Two Approaches for Automatic Nuclei Cell Counting in Low Resolution Fluorescence Images

  • Thierry BrouardEmail author
  • Aurélie Chantôme
Part of the Computational Methods in Applied Sciences book series (COMPUTMETHODS, volume 19)


This paper deals with the problem of counting nuclei in low-resolution fluorescence images. The low resolution is a consequence of the usage of a large field of view, this to reduce the number of experiments, implying time saving and money saving. But the small size of nuclei increases the risk of error in counting. In this work we used some image processing basic operators in order to extract potential shapes. These shape are then characterized (size, shape, edges) to decide if they are noise or not. Two approaches are presented for this: the first one correspond to a translation of some basic knowledge used by practitioners; the second one uses a supervised classification technique where it is the computer who discovers the knowledge by the analysis of a database of cases. This leads to a fast technique which gives very good results, validated by cell biology experts.


Image processing Classification SVM Cell counting 



The authors wish to thank C. Vandier and A. Girault (both belonging to the INSERM U921, Nutrition, Croissance & Cancer Lab.) for their advice and assistance in carrying out this work.


  1. 1.
    Adiga, P., Chaudhuri, B.: An efficient method based on watershed and rule-based merging for segmentation of 3-d histo-pathological images. Pattern Recogn. 34, 1449–1458 (2001)zbMATHCrossRefGoogle Scholar
  2. 2.
    Chang, C.-C., Lin C.-J.: LIBSVM: a library for support vector machines (2001)
  3. 3.
    Cloppet, F., Boucher, A.: Segmentation of overlapping/aggregating nuclei cells in biological images. In: 19th International Conference on Pattern Recognition (ICPR), Tampa, FL, USA (2008)Google Scholar
  4. 4.
    Dill, D., Scholz, A., Gül, M., Wolf, B.: Methods for counting cells supported by digital image processing. In: Heidelberg, S.B. (ed.) 14th Nordic-Baltic Conference on Biomedical Engineering and Medical Physics. In: IFMBE Proceedings, vol.20, pp. 493–496. Riga, Latvia (2008)CrossRefGoogle Scholar
  5. 5.
    Fan, R.-E., Chen, P.-H., Lin, C.-J.: Working set selection using second order information for training SVM. J. Mac. Learn. Res. 6, 1889–1918 (2005)MathSciNetGoogle Scholar
  6. 6.
    Imagej: Image processing and analysis in java.
  7. 7.
    Kuba, H., Hotta, K., Takahashi, H.: Automatic Particle Detection and Counting by One-Class SVM from Microscope Image. LNCS 5507/2009, pp. 361–368 (2009) doi: 10.1007/978-3-642-03040-6_44Google Scholar
  8. 8.
    Lerner, B., Clocksin, W., Dhanjal, S., Hulten, M., and Bishop, C.: Feature representation and signal classification in fluorescence in-situ hybridization image analysis. IEEE Trans. Syst. Man Cybern. Part A Syst. Humans 31(6), 655–665 (2001)CrossRefGoogle Scholar
  9. 9.
    Lerner, B.: Bayesian fluorescence in situ hybridisation signal classification. Artif. Intelli. Med. 30(3), 301–316 (2004)CrossRefGoogle Scholar
  10. 10.
    Markiewicz, T., Osowski, S., Mariańska, B.: White Blood Cell Automatic Counting System Based on Support Vector Machine. LNCS 4432/2007, pp. 318–326 (2007) doi: 10.1007/978-3-540-71629-7_36Google Scholar
  11. 11.
    Nanni, L., Lumini, A.: A reliable method for cell phenotype image classification. Artif. Intell. Med. 43(2), 87–97 (2008)CrossRefGoogle Scholar
  12. 12.
    Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. Part A Syst. Humans 9(1), 62–66 (1979)MathSciNetGoogle Scholar
  13. 13.
    Pedroso, J.-P., Murata, N.: Support vector machines with different norms: motivation, formulations and results. Pattern Recogn. Lett. 22(12), 1263–1272 (2001)Google Scholar
  14. 14.
    Potier, M., Joulin, V., Roger, S., Besson, P., Jourdan, M.-L., Leguennec, J.-Y., Bougnoux, P., Vandier, C.: Identification of sk3 channel as a new mediator of breast cancer cell migration. Mol. Cancer Ther. 5(11), 2946–2953 (2006)CrossRefGoogle Scholar
  15. 15.
    Schmitt, O., Hasse, M.: Radial symmetries based decomposition of cell clusters in binary and grey level images. Pattern Recogn. 41, 1905–1923 (2008)zbMATHCrossRefGoogle Scholar
  16. 16.
    Sezgin, M., Sankur, B.: Survey over image thresholding techniques and quantitative performance evaluation. J. Electron. Imag. 13(1), 146–168 (2004)CrossRefGoogle Scholar
  17. 17.
    Shawe-Taylor, J., Cristianini, N.: Support Vector Machines and other kernel-based learning methods. Cambridge University Press (2000)Google Scholar
  18. 18.
    Theera-Umpon, N., Dougherty, E., Gader, P.: Non-homothetic granulometric mixing theory with application to blood cell counting. Pattern Recogn. 34, 2547–2560 (2001)zbMATHCrossRefGoogle Scholar
  19. 19.
    Ushizima, D.M., Lorena, A.C., de Carvalho, A.C.P.: Support Vector Machines Applied to White Blood Recognition. In: 5th International Conference Hybrid Intelligent Systems, Rio de Janeiro, pp. 234–237. Rio de Janeiro, Brazil (2005)Google Scholar
  20. 20.
    Villalonga, N., Ferreres, J.-C., Argilés, J.-M., Condom, E., Felipe, A.: Potassium channels are a new target field in anticancer drug design. Recent Pat. Anticancer Drug Discov. 2(3), 212–223 (2007)CrossRefGoogle Scholar
  21. 21.
    Ta, V.-T., Lézoray, O., Elmoataz, A., Schüpp, S.: Graph-based tools for microscopic cellular image segmentation. Pattern Recogn. 42, 1113–1125 (2009)CrossRefGoogle Scholar
  22. 22.
    Xbench homepage.

Copyright information

© Springer Science+Business Media B.V. 2011

Authors and Affiliations

  1. 1.Laboratoire d’InformatiqueUniversité François RabelaisToursFrance
  2. 2.INSERM U921, Nutrition, Croissance & CancerToursFrance

Personalised recommendations