Advertisement

Feature Selection and Mass Classification Using Particle Swarm Optimization and Support Vector Machine

  • Man To Wong
  • Xiangjian He
  • Wei-Chang Yeh
  • Zaidah Ibrahim
  • Yuk Ying Chung
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8836)

Abstract

This paper proposes an effective technique to classify regions of interests (ROIs) of digitized mammograms into mass and normal breast tissue regions by using particle swarm optimization (PSO) based feature selection and Support Vector Machine (SVM). Twenty-three texture features were derived from the gray level co-occurrence matrix (GLCM) and gray level histogram of each ROI. PSO is used to search for the gamma and C parameters of SVM with RBF kernel which will give the best classification accuracy, using all the 23 features. Using the parameters of SVM found by PSO, PSO based feature selection is used to determine the significant features. Experimental results show that the proposed PSO based feature selection technique can find the significant features that can improve the classification accuracy of SVM. The proposed classification approach using PSO and SVM has better specificity and sensitivity when compared to other mass classification techniques.

Keywords

mass classification support vector machine particle swarm optimization feature selection 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Garfinkel, L., Catherind, M., Boring, C., Heath, C.: Change trends: an overview of breast cancer incidence and mortality. Cancer 74(1), 222–227 (1997)Google Scholar
  2. 2.
    Bovis, K., Singh, S., Fieldsend, J., Pinder, C.: Identification of masses in digital mammograms with MLP and RBF nets. In: Proc. of the IEEE-INNS-ENNS International Joint Conference in Neural Networks, pp. 342–347 (2000)Google Scholar
  3. 3.
    Cheng, H., Cai, X., Chen, X., Hu, X., Lou, X.: Computer aided detection and classification of microcalcifications in mammograms:a survey. Pattern Recog. 36, 2967–2991 (2003)CrossRefzbMATHGoogle Scholar
  4. 4.
    Cheng, H., Shi, X., Min, R., Hu, L., Cai, X., Du, H.: Approaches for automated detection and classification of masses in mammograms. Pattern Recog. 39, 646–668 (2006)CrossRefGoogle Scholar
  5. 5.
    Eisa, M.M., Ewees, A.A., Refaat, M.M., Elgamal, A.F.: Effective medical image retrieval technique based on texture features. International Journal of Intelligent Computing and Information Science 13(2), 19–33 (2013)Google Scholar
  6. 6.
    Sahiner, B., Chan, H.P., Petrick, N., Wei, D., Helvie, M.A., Adler, D.D., Goodsitt, M.M.: Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images. IEEE Trans. Med. Imaging 15, 598–610 (1996)CrossRefGoogle Scholar
  7. 7.
    Tourassi, G.D., Vargas-Voracek, R., Catarious, D.M., Floyd, C.E.: Computer-assisted detection of mammographic masses: a template matching scheme based on mutual information. Med. Phys. 30, 2123–2130 (2003)CrossRefGoogle Scholar
  8. 8.
    Christoyianni, I., Dermatas, E., Kokkinakis, G.: Neural classification of abnormal tissue in digital mammography using statistical features of the texture. In: Proc. of the 6th IEEE Int’l Conf. on Electronics, Circuits & Systems, vol. 1, pp. 117–120 (1999)Google Scholar
  9. 9.
    Haralick, R.M., Shanmugam, K., Dinstein, I.: Texture features for image classification. IEEE Trans. Syst. Man Cybernet, SMC 3(6), 610–621 (1973)CrossRefGoogle Scholar
  10. 10.
    Petrosian, A., Chan, H.P., Helvie, M.A., Goodsitt, M.M., Adler, D.D.: Computer-aided diagnosis in mammography: classification of mass and normal tissue by texture analysis. Physics in Medicine and Biology 39(12), 2273–2288 (1994)CrossRefGoogle Scholar
  11. 11.
    Angelini, E., Campanini, R., Iampieri, E., Lanconelli, N., Masotti, M.: Testing the performances of Different Image Representations for Mass Classification in Digital mammograms. Int’l Journal of Modern Phys. C 17(1), 113–131 (2006)CrossRefzbMATHGoogle Scholar
  12. 12.
    The Mini-MIAS Database of Mammograms, http://peipa.essex.ac.uk
  13. 13.
    Witten, I.H., Frank, E.: Data mining: practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann (2005)Google Scholar
  14. 14.
    Hsu, C.W., Chang, C.C., Lin, C.J.: A practical guide to support vector classification, http://www.csie.ntu.edu.tw/~cjlin (last updated on April 15, 2010)
  15. 15.
    Bradski, G., Kaehler, A.: LearningOpenCV, 1st edn. O’Reilly (September 2008) Google Scholar
  16. 16.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. on Intelligent Systems and Technology 2(3), Article No. 27 (2011)Google Scholar
  17. 17.
    Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proc. of the IEEE International Joint Conf. on Neural Networks, Australia, vol. 4, pp. 1942–1948 (1995)Google Scholar
  18. 18.
    Eberhart, R., Shi, Y.: Particle swarm optimization: developments, applications and resources. In: Proc. of the Congress on Evolutionary Computation, pp. 81–86 (2001)Google Scholar
  19. 19.
    Kennedy, J., Eberhart, R.: A discrete binary version of the particle swarm algorithm. In: IEEE Int’l Conf. on Syst., Man, and Cybernetics, vol. 5, pp. 4104–4108 (1997)Google Scholar
  20. 20.
    Islam, M.J., Ahmadi, M., Sid-Ahmed, M.A.: An efficient automatic mass classification method in digitized mammograms using artificial neural network. International Journal of Artificial Intelligence and Applications 1(3), 1–13 (2010)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Man To Wong
    • 1
  • Xiangjian He
    • 1
  • Wei-Chang Yeh
    • 2
  • Zaidah Ibrahim
    • 1
    • 3
  • Yuk Ying Chung
    • 4
  1. 1.Faculty of Engineering and Information TechnologyUniversity of Technology SydneyAustralia
  2. 2.Department of Industrial Engineering and Engineering ManagementNational Tsing Hua UniversityHsinchuTaiwan
  3. 3.Faculty of Computer and Mathematical SciencesUniversiti Teknologi MARAMalaysia
  4. 4.School of Information TechnologiesUniversity of SydneyAustralia

Personalised recommendations