Complexity Aspects of Image Classification

  • Andreas A. Albrecht
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4987)

Abstract

Feature selection and parameter settings for classifiers are both important issues in computer-assisted medical diagnosis. In the present paper, we highlight some of the complexity problems posed by both tasks. For the feature selection problem we propose a search-based procedure with a proven time bound for the convergence to optimum solutions. Interestingly, the time bound differs from fixed-parameter tractable algorithms by an instance-specific factor only. The stochastic search method has been utilized in the context of micro array data classification. For the classification of medical images we propose a generic upper bound for the size of classifiers that basically depends on the number of training samples only. The evaluation on a number of benchmark problems produced a close correspondence to the size of classifiers with best generalization results reported in the literature.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Albrecht, A.A.: Stochastic Local Search for the Feature Set Problem with Applications to Microarray Data. Appl. Math. Comput. 183, 1148–1164 (2006)MATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Albrecht, A., Loomes, M.J., Steinhöfel, K., Taupitz, M.: Adaptive Simulated Annealing for CT Image Classification. Int. J. Pattern Recogn. 16, 573–588 (2002)Google Scholar
  3. 3.
    Albrecht, A.A., Chashkin, A.V., Iliopoulos, C.S., Kasim-Zade, O.M., Lappas, G., Steinhöfel, K.: A priori Estimation of Classification Circuit Complexity. In: Daykin, J.W., Steinhöfel, K., Mohamed, M. (eds.) Texts in Algorithmics, vol. 8, pp. 97–114, King’s College, London (2007)Google Scholar
  4. 4.
    Cotta, C., Moscato, P.: The k-Feature Set Problem is W[2]-complete. J. Comput. System Sci. 67, 686–690 (2003)MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Doi, K.: Current Status and Future Potential of Computer-aided Diagnosis in Medical Imaging. British J. Radiol. 78, S3–S19 (2005)CrossRefGoogle Scholar
  6. 6.
    Downey, R., Fellows, M.: Parameterized Complexity. Springer, Heidelberg (1998)MATHGoogle Scholar
  7. 7.
    Gletsos, M., Mougiakakou, S.G., Matsopoulos, G.K., Nikita, K.S., Nikita, A.S., Kelekis, D.: A Computer-aided Diagnostic System to Characterize CT Focal Liver Lesions: Design and Optimization of a Neural Network Classifier. IEEE T. Inform. Techn. Biomed. 7, 153–162 (2003)Google Scholar
  8. 8.
    Hein, E., Albrecht, A., Melzer, D., Steinhöfel, K., Rogalla, P., Hamm, B., Taupitz, M.: Computer-assisted Diagnosis of Focal Liver Lesions on CT Images. Acad. Radiol. 12, 1205–1210 (2005)CrossRefGoogle Scholar
  9. 9.
    Lappas, G., Frank, R.J., Albrecht, A.A.: A Computational Study on Circuit Size vs. Circuit Depth. Int. J. Artif. Intell. Tools. 15, 143–162 (2006)Google Scholar
  10. 10.
    Davies, S., Russell, S.: NP-completeness of Searches for the Smallest Possible Feature Set. In: Greiner, R. (ed.) Proceedings of the AAAI Symposium on Relevance, pp. 41–43. AAAI Press, Menlo Park (1994)Google Scholar
  11. 11.
    Susomboon, R., Raicu, D.S., Furst, J.: Pixel-based Texture Classification of Tissues in Computed Tomography. In: Proceedings DePaul CTI Research Symposium (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Andreas A. Albrecht
    • 1
  1. 1.Science and Technology Research InstituteUniversity of HertfordshireHatfieldUK

Personalised recommendations