Advertisement

Can ICA Help Classify Skin Cancer and Benign Lesions?

  • Ch. Mies
  • Ch. Bauer
  • G. Ackermann
  • W. Bäumler
  • C. Abels
  • C. G. Puntonet
  • M. R. Alvarez
  • E. W. Lang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2085)

Abstract

Various neural network models for the identification and classification of different skin lesions from ALA-induced fluorescence images are presented. After different image preprocessing steps, eigenimages and independent base images are extracted using PCA and ICA, respectively. In order to extract local information in the images rather than global features, Generative Topographic Mapping is added to cluster patches of the images first and then extract local features by ICA (local ICA). These components are used to distinguish skin cancer from benign lesions. An average classification rate of 70% is obtained, which considerably exceeds the rate achieved by an experienced physician.

Keywords

Principal Component Analysis Benign Lesion Recognition Rate Independent Component Analysis Basal Cell Carcinoma 
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. BLS98.
    M.S. Bartlett, H. Martin Lades, Terrence J. Sejnowski. Independent component representations for face recognition. Proceedings of the SPIE Symposium on Electronic Imaging: Science and technology; Conference on Human Vision and Electronic III, San Jose, California, 1998Google Scholar
  2. BSW97.
    C.M. Bishop, M. Svensen, C.K.I. Williams. A Principle Alternative to the Self Organizing Map Advances in Neural Information Processing Systems, volume 9, 354–360, MIT Press, 1997bGoogle Scholar
  3. KM99.
    J. Karhunen, S. Malaroiu. Local independent component analysis using clustering. International Workshop on Independent Component Analysis, Aussois, France, 1999Google Scholar
  4. MBA01.
    C. Mies, C. Bauer, G. Ackermann, W. Bäumler, C. Abels, R.M. Szeimies, E.W. Lang. Classification of Skin Cancer And Benign Lesions Using Idependent Component Analysis. Proceedings of ISI, Dubai, 2001Google Scholar
  5. PK97.
    P. Pajunen, J. Karhunen. A Maximum Likelihood Approach to Nonlinear Blind Source Separation. Proceedings of the Int. Conf. on Artificial Neural Networks (ICANN’97), Lausanne, Switzerland, 1997Google Scholar
  6. TP91.
    M. Turk, A. Pentland. Eigenfaces for Recognition. Journal of Cognitive Neuroscience, 3:71–86, 1991CrossRefGoogle Scholar
  7. YA97.
    H.H. Yang, S. Amari. Adaptive On-Line Learning Algorithms for Blind Separation-Maximum Entropy and Minimum Mutual Information. Neural Computation, 1997Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Ch. Mies
    • 1
  • Ch. Bauer
    • 1
    • 2
  • G. Ackermann
    • 2
  • W. Bäumler
    • 2
  • C. Abels
    • 2
  • C. G. Puntonet
    • 3
  • M. R. Alvarez
    • 3
  • E. W. Lang
    • 1
  1. 1.Institute of BiophysicsUniversity of RegensburgRegensburgGermany
  2. 2.Department of DermatologyUniversity HospitalRegensburgGermany
  3. 3.Departamento de Arquitectura y Tecnologia de Computadores E.T.S. Ingenieria InformaticaUniversidad de GranadaGranadaSpain

Personalised recommendations