Applications of Neural Networks in Semantic Analysis of Skin Cancer Images

  • K. Przystalski
  • L. Nowak
  • M. Ogorzałek
  • G. Surówka

Abstract

Computational intelligence is finding more and more applications in computer aided diagnostics, helping doctors to process large quantities of various medical data [Buronni et al. 2004]. In dermatology it is extremely difficult to perform automatic diagnostic differentiation of malignant melanoma based only on dermatoscopic images. Applying artificial intelligence algorithms to explore and search large database of dermatoscopic images allow doctors to semantically filter out image with specified characteristics. This paper presents an semantic approach for characteristic objects classification found in image database of pigment skin lesions, based on radial basis function kernel for artificial neural networks. Presented approach is divided into few parts: JSEG image segmentation [Deng et al. 2001], feature extraction and classification. Prepared features vector consist of color models parts. For classification Artificial Neural Networks and Support Vector Machines are used and their performance is evaluated and compared. Success rates in both cases are greater than 90%.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [Argenziano et al. 1998]
    Argenziano, G., Fabbrocini, G., Carli, P., DeGiorgi, V., Sammarco, P.E., Delfino, M.: Epiluminescence microscopy for the diagnosis of doubtful melanocytic skin lesions. Arch. Dermatl. 134, 1563–1570 (1998)CrossRefGoogle Scholar
  2. [Buronni et al. 2004]
    Buronni, M., Corona, R., Dell’Eva, G., Sera, F., Bono, R., Puddu, P., Perotti, R., Nobile, F., Andreassi, L., Rubegni, P.: Melanoma computer-aided diagnosis: reliability and feasibility study. Clin. Cancer Res. 1881–1886 (2004)Google Scholar
  3. [Chuan et al. 2009]
    Yu-Chang, C., Wang, H.J., Li, C.F.: Semantic analysis of real-world images using support vector machine. Experts Systems with Applications, 10560–10569 (2009)Google Scholar
  4. [Deng et al. 2001]
    Deng, Y., Manjunat, B.S.: Unsupervised segmentation of color-texture regions in images and video. IEEE Transactions on Pattern Analysis and Machine Intelligence (2001)Google Scholar
  5. [Liu et al. 2005]
    Liu, Y., Zhang, D., Lu, G., Ma, Y.: Region-based image retrieval with high-level semantic color names. In: IEEE Proc. of the Multimedia Modeling Conf., pp. 180–187 (2005)Google Scholar
  6. [Menzies 1999]
    Menzies, S.W.: Automated epiluminescence microscopy: human vs machine in the diagnosis of melanoma. Arch. Dermatol. 135, 1538–1540 (1999)CrossRefGoogle Scholar
  7. [Menzies et al. 2005]
    Menzies, S.W., Bischof, L., Talbot, H., et al.: The Performance of SolarScan. An automated dermoscopy image analysis instrument for the diagnosis of primary melanome. Archive of Dermatology, 1388–1396 (2005)Google Scholar
  8. [Muezzinoglu 2006]
    Muezzinoglu, M.K., Zurada, J.M.: RBF-based neurodynamic nearest neighbor classification in real pattern space. Pattern Recognition (2006)Google Scholar
  9. [Stolz et al. 1994]
    Stolz, W., Riemann, A., Cognetta, A.B., Pillet, L., Abmayr, W., Hölzel, D., Bilek, P., Nachbar, F., Landthaler, M., Braun-Falco, O.: ABCD rule of dermatoscopy: a new practical method for early recognition of malignant melanoma. Eur. J. Dermatol. 7, 521–528 (1994)Google Scholar
  10. [Wu et al. 2008]
    Wu, Y. C., Lee, Y.S., Yen, S. J., Yang, Y.C.: Robust and efficient multiclass SVM models for phrase pattern recognition. Pattern Recognition 2874–2889 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • K. Przystalski
    • 1
  • L. Nowak
    • 1
  • M. Ogorzałek
    • 1
  • G. Surówka
    • 1
  1. 1.Department of Information Technologies, Faculty of Physics, Astronomy and Applied Computer ScienceJagiellonian UniversityKrakowPoland

Personalised recommendations