Mammogram Image Segmentation Using Hybridization of Fuzzy Clustering and Optimization Algorithms

  • Guru Kalyan Kanungo
  • Nalini Singh
  • Judhisthir Dash
  • Annapurna Mishra
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 309)


Mammogram images have the ability to assist physicians in detecting breast cancer caused by cells abnormal growth. But due to visual interpretation, false results can be obtained. In this paper, to reduce false results, image segmentation is carried out to find breast cancer mass. Image segmentation using Fuzzy clustering: K means, FCM, and FPCM shows result better than other existing methods but initialization problem and sensitivity to noise do not make them to achieve better accuracy. Various extension of the FCM for segmentation is developed. But most of them modify the objective function which changes the basic FCM algorithm. Hence efforts have been made to develop FCM algorithm without modifying objective function for better segmentation. We have proposed a technique GA-ACO-FCM, which is the hybridization of optimization tools: genetic algorithm and ant colony optimization with fuzzy C means .GA-ACO-FCM is suitable to overcome initialization problem of FCM and shows better results with achieving high accuracy.


Image segmentation Mammography K-means Fuzzy C-means FPCM and GA-ACO-FCM 



The authors thank to Prof. A.K. Tripathy, Dr. B.B. Mishra, and Dept. of Electronics and Telecommunication for their valuable tips and suggestion on this topic and programming.


  1. 1.
    Dong, A., Wang, B.: Feature selection and analysis on mammogram classification. In: Communications, Computers and Signal Processing, pp. 731–735 (2009)Google Scholar
  2. 2.
    Thangavel, K., Mohideen, A.K.: Semi-supervised k-means clustering for outlier detection in mammogram classification. In: IEEE International Conference on Trendz in Information Sciences & Computing (TISC), pp. 68–72 (2010)Google Scholar
  3. 3.
    Cahoon, T.C., Sutton, M.A., Bezdek, J.C.: Breast cancer detection using image processing techniques. In: IEEE 9th International Conference on Fuzzy Systems, vol. 2, pp. 973–976 (2000)Google Scholar
  4. 4.
    Barrea, A.: Local fuzzy C-means clustering for medical spectroscopy images. Appl. Math. Sci. 5(30), 1449–1458 (2011)MATHGoogle Scholar
  5. 5.
    Maitra, I.K., Nag, S., Bandyopadhyay, S.K.: Identification of abnormal masses in digital mammography images. Int. J. Comput. Graph. 2(1), 17–30 (2011)Google Scholar
  6. 6.
    Singh, N., Mohapatra, A.G., Kanungo, G.K.: Breast cancer mass detection in mammograms using K-means and fuzzy C-means clustering. Int. J. Comput. Appl. 22(2), 15–21 (2011)Google Scholar
  7. 7.
    Prasad, K.S., Basha, S.S.: Automatic detection of breast cancer mass in mammograms using morphological operators and fuzzy C-means clustering. J. Theor. Appl. Info. Technol. 5, 704–709 (2009)Google Scholar
  8. 8.
    Das, P., Bhattacharyya, D., Bandyopadhyay, S.K., Kim, T.H.: Analysis and diagnosis of breast cancer. Int. J. u- and e-Serv. Sci. Technol. 2(2), 1–12 (2009)Google Scholar
  9. 9.
    Peng, Y., Hou, X., Liu, S.: The k-means clustering algorithm based on density and ant colony. In: IEEE International Conference in Neural Networks and Signal Processing, vol. 1, pp. 457–460 (2003)Google Scholar
  10. 10.
    Azadeh, A., Keramati, A., Panahi, H.: A hybrid GA-ant colony approach for exploring the relationship between IT and firm performance. Int. J. Bus. Info. Syst. Arch. 4(5), 542–563 (2009)Google Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  • Guru Kalyan Kanungo
    • 1
  • Nalini Singh
    • 2
  • Judhisthir Dash
    • 1
  • Annapurna Mishra
    • 1
  1. 1.Department of Electronics and Telecommunication EngineeringSilicon Institute of TechnologyBhubaneswarIndia
  2. 2.Department of Applied Electronics and Instrumentation EngineeringSilicon Institute of TechnologyBhubaneswarIndia

Personalised recommendations