An Improved Initialization Based Histogram of K-Mean Clustering Algorithm for Hyperchromatic Nucleus Segmentation in Breast Carcinoma Histopathological Images

  • Xiao Jian TanEmail author
  • Nazahah Mustafa
  • Mohd Yusoff Mashor
  • Khairul Shakir Ab Rahman
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 547)


Mitotic count assessment in breast carcinoma can be a considerable challenge especially when involve with algorithm development. The challenges lie within the hyperchromatic nucleus segmentation that served as a fundamental block in mitotic count assessment. In this study, we proposed an improved initialization based histogram of K-Mean clustering algorithm for hyperchromatic nucleus segmentation in breast carcinoma histopathological images. The focus is to segment the hyperchromatic nucleus from the background using K-Mean clustering algorithm. Conventional initialization method for K-Mean clustering was improved by establishing a relationship between the hyperchromatic nucleus and the intensity histogram. 75 images captured from 15 histopathological slides were used as dataset. The overall Sensitivity in ground truth segmentation of the proposed method was found to have a percentage of 100.0%. The values of precision (AreaPre) and sensitivity (AreaSen) in mitotic cells area segmentation were found to be promising with percentages of 95.2% and 89.2%, respectively. The promising results perhaps could be used to enhance performance of the true mitotic cell detection.


Breast carcinoma Nottingham histological grading system Hyperchromatic nucleus Segmentation K-Mean clustering 



The authors would like to acknowledge the support from the Fundamental Research Grant Scheme (FRGC) under a grant number of FRGS/1/2016/SKK06/UNIMAP/02/3 from the Ministry of Higher Education Malaysia. The protocol of this study had been approved by Medical Research and Committee of National Medical Research Register (NMRR) Malaysia (NMRR-17-281-34236).


  1. 1.
    Doyle, S., Feldman, M., Shih, N., Tomaszewski, J., Madabhushi, A.: Cascaded discrimination of normal, abnormal, and confounder classes in histopathology: gleason grading of prostate cancer. BMC Bioinform. 13(1), 282 (2012). Scholar
  2. 2.
    Nateghi, R., Danyali, H., Helfroush, M.S.: Maximized inter-class weighted mean for fast and accurate mitosis cells detection in breast cancer histopathology images. J. Med. Syst. 41(9) (2017).
  3. 3.
    Tan, X.J., Mustafa, N., Mashor, M.Y., Rahman, K.S.: Hyperchromatic nucleus segmentation on breast histopathological images for mitosis detection. J. Telecommun. Electron. Comput. Eng. 10(1–16), 27–30 (2018)Google Scholar
  4. 4.
    Pourakpour, F., Ghassemian, H.: Automated mitosis detection based on combination of effective textural and morphological features from breast cancer histology slide images. (November), 25–27 (2015).
  5. 5.
    Khan, A.M., Eldaly, H., Rajpoot, N.M.: A gamma-gaussian mixture model for detection of mitotic cells in breast cancer histopathology images. J. Pathol. Inform. 4(Icpr), 11 (2013).
  6. 6.
    Nasir, A.S.A., Mashor, M.Y., Mohamed, Z.: Segmentation based approach for detection of malaria parasites using moving k-means clustering. In: 2012 IEEE EMBS Conference on Biomedical Engineering and Sciences, pp. 653–658 (2012).
  7. 7.
    Mashor, M.Y.: Hybrid training algorithm for RBF network. Int. J. Comput. Internet Manag. 8(1990), 50–65 (2000). Scholar
  8. 8.
    Shao, G., Wu, S., Li, T.: cDNA microarray image segmentation with an improved moving k-means clustering method. In: Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing IEEE ICSC 2015, pp. 306–311 (2015).
  9. 9.
    Fuyuan, C., Liang, J.Y., Jiang, G.: An initialization method for the K-Means algorithm using neighborhood model. Comput. Math. Appl. 58(3), 474–483 (2009)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Meilă, M., Heckerman, D.: An experimental comparison of several clustering and initialization methods. In: Proceedings of the Fourteenth Conference on Uncertain, Artificial Intelligence, pp. 386–395 (1998)Google Scholar
  11. 11.
    Vancea, C.C., Miclea, V.C., Nedevschi, S.: Improving stereo reconstruction by sub-pixel correction using histogram matching. In: IEEE Intelligent Vehicles Symposium (IV), Proceedings, pp. 335–341 (2016).
  12. 12.
    Hamann, S., Hell, H., Pankow, D., Wunderer, R.: Color model selection and separation. In: DigiScript™. Springer, Berlin, Heidelberg (1997).
  13. 13.
    Veta, M., Pluim, J.P.W., Van, D.P.J., Viergever, M.A.: Breast cancer histopathology image analysis: a review. IEEE Trans. Biomed. Eng. 61(5), 1400–1411 (2014). Scholar
  14. 14.
    Veta, M., Van, D.P.J., Willems, S., Wang, H., Madabhushi, A., Gonzalez, F., Roa, A.C., Larsen, A.B.L., Vestergaard, J.S., Dahl, B., Cireșan, D.C., Schmidhuber, J., Giusti, A., Luca, M.: Assessment of mitosis detection algorithms in breast cancer histopathology images. Med. Image Anal. 2013, 1–21 (2013).

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Xiao Jian Tan
    • 1
    Email author
  • Nazahah Mustafa
    • 1
  • Mohd Yusoff Mashor
    • 1
  • Khairul Shakir Ab Rahman
    • 2
  1. 1.School of Mechatronic EngineeringUniversity Malaysia PerlisArauMalaysia
  2. 2.Hospital Tuanku FauziahKangarMalaysia

Personalised recommendations