Abstract
Breast cancer is the leading cancer among females, the key technology of preventing breast cancers is early detection. Based on the advantage of support vector machine (SVM), finding global solution and possessing higher generalization capability on dealing with the small sample, a new method of diagnosing breast cancer by CAD is proposed in this paper. Firstly, a principal component analysis is used to represent the information of ROI image, which account for most of the variance of the original data set while significantly reducing the data dimension. After the extraction of principal components, only those data of which account for most part of variance were retained as the feature vector and input into a SVM classification and BP neural network classification to classify. Finally, the results of experiment show that the accuracy and specificity for the diagnosis of breast cancer using SVM classification is good.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Mangasarian, O.L., Nick Street, W., Wolberg, W.H.: Breast cancer diagnosis and prognosis via linear programming. Operations Research, 570–577 (1995)
Breiman, L., Friedman, J., Olshen, R.: Classification and Regression Trees. Wadsworth (1984)
Burke, H.B., Goodman, P.H., et al.: Artificial neural networks improve the accuracy of cancer survival prediction. Cancer, pp. 857–862 (1997)
Zhu, C., Palmer, G.M., Breslin, T.M., Harter, J., Ramanujam, N.: Diagnosis of Breast Cancer Using Diffuse Reflectance Spectroscopy: Comparison of a Monte Carlo Versus Partial Least Squares Analysis Based Feature Extraction Technique. Lasers in Surgery and Medicine, pp. 714–724 (2006)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, Heidelberg (1995)
Goertzel, B., Venuto, J.: Accurate SVM Text Classification for Highly Skewed Data Using Threshold Tuning and Query-Expansion-Based Feature Selection.Neural Networks. In: IJCNN 2006. International Joint Conference on, pp. 1220–1225 (2006)
LeCun, Y.: Comparison of learning algotithms for handwritten digit recognition. Image and Vision Computing, pp. 675–692 (2003)
Qin, J., He, Z.: A SVM face recognition method based on Gabor-featured key points. Machine Learning and Cybernetics. In: Proceedings of 2005 International Conference on, pp. 5144–5149 (2005)
Ye, Z., Auner, G.: Principal component analysis approach for biomedical sample identification. Systems, Man and Cybernetics. In: 2004 IEEE International Conference on, pp. 1348–1353 (2004)
Bian, Z., Zhang, X.: Pattern Recognition. Tsinghua University Press, Beijing (2000)
Xu, J.: Image processing and analysis. Science Press, Beijing (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liu, J., Ma, W. (2007). An Effective Recognition Method of Breast Cancer Based on PCA and SVM Algorithm. In: Zhang, D. (eds) Medical Biometrics. ICMB 2008. Lecture Notes in Computer Science, vol 4901. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-77413-6_8
Download citation
DOI: https://doi.org/10.1007/978-3-540-77413-6_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-77410-5
Online ISBN: 978-3-540-77413-6
eBook Packages: Computer ScienceComputer Science (R0)