Support Vector Machine Approach for Classification of Cancerous Prostate Regions

The objective of this paper, is to apply support vector machine (SVM) approach for the classification of cancerous and normal regions of prostate images. Three kinds of textural features are extracted and used for the analysis: parameters of the Gauss- Markov random field (GMRF), correlation function and relative entropy. Prostate images are acquired by the system consisting of a microscope, video camera and a digitizing board. Cross-validated classification over a database of 46 images is implemented to evaluate the performance. In SVM classification, sensitivity and specificity of 96.2% and 97.0% are achieved for the 32x32 pixel block sized data, respectively, with an overall accuracy of 96.6%. Classification performance is compared with artificial neural network and k-nearest neighbor classifiers. Experimental results demonstrate that the SVM approach gives the best performance.

• Metehan Makinacı

• Computer-aided diagnosis
• support vector machines
• Gauss-Markov random fields
• texture classification.

[1] U. Schenck, and W. Planding, "Quantitation of visual screening
technique in cytology," in Proc. Image Analysis in Medicine, II.
National Symposium, pp. 7-14, 1998.
[2] D. Kopec, M.H. Kabir, D. Reinharth, O. Rothschild, and J.A.
Castiglione, "Human Errors in Medical Practice: Systematic
Classification and Reduction with Automated Information Systems," J.
of Medical Systems, vol. 27, no. 4, pp. 297-313, Aug. 2003.
[3] Vapnik, V., Statistical Learning Theory, Wiley, New York, 1998.
[4] I. El-Naqa, Y. Yang, M.N. Wernick, N.P. Galatsanos, R.M. Nishikawa,
"A Support Vector Machine Approach for Detection of
Microcalcifications", IEEE Tran. Med. Imaging, vol. 21, no. 12, pp.
1552-1563, Dec. 2002.
[5] A. Schwaighofer, P. Mayer, A. Krause, J. Beuthan, H. Rost, G. Metzger,
G.A. M├╝ller, A.K. Scheel, "Classification Of Rheumatoid Inflammation
Based on Laser Imaging", IEEE Tran. on Biomed. Eng., vol. 50, no. 3,
pp. 375-382, March 2003.
[6] K.N. Prakash, A.G. Ramakrishnan, S. Suresh, T.W.P. Chow, "Fetal
Lung Maturity Analysis Using Ultrasound Inage Features", IEEE Tran.
on Inf. Tech. in Biomed., vol. 6, no. 1, pp. 38-45, March 2002.
[7] S.B. Gökt├╝rk, C. Tomasi, B. Acar, C.F. Beaulieu, D.S. Paik, R.B.
Jeffrey, J. Yee, S. Napel, "A Statistical 3-D Pattern Processing Method
for Computer-Aided Detection of Polyps in CT Colonography", IEEE
Tran. on Med. Imag., vol. 20, no. 12, pp. 1251-1260, Dec. 2001.
[8] S. Chatterjee, "Classification of natural textures using Gaussian Markov
random field models", in Markov Random Fields, Theory and
Applications, R. Chellappa, A. Jain, Ed., Academic Press, 1993, pp.
159-177.
[9] B.S. Manjunath, R. Chellappa, "Unsupervised texture segmentation
using Markov random field models," IEEE Tran. Patt. Anal. Machine
Intel., vol. 13, pp. 478-482, 1991.
[10] M.E. Jernigan, F. D-Astous, "Entropy-based texture analysis in the
spatial frequency domain," IEEE Tran. Patt. Anal. Machine Intel., vol.
6, pp. 237-243, 1984.
[11] S.Z. Li, Markov Random Field Modelling in Computer Vision, Springer-
Verlag, 1995.
[12] A. Rosenfeld, "Image modelling during the 1980s: A brief overview", in
Markov Random Fields, Theory and Applications, R. Chellappa, A. Jain,
Ed., Academic Press, 1993, pp. 1-10.
[13] R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification, 2nd ed., John
Wiley & Sons, Inc., 2001, ch. 2,4,6.