A Modular Neural Network System for the Analysis of Nuclei in Histopathological Sections

  • C. S. Pattichis
  • F. Schnorrenberg
  • C. N. Schizas
  • M. S. Pattichis
  • K. Kyriacou
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 96)


The evaluation of immunocytochemically stained histopathological sections presents a complex problem due to many variations that are inherent in the methodology. This chapter describes a modular neural network system which is being used for the detection and classification of breast cancer nuclei named Biopsy Analysis Support System (BASS). The system is based on a modular architecture where the detection and classification stages are independent. Two different methods for the detection of nuclei are being used: the one approach is based on a feed forward neural network (FNN) which uses a block-based singular value decomposition (SVD) of the image, to signal the likelihood of occurrence of nuclei.


Positive Predictive Value Singular Value Decomposition Radial Basis Function Neural Network Human Expert Neural Network Classifier 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Alcatel TITN Answare (1993), IMMUNO 4.00: User’s Guide, 1st ed., Grenoble, France.Google Scholar
  2. [2]
    Bacus, S. and Flowers, J.L. (1988), “The evaluation of estrogen receptor in primary breast carcinoma by computer-assisted image analysis,” Am. J. of Clinical Pathology, vol. 90, pp. 233–239.Google Scholar
  3. [3]
    Bartels, P.H. (1992), “Computer generated diagnosis and image analysis, an overview,” Cancer, vol. 69, pp. 1636–1638.PubMedCrossRefGoogle Scholar
  4. [4]
    Becker, R.L. and Usaf, M.C. (1995), “Applications of neural networks in histopathology,” Pathologica, vol. 87, no. 3, pp. 246254.Google Scholar
  5. [5]
    Bibbo, M., Bartels, P.H., Pfeifer, T., Thompson, D., Minimo, C., and Galera Davidson, H. (1993), “Belief network for grading prostate lesions,” Anal. Quant. Cytol. Histol., vol. 15, pp. 124–135.PubMedGoogle Scholar
  6. [6]
    Biesterfeld, S., Kluppel, D., Koch, R., Schneider, S., Steinhagen, G., Mihalcea, A.M., and Schroder, W. (1998), “Rapid and prognostically valid quantification of immunohistochemical reactions by immunohistometry of the most positive tumour focus,” Journal of Pathology, vol. 185, no. 1, pp. 25–31.PubMedCrossRefGoogle Scholar
  7. [7]
    Birdsong, G.G. (1996), “Automated screening of cervical cytology specimens,” Human Pathology, vol. 27, pp. 468–481.PubMedCrossRefGoogle Scholar
  8. [8]
    Brugal, G. (1985), “Color processing in automated image analysis for cytology,” in Mary, J.Y. and Rigaut, J.P. (Eds.), Quant. Image Analysis in Cancer Cytology and Histology, Amsterdam: Elsevier, pp. 19–33.Google Scholar
  9. [9]
    Burke, H.B. (1994), “Artificial neural networks for cancer research. Outcome prediction,” Sem. Surgical Oncology, vol. 10, pp. 73–79.CrossRefGoogle Scholar
  10. [10]
    Carter, C.L., Allen, C., and Henson, D.E. (1989), “Relation of tumour size, lymph mode status and survival in 24,740 breast cancer cases,” Cancer, vol. 63, pp. 181–187.PubMedCrossRefGoogle Scholar
  11. [11]
    Cell Analysis Systems Inc. (1990), Cell Analysis Systems: Quantitative Estrogen Progesterone Users Manual,Application Version 2.0, Catalog Number 201325–00, USA.Google Scholar
  12. [12]
    Charpin, C., Martin, P.M., DeVictor, B., Lavaut, M.N., Habib, M.C., Andrac, L., and Toga, M. (1988), “Multiparametric study (SAMBA 200) of estrogen receptor immunocytochemical assay in 400 human breast carcinomas,” Cancer Research, vol. 48, pp. 1578–1586.PubMedGoogle Scholar
  13. [13]
    Chen, S., Cowan, C.F.N., and Grant, P.M. (1991), “Orthogonal least squares learning algorithm for radial basis function networks,” IEEE Trans. Neural Networks, vol. 2, no. 2, pp. 302309.Google Scholar
  14. [14]
    Cohen, C. (1996), “Image cytometric analysis in pathology,” Human Pathology, vol. 27, no. 5, pp. 482–493.PubMedCrossRefGoogle Scholar
  15. [15]
    Dawson, A.E., Austin Jr., R.E., and Weinberg, D.S. (1991), “Nuclear grading of breast carcinoma by image analysis,” American Journal of Clinical Pathology, vol. 95 (Suppl. 1), pp. S29 - S37.PubMedGoogle Scholar
  16. [16]
    De Laurentiis, M., De Placido, S., Bianco, AR., Clark, G.M., and Ravdin, P.M. (1999), “A prognostic model that makes quantitative estimates of probability of relapse for breast cancer patients,” Clinical Cancer Research, vol. 5, no. 12, pp. 4133–4139.PubMedGoogle Scholar
  17. [17]
    Deligdisch, L., Einstein, A.J., Guera, D., and Gil, J. (1995), “Ovarian dysplasia in epithelial inclusion cysts. A morphometric approach using neural networks,” Cancer, vol. 76, no. 6, pp. 10271034.Google Scholar
  18. [18]
    Demuth, H. and Beale, M. (1994), Neural Network Toolbox, The MathWorks, Inc., Natick, Mass., USA.Google Scholar
  19. [19]
    Furness, P.N., Levesley, J., Luo, Z., Taub, N., Kazi, J.I., Bates, W.D., and Nicholson, M.L. (1999), “A neural network approach to the biospy diagnosis of early acute renal transplant rejection,” Histopathology, vol. 35, pp. 461–467.PubMedCrossRefGoogle Scholar
  20. [20]
    Garfinkel, L., Boring, C.C., and Heath, C.W. Jr. (1994), “Changing trends. An overview of breast cancer incidence and mortality,” Cancer, vol. 74, pp. 222–227.PubMedCrossRefGoogle Scholar
  21. [21]
    Goldschmidt, D., Decaestecker, C., Berthe, J.V., Gordower, L., Remmelink, M., Danguy, A., Pasteels, J.L., Salmon, I., and Kiss, R. (1996), “The contribution of image cytometry and artificial intelligence-related methods of numerical data analysis for adipose tumor histopathologic classification,” Laboratory Investigation, vol. 75, no. 3, pp. 295–306.PubMedGoogle Scholar
  22. [22]
    Haykin, S. (1994), Neural Networks: a Comprehensive Foundation, New York, USA: Macmillan, 1994.Google Scholar
  23. [23]
    Hong, Z.-Q. (1991), “Algebraic feature extraction of image for recognition,” Pattern Recognition, vol. 24, no. 3, pp. 211–219.CrossRefGoogle Scholar
  24. [24]
    Hubel, D.H. and Wiesel, T.N. (1962), “Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex,” J. Physiol., Lond., vol. 160, pp. 106–154.Google Scholar
  25. [25]
    Jagoe, R., Steele, J.H., Vucicevic, V., Alexander, N., van Noorden, S., Wooton, R., and Polak, J.M. (1991), “Observer variation in quantification of immunocytochemistry by image analysis,” Histochemical Journal, vol. 23, pp. 541–547.PubMedCrossRefGoogle Scholar
  26. [26]
    Jain, A.K. (1989), Fundamentals of Digital Image Processing, Englewood Cliffs, New Jersey, USA: Prentice Hall, 1989.Google Scholar
  27. [27]
    Kelsey, J.L. and Horn-Ross, P.L. (1993), “Breast cancer: magnitude of the problem and descriptive epidemiology,” Epidemiological Reviews, vol. 15, no. 1, pp. 7–16.Google Scholar
  28. [28]
    Kok, M.R. and Boon, M.E. (1996), “Consequences of neural network technology for cervical screening,” Cancer, vol. 78, pp. 112–117.PubMedCrossRefGoogle Scholar
  29. [29]
    Koss, L.G. (2000), “The Application of PAPNET to Diagnostic Cytology,” in Lisboa, P.J.G., Ifeachor, C., and Szczepaniak, P.S. (Eds.), Artificial Neural Networks in Biomedicine, Springer-Verlag, London, pp. 51–67.CrossRefGoogle Scholar
  30. [30]
    Lundin, M., Lundin, J., Burke, H.B., Toikkanen, S., Pylkkanen, L., and Joensuu, H. (1999), “Artificial neural networks applied to survival prediction in breast cancer,” Oncology, vol. 57, pp. 281286.Google Scholar
  31. [31]
    Mangasarian, O.L., Street, W.N., and Wolberg, W.H. (1995), “Breast cancer diagnosis and prognosis via linear programming,” Operations Research, vol. 43, no. 4, pp. 570–577.CrossRefGoogle Scholar
  32. [32]
    Man, D. and Hildreth, E. (1980), “Theory of edge detection,” Proc. R. Soc. Lond., vol. B 207, pp. 187–217.Google Scholar
  33. [33]
    McCarty Jr., K.S., Miller, L.S., Cox, E.B., Konrath, J., and McCarty Sr., K.S. (1985), “Estrogen receptor analyses. Correlation of biochemical and immunohistochemical methods using monoclonal antireceptor antibodies,” Arch. Pathol. Lab. Med., vol. 109, pp. 716–721.PubMedGoogle Scholar
  34. [34]
    Millot, C. and Dufer, J. (2000), “Clinical applications of image cytometry to human tumour analysis,” Histology Histopathology, vol. 15, no. 4, pp. 1185–200.PubMedGoogle Scholar
  35. [35]
    Naguib, R.N., Sakim, H.A., Lakshmi, M.S., Wadehra, V., Lennard, T.W., Bhatavdekar, J., and Sherbet, G.V. (1999), “DNA ploidy and cell cycle distribution of breast cancer aspirate cells measured by image cytometry and analyzed by artificial neural networks for their prognostic significance,” IEEE Trans Information Technology Biomedicine, vol. 3, no. 1, pp. 61–69.CrossRefGoogle Scholar
  36. [36]
    Newcomb, P.A. and Lantz, P.M. (1993), “Recent trends in breast cancer incidence, mortality, and mammography,” Breast Cancer Research and Treatment, vol. 28, pp. 97–106.PubMedCrossRefGoogle Scholar
  37. [37]
    O’Brien, M.J. and Sotnikov, A.V. (1996), “Digital imaging in anatomic pathology,” American Journal of Clinical Pathology, vol. 106, no. 4, suppl. 1, pp. S25 - S32.Google Scholar
  38. [38]
    Pantazopoulos, D., Karakitsos, P., Iokim-Liossi, A., Pouliakis, A., Botsoli-Stergiou, E., and Dimopoulos, C. (1998), “Back propagation neural network in the discrimination of benign from malignant lower urinary tract lesions,” Journal of Urology, vol. 159, no. 5, pp. 1619–1623.PubMedCrossRefGoogle Scholar
  39. [39]
    Pisani, P., Parkin, D.M., Bray, F., and Ferlay, J. (1999), “Estimates of the world mortality from 25 cancers in 1990,” International Journal of Cancer, vol. 83, pp. 18–29.CrossRefGoogle Scholar
  40. [40]
    Press, W.H., Flattery, B.P., Teukovsky, S.A., and Vetterling, W.T. (1988), Numerical Recipes in C, Cambridge, UK: University Press.Google Scholar
  41. [41]
    Ravdin, P.M. and Clark, G.M. (1992), “A practical application of neural network analysis for predicting outcome of individual breast cancer patients,” Breast Cancer Research and Treatment, vol. 22, pp. 285–293.PubMedCrossRefGoogle Scholar
  42. [42]
    Schnorrenberg, F., Pattichis, C.S., Kyriacou, K., Vassiliou, M., and Schizas, C.N. (1996), “Computer-aided classification of breast cancer nuclei,” Technology and Health Care, vol. 4, no. 2, pp. 147–161.PubMedGoogle Scholar
  43. [43]
    Schnorrenberg, F., Pattichis, C.S., Kyriacou, K., and Schizas, C.N. (1997), “Computer-aided detection of breast cancer nuclei,” IEEE Trans. Information Technology in Biomedicine, vol. 1, no. 2, pp. 128–140.CrossRefGoogle Scholar
  44. [44]
    Schnorrenberg, F., Tsapatsoulis, N., Pattichis, C.S., Schizas, C.N., Kollias, S., Vassiliou, M., Adamou, A., and Kyriacou, K. (2000), “Improved detection of breast cancer nuclei using modular neural networks,” IEEE Engineering in Medicine and Biology Magazine, Special Issue on Classifying Patterns with Neural Networks, vol. 19, no. 1, pp. 48–63.Google Scholar
  45. [45]
    Schnorrenberg, F., Pattichis, C.S., Kyriacou, K., and Schizas, C.N. (2000), “Content-based retrieval of breast cancer biopsy slides,” Technology and Health Care, vol. 8, to appear in Dec.Google Scholar
  46. [46]
    Störkel, S., Reichert, T., Reiffen, K.A., and Wagner, W. (1993), “EGFR and PCNA expression in oral squamous cell carcinomas: a valuable tool in estimating the patients prognosis,” European Journal of Cancer, vol. 29B, pp. 273–277.Google Scholar
  47. [47]
    Taylor, C.R. (1993), “An exaltation of experts: concerted efforts in the standardization of immunohistochemistry,” Applied Immunohistochemistry, vol. 1, pp. 232–243.Google Scholar
  48. [48]
    True, L.D. (1996), “Morphometric applications in anatomic pathology,” Human Pathology, vol. 27, pp. 450–467.PubMedCrossRefGoogle Scholar
  49. [49]
    Weinberg, D.S. (1994), “Quantitative immunocytochemistry in pathology,” in: Marchevsky, A.M. and Bartels, P.H. (Eds.), Image Analysis: a Primer for Pathologists, New York, USA: Raven Press Ltd., pp. 235–260.Google Scholar
  50. [50]
    Willemse, F., Nap, M., Henzen-Logmans, S.C., and Eggink, H.F. (1994), “Quantification of area percentage of immunohistochemical staining by true color image analysis with application of fixed thresholds,” Analytical and Quantitative Cytology and Histology, vol. 16, no. 5, pp. 357–364.PubMedGoogle Scholar
  51. [51]
    Wolberg, W.H., Street, W.N., and Mangassarian, O.L. (1999), “Importance of nuclear morphology in breast cancer prognosis,” Clinical Cancer Research, vol. 11, pp. 3542–3548.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • C. S. Pattichis
  • F. Schnorrenberg
  • C. N. Schizas
  • M. S. Pattichis
  • K. Kyriacou

There are no affiliations available

Personalised recommendations