Advertisement

Deep Convolutional Gaussian Mixture Model for Stain-Color Normalization of Histopathological Images

  • Farhad Ghazvinian ZanjaniEmail author
  • Svitlana Zinger
  • Peter H. N. de With
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11071)

Abstract

Automated microscopic analysis of stained histopathological images is degraded by the amount of color and intensity variations in data. This paper presents a novel unsupervised probabilistic approach by integrating a convolutional neural network (CNN) and the Gaussian mixture model (GMM) in a unified framework, which jointly optimizes the modeling and normalizing the color and intensity of hematoxylin- and eosin-stained (H&E) histological images. In contrast to conventional GMM-based methods that are applied only on the color distribution of data for stain color normalization, our proposal learns how to cluster the tissue structures according to their shape and appearance and simultaneously fits a multivariate GMM to the data. This approach is more robust than standard GMM in the presence of strong staining variations because fitting the GMM is conditioned on the appearance of tissue structures in the density channel of an image. Performing a gradient descent optimization in an end-to-end learning, the network learns to maximize the log-likelihood of data given estimated parameters of multivariate Gaussian distributions. Our method does not need ground truth, shape and color assumptions of image contents or manual tuning of parameters and thresholds which makes it applicable to a wide range of histopathological images. Experiments show that our proposed method outperforms the state-of-the-art algorithms in terms of achieving a higher color constancy.

Keywords

Computational pathology Stain-color normalization Gaussian mixture model (GMM) Convolutional neural network (CNN) 

References

  1. 1.
    Bejnordi, B., et al.: Stain specific standardization of whole-slide histopathological images. IEEE Trans. Med. Imaging 35(2), 404–415 (2016)CrossRefGoogle Scholar
  2. 2.
    Ciompi, F., Geessink, O., Bejnordi, B.E., et al.: The importance of stain normalization in colorectal tissue classification with convolutional networks. In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), pp. 160–163. IEEE (2017)Google Scholar
  3. 3.
    Niethammer, M., Borland, D., Marron, J.S., Woosley, J., Thomas, N.E.: Appearance normalization of histology slides. In: Wang, F., Yan, P., Suzuki, K., Shen, D. (eds.) MLMI 2010. LNCS, vol. 6357, pp. 58–66. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-15948-0_8CrossRefGoogle Scholar
  4. 4.
    Khan, A., Rajpoot, N., Treanor, D., Magee, D.: A nonlinear mapping approach to stain normalization in digital histopathology images using image-specific color deconvolution. IEEE Trans. Biomed. Eng. 61(6), 1729–1738 (2014)CrossRefGoogle Scholar
  5. 5.
    Reinhard, E., Adhikhmin, M., Gooch, B., Shirley, P.: Color transfer between images. IEEE Comput. Graph. Appl. 21(5), 34–41 (2001)CrossRefGoogle Scholar
  6. 6.
    Macenko, M., et al.: A method for normalizing histology slides for quantitative analysis. In: Proceedings of IEEE International Symposium on Biomedical Imaging Nano Macro, pp. 1107–1110 (2009)Google Scholar
  7. 7.
    Vahadane, A., et al.: Structure-preserving color normalization and sparse stain separation for histological images. IEEE Trans. Med. Imaging 35(8), 1962–1971 (2016)CrossRefGoogle Scholar
  8. 8.
    Magee, D., et al.: Color normalization in digital histopathology images. In: Proceedings of Optical Tissue Image Analysis Microscopy, Histopathology Endoscopy, pp. 100–111 (2009)Google Scholar
  9. 9.
    Ajay Basavanhally, A.M.: Em-based segmentation-driven color standardization of digitized histopathology. Proc. SPIE 12, 8676–8676-12 (2013)Google Scholar
  10. 10.
    Ruifrok, A.C., Johnston, D.A.: Quantification of histochemical staining by color deconvolution. Analyt. Quant. Cytol. Histol. Int. Acad. Cytol. Am. Soc. Cytol. 23(4), 291–299 (2001)Google Scholar
  11. 11.
    Christopher, M.B.: Pattern Recognition and Machine learning. Springer, New York (2016)Google Scholar
  12. 12.
    Zong, B., et al.: Deep autoencoding gaussian mixture model for unsupervised anomaly detection. In: International Conference on Learning Representations (2018)Google Scholar
  13. 13.
    van den Oord, A., Schrauwen, B.: Factoring variations in natural images with deep gaussian mixture models. In: Advances in Neural Information Processing Systems, vol. 27, pp. 3518–3526. Curran Associates, Inc. (2014)Google Scholar
  14. 14.
    van der Laak, J.A., Pahlplatz, M.M., Hanselaar, A.G., de Wilde, P.C.: Hue-saturation-density (hsd) model for stain recognition in digital images from transmitted light microscopy. Cytometry 39(4), 275–284 (2000)CrossRefGoogle Scholar
  15. 15.
    Petersen, K.B., Pedersen, M.S.: The Matrix Cookbook. Technical University of Denmark, version 20121115, November 2012Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Farhad Ghazvinian Zanjani
    • 1
    Email author
  • Svitlana Zinger
    • 1
  • Peter H. N. de With
    • 1
  1. 1.Eindhoven University of TechnologyEindhovenThe Netherlands

Personalised recommendations