Advertisement

Stochastic Geometry for Automatic Assessment of Ki-67 Index in Breast Cancer Preparations

  • Marek Kowal
  • Marcin Skobel
  • Józef Korbicz
  • Roman Monczak
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10814)

Abstract

Proliferative activity of cells is one of the most critical factors in breast cancer diagnosis. It is used to evaluate tumor cell progression and to predict treatment responses in chemotherapy. Ki-67 is a nuclear biomarker commonly used to measure cellular proliferation rate. The ratio between the number of Ki-67 positive tumor nuclei and all tumor nuclei defines Ki-67 index. However, manual cell counting is tedious and time consuming because hundreds of nuclei must be labeled. To speed up the analysis process, nuclei can be segmented automatically and then classified based on staining color. Unfortunately, segmentation of individual nuclei is a big challenge because they often create complex clusters comprised of many touching and overlapping nuclei. To deal with complexities and ambiguities of cytological material we propose a generative model which approximates nuclei using ellipses. We assume that the process of generating a cytological sample has stochastic nature. Therefore it is possible to reconstruct this process using marked point process tuned according to observed cytological sample. To verify the potential of the proposed method, we applied it to determine Ki-67 index in breast cancer immunochemistry samples. The results of experiments have shown that Ki-67 indices determined by proposed approach correlate well with those computed manually.

Keywords

Breast cancer Ki-67 index Nuclei segmentation Stochastic process Steepest ascent optimization Maximum a posteriori estimation 

Notes

Acknowledgments

The research was supported by National Science Centre, Poland (2015/17/B/ST7/03704).

References

  1. 1.
    Abubakar, M., et al.: High-throughput automated scoring of Ki67 in breast cancer tissue microarrays from the Breast Cancer Association Consortium. J. Pathol: Clin. Res. 2(3), 138–153 (2016)Google Scholar
  2. 2.
    Baddeley, A.J., van Lieshout, M.N.M.: ICM for object recognition. In: Dodge, Y., Whittaker, J. (eds.) Computational Statistics, vol. 2, pp. 271–286. Physica-Verlag HD, Heidelberg (1992).  https://doi.org/10.1007/978-3-642-48678-4_34CrossRefGoogle Scholar
  3. 3.
    Baddeley, A.J., van Lieshout, M.N.M.: Stochastic geometry models in high-level vision. In: Mardia, K.V., Kanji, G.K. (eds.) Advances in Applied Statistics, Statistics and Images, vol. 1, pp. 231–256. Carfax Publishing, Abingdon (1993)Google Scholar
  4. 4.
    Bembenik, R., Jóźwicki, W., Protaziuk, G.: Methods for mining co-location patterns with extended spatial objects. Int. J. Appl. Math. Comput. Sci. 27(4), 681–695 (2017)CrossRefGoogle Scholar
  5. 5.
    Cheang, M.C., Chia, S.K., Voduc, D., Leung, S., Snider, J.: Ki67 index, HER2 status, and prognosis of patients with luminal B breast cancer. J. Natl. Cancer Inst. 101(10), 736–750 (2009)CrossRefGoogle Scholar
  6. 6.
    Descombes, X.: Stochastic Geometry for Image Analysis. Wiley, Hoboken (2012)zbMATHGoogle Scholar
  7. 7.
    Descombes, X.: Multiple objects detection in biological images using a marked point process framework. Methods 115(Suppl. C), 2–8 (2017)CrossRefGoogle Scholar
  8. 8.
    Kowal, M., Filipczuk, P.: Nuclei segmentation for computer-aided diagnosis of breast cancer. Int. J. Appl. Math. Comput. Sci. 24(1), 19–31 (2014)MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    van Lieshout, M.N.M.: Markov point processes and their applications in high-level imaging. Bull. Int. Stat. Inst. 56, 559–576 (1995)zbMATHGoogle Scholar
  10. 10.
    Markowsky, P., Reith, S., Zuber, T.E., König, R., Rohr, K., Schnörr, C.: Segmentation of cell structures using model-based set covering with iterative reweighting. In: 2017 IEEE 14th International Symposium Biomedical Imaging (ISBI 2017), pp. 392–396, April 2017Google Scholar
  11. 11.
    Mazurek, P., Oszutowska-Mazurek, D.: From the slit-island method to the Ising model: analysis of irregular grayscale objects. Int. J. Appl. Math. Comput. Sci. 24(1), 49–63 (2014)MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Ruifrok, A.C., Johnston, D.A.: Quantification of histochemical staining by color deconvolution. Anal. Quant. Cytol. Histol. 23(4), 291–299 (2001)Google Scholar
  13. 13.
    Saha, M., Chakraborty, C., Arun, I., Ahmed, R., Chatterjee, S.: An advanced deep learning approach for Ki-67 stained hotspot detection and proliferation rate scoring for prognostic evaluation of breast cancer. Sci. Rep. 7(1), 3213 (2017)CrossRefGoogle Scholar
  14. 14.
    Strauss, D.J.: A model for clustering. Biometrika 62(2), 467–475 (1975)MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Tuominen, V.J., Ruotoistenmäki, S., Viitanen, A., Jumppanen, M., Isola, J.: ImmunoRatio: a publicly available web application for quantitative image analysis of estrogen receptor (ER), progesterone receptor (PR), and Ki-67. Breast Cancer Res. 12(4), R56 (2010).  https://doi.org/10.1186/bcr2615CrossRefGoogle Scholar
  16. 16.
    Vörös, A., Csörgő, E., Nyári, T., Cserni, G.: An intra- and interobserver reproducibility analysis of the Ki-67 proliferation marker assessment on core biopsies of breast cancer patients and its potential clinical implications. Pathobiology 80, 111–118 (2013).  https://doi.org/10.1159/000343795CrossRefGoogle Scholar
  17. 17.
    Xing, F., Su, H., Neltner, J., Yang, L.: Automatic Ki-67 counting using robust cell detection and online dictionary learning. IEEE Trans. Biomed. Eng. 61(3), 859–870 (2014)CrossRefGoogle Scholar
  18. 18.
    Yeo, M.K., Kim, H.E., Kim, S.H., Chae, B.J., Song, B.J., Lee, A.: Clinical usefulness of the free web-based image analysis application ImmunoRatio for assessment of Ki-67 labelling index in breast cancer. J. Clin. Pathol. 70(8), 715–719 (2017). http://jcp.bmj.com/content/70/8/715

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Marek Kowal
    • 1
  • Marcin Skobel
    • 1
  • Józef Korbicz
    • 1
  • Roman Monczak
    • 2
  1. 1.Faculty of Computer, Electrical and Control Engineering, Institute of Control and Computation EngineeringUniversity of Zielona GóraZielona GóraPoland
  2. 2.Department of PathomorphologyUniversity Hospital in Zielona GóraZielona GóraPoland

Personalised recommendations