to reflect structures used in medical diagnosis. The learning and classification stage is performed using AdaBoost.M1 with C4.5 decision trees. For the automatically segmented database, classification delivered a false positive rate of 8.75% for a sensitivity of 95%. The same classification procedure applied to manually segmented images by an experienced dermatologist yielded a false positive rate of 4.62% for a sensitivity of 95%.

Keywords

Automatic Segmentation Hair Removal Melanocytic Lesion Image Segmentation Algorithm False Detection Rate 
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.
    Rubegni, P., Burroni, M., Dell’eva, G., Andreassi, L.: Digital dermoscopy analysis for automated diagnosis of pigmented skin lesion. Clinics in Dermatology 20(3), 309–312 (2002)CrossRefGoogle Scholar
  2. 2.
    Nachbar, F., Stolz, W., Merkle, T., Cognetta, A., Vogt, T., Landthaler, M., Bilek, P., Braun-Falco, O., Plewig, G.: The ABCD rule of dermatoscopy: high prospective value in the diagnosis of doubtful melanocytic skin lesions. Journal of the American Academy of Dermatology 30(4), 551–559 (1994)CrossRefGoogle Scholar
  3. 3.
    Lorentzen, H., Weismann, K., Kenet, R., Secher, L., Larsen, F.: Comparison of dermatoscopic abcd rule and risk stratification in the diagnosis of malignant melanoma. Acta Derm Venereol 80(2), 122–126 (2000)Google Scholar
  4. 4.
    Johr, R.H.: Dermoscopy: alternative melanocytic algorithms - the abcd rule of dermatoscopy, menzies scoring method, and 7-point checklist. Clinics in Dermatology 20(3), 240–247 (2002)CrossRefGoogle Scholar
  5. 5.
    Cascinelli, N., Ferrario, M., Tonelli, T., Leo, E.: A possible new tool for clinical diagnosis of melanoma: The computer. Journal of the American Academy of Dermatology 16(2), 361–367 (1987)CrossRefGoogle Scholar
  6. 6.
    Ganster, H., Pinz, A., Rhrer, R., Wildling, E., Binder, M., Kittler, H.: Automated melanoma recognition. IEEE Transactions on Medical Imaging 20, 233–239 (2001)CrossRefGoogle Scholar
  7. 7.
    Celebi, M.E., Kingravi, H.A., Uddin, B., Iyatomi, H., Aslandogan, Y.A., Stoecker, W.V., Moss, R.H.: A methodological approach to the classification of dermoscopy images. Comput. Med. Imaging Graph 31(6), 362–373 (2007)CrossRefGoogle Scholar
  8. 8.
    Robnik-Šikonja, M., Kononenko, I.: Theoretical and empirical analysis of relieff and rrelieff. Mach. Learn. 53(1-2), 23–69 (2003)MATHCrossRefGoogle Scholar
  9. 9.
    Hall, M.A.: Correlation-based feature selection for discrete and numeric class machine learning. In: ICML 2000: Proceedings of the 7th International Conference on Machine Learning, San Francisco, CA, USA, pp. 359–366 (2000)Google Scholar
  10. 10.
    Schlkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. The MIT Press, Cambridge (2001)Google Scholar
  11. 11.
    Lee, T., Ng, V., Gallagher, R., Coldman, A.: Dullrazor: A software approach to hair removal from images. Computers in Biology and Medicine 27(11), 533–543 (1997)CrossRefGoogle Scholar
  12. 12.
    Otsu, N.: A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man and Cybernetics 9(1), 62–66 (1979)CrossRefMathSciNetGoogle Scholar
  13. 13.
    Koepfler, G., Lopez, C., Morel, J.M.: A multiscale algorithm for image segmentation by variational method. SIAM J. Numer. Anal. 31(1), 282–299 (1994)MATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Paragios, N., Deriche, R.: Geodesic active regions: A new framework to deal with frame partition problems in computer vision. Journal of Visual Communication and Image Representation 13, 249–268 (2002)CrossRefGoogle Scholar
  15. 15.
    Cao, F., Musé, P., Sur, F.: Extracting meaningful curves from images. Journal of Mathematical Imaging and Vision 22(2-3), 159–181 (2005)CrossRefMathSciNetGoogle Scholar
  16. 16.
    Cardelino, J., Randall, G., Bertalmio, M., Caselles, V.: Region based segmentation using the tree of shapes. In: IEEE International Conference on Image Processing, Proceedings (2006)Google Scholar
  17. 17.
    Quinlan, R.J.: C4.5: Programs for Machine Learning. Morgan Kaufmann Series in Machine Learning. Morgan Kaufmann, San Francisco (1993)Google Scholar
  18. 18.
    Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119–139 (1997)MATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    Nitesh, V., Chawla, N., Bowyer, K., Hall, L., Kegelmeyer, W.: Smote: Synthetic minority over-sampling technique. J. Artif. Intell. Res (JAIR) 16, 321–357 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Germán Capdehourat
    • 1
  • Andrés Corez
    • 1
  • Anabella Bazzano
    • 2
  • Pablo Musé
    • 1
  1. 1.Departamento de Procesamiento de Señales, Instituto de Ingeniería Eléctrica, Facultad de IngenieríaUniversidad de la RepúblicaUruguay
  2. 2.Unidad de Lesiones Pigmentadas, Cátedra de Dermatología, Hospital de Clínicas, Facultad de MedicinaUniversidad de la RepúblicaUruguay

Personalised recommendations