Abstract
The classification of normal and malginant colon tissue cells is crucial to the diagnosis of colon cancer in humans. Given the right set of feature vectors, Support Vector Machines (SVMs) have been shown to perform reasonably well for the classification [4,13]. In this paper, we address the following question: how does the choice of a kernel function and its parameters affect the SVM classification performance in such a system? We show that the Gaussian kernel function combined with an optimal choice of parameters can produce high classification accuracy.
Chapter PDF
Similar content being viewed by others
Keywords
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
Bowel cancer factsheet, Cancer Research UK (April 2003)
Chapelle, O., Vapnik, V.: Model selection for support vector machines. In: Proc. Advances in Neural Information Processing Systems, NIPS (1999)
Coifman, R., Lafon, S.: Geometric harmonics. Technical report, Department of Applied Mathematics, Yale University (2003)
Davis, G., Maggioni, M., Coifman, R., Rimm, D., Levenson, R.: Spectral/spatial analysis of colon carcinoma. In: United States and Canadian Academy of Pathology Meeting, Washington DC (March 2003)
Everson, R., Roberts, S.: Independent component analysis: A flexible nonlinearity and decorrelating manifold approach. In: Proc. IEEE NNSP (1998)
Gualtieri, J.A., Cromp, R.F.: Support vector machines for hyperspectral remote sensing classification. In: Proc. SPIE Workshop, Advances in Computer Assisted Recognition (ACAR) (October 1998)
Hsu, C.W., Chang, C.C., Lin, C.J.: A practical guide to support vector machines. Technical report, Department of Computer Science & Information Engineering, National Taiwan University (July 2003)
Joachims, J.: Estimating the generalization performance of a svm efficiently. In: Proc. Intl. Conf. on Machine Learning, Morgan Kaufmann, San Francisco (2000)
Lee, J.H., Lin, C.J.: Automatic model selection for SVM. Technical report, Department of Computer Science & Information Engineering, National Taiwan University (November 2000)
Levenson, R., Hoyt, C.: Spectral imaging & microscopy. American Laboratory, pp. 26–33 (November 2000)
Mercier, G., Lennon, M.: Support vector machines for hyperspectral image classification with spectral based kernels. In: Proc. IEEE Intl. Geoscience & Remote Sensing Symposium, IGARSS (2003)
Ou, Y.Y., Chen, C.Y., Hwang, S.C., Oyang, Y.J.: Expediting model selection for SVM based on data reduction. In: Proc. Intl. Conf. on Systems, Man, and Cybernetics (ICSMC) (October 2003)
Rajpoot, K.M., Rajpoot, N.M.: Hyperspectral colon tissue cell classification. In: SPIE Medical Imaging (MI) (February 2004)
Staelin, C.: Parameter selection for support vector machines. Technical report, HP Labs, Israel (2002)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Weston, J., Mukherjee, S., Chapelle, O., Pontil, M., Poggio, T., Vapnik, V.: Feature selection for SVMs. In: Proc. Advances in Neural Information Processing Systems, NIPS (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rajpoot, K., Rajpoot, N. (2004). SVM Optimization for Hyperspectral Colon Tissue Cell Classification. In: Barillot, C., Haynor, D.R., Hellier, P. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2004. MICCAI 2004. Lecture Notes in Computer Science, vol 3217. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30136-3_101
Download citation
DOI: https://doi.org/10.1007/978-3-540-30136-3_101
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22977-3
Online ISBN: 978-3-540-30136-3
eBook Packages: Springer Book Archive