A Fast and Scalable Pipeline for Stain Normalization of Whole-Slide Images in Histopathology

  • Milos StanisavljevicEmail author
  • Andreea Anghel
  • Nikolaos Papandreou
  • Sonali Andani
  • Pushpak Pati
  • Jan Hendrik Rüschoff
  • Peter Wild
  • Maria Gabrani
  • Haralampos Pozidis
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11134)


Stain normalization is one of the main tasks in the processing pipeline of computer-aided diagnosis systems in modern digital pathology. Some of the challenges in this tasks are memory and runtime bottlenecks associated with large image datasets. In this work, we present a scalable and fast pipeline for stain normalization using a state-of-the-art unsupervised method based on stain-vector estimation. The proposed system supports single-node and distributed implementations. Based on a highly-optimized engine, our architecture enables high-speed and large-scale processing of high-magnification whole-slide images (WSI). We demonstrate the performance of the system using measurements from different datasets. Moreover, by using a novel pixel-sampling optimization we show lower processing time per image than the scanning time of ultrafast WSI scanners with the single-node implementation and additional 3.44 average speed-up with the 4-nodes distributed pipeline.


Histopathological image processing Whole-slide images Stain normalization Distributed computing Color deconvolution 


  1. 1.
    Alsubaie, N., Trahearn, N., Raza, S.E.A., Snead, D., Rajpoot, N.M.: Stain deconvolution using statistical analysis of multi-resolution stain colour representation. PloS One 12(1), e0169875 (2017). Scholar
  2. 2.
    Bejnordi, B.E., et al.: Stain specific standardization of whole-slide histopathological images. IEEE Trans. Med. Imaging 35(2), 404–415 (2016)CrossRefGoogle Scholar
  3. 3.
    Brown, M.B., Wolfe, R.A.: Estimation of the variance of percentile estimates. Comput. Stat. Data Anal. 1, 167–174 (1983)CrossRefGoogle Scholar
  4. 4.
    Fast approximate function of exponential function exp and log.
  5. 5.
    Harrison, R.L.: Introduction to Monte Carlo simulation. In: Granja, C., Leroy, C. (eds.) American Institute of Physics Conference Series. American Institute of Physics Conference Series, vol. 1204, pp. 17–21 (2010).
  6. 6.
    ISBI challenge on cancer metastasis detection in lymph node.
  7. 7.
    Janowczyk, A., Basavanhally, A., Madabhushi, A.: Stain normalization using sparse autoencoders (StaNoSA): application to digital pathology. Comput. Med. Imaging Graph. 57, 50–61 (2017)CrossRefGoogle Scholar
  8. 8.
    Khan, A.M., 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), 1729738 (2014)CrossRefGoogle Scholar
  9. 9.
    Li, X., Plataniotis, K.N.: A complete color normalization approach to histopathology images using color cues computed from saturation-weighted statistics. IEEE Trans. Biomed. Eng. 62(7), 1862–1873 (2015)CrossRefGoogle Scholar
  10. 10.
    Litjens, G., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)CrossRefGoogle Scholar
  11. 11.
    Macenko, M., et al.: A method for normalizing histology slides for quantitative analysis. In: 2009 IEEE International Symposium on Biomedical Imaging, pp. 1107–1110 (2009)Google Scholar
  12. 12.
    Open MPI: Open Source High Performance Computing.
  13. 13.
    OpenMP 4.0 Specifications.
  14. 14.
    OpenSlide is a C library that provides a simple interface to read whole-slide images.
  15. 15.
    Rabinovich, A., Agarwal, S., Laris, C., Price, J., Belongie, S.: Unsupervised color decomposition of histologically stained tissue samples. In: Advances in Neural Information Processing Systems, pp. 667–674 (2003)Google Scholar
  16. 16.
    Reinhard, E., Adhikhmin, M., Gooch, B., Shirley, P.: Color transfer between images. IEEE Comput. Graph. Appl. 21(5), 34–41 (2001). Scholar
  17. 17.
    Ruifrok, A.C., Johnston, D.A.: Quantification of histochemical staining by color deconvolution. Anal. Quant. Cytol. Histol. 23(4), 291–9 (2001)Google Scholar
  18. 18.
    Schoonjans, F., De Bacquer, D., Schmid, P.: Estimation of population percentiles (Cambridge, Mass.). Epidemiology 22(5), 750 (2011)CrossRefGoogle Scholar
  19. 19.
    Staining unmixing and normalization.
  20. 20.
    Tumor Proliferation Assessment Challenge 2016, TUPAC16 - MICCAI Grand Challenge.
  21. 21.
    Veta, M., Pluim, J.P.W., van Diest, P.J., Viergever, M.A.: Breast cancer histopathology image analysis: a review. IEEE Trans. Biomed. Eng. 61(5), 1400–1411 (2014)CrossRefGoogle Scholar
  22. 22.
    Vink, J.P., Leeuwen, M.B.V., Deurzen, C.H.M.V., Haan, G.D.: Efficient nucleus detector in histopathology images. J. Microsc. 249(2), 124–135 (2013)CrossRefGoogle Scholar
  23. 23.
    Wernick, M.N., Yang, Y., Brankov, J.G., Yourganov, G., Strother, S.C.: Machine learning in medical imaging. IEEE Sig. Process. Mag. 27(4), 25–38 (2010)CrossRefGoogle Scholar
  24. 24.
    Zerhouni, E., Lnyi, D., Viana, M., Gabrani, M.: Wide residual networks for mitosis detection. In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), pp. 924–928 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Milos Stanisavljevic
    • 1
    Email author
  • Andreea Anghel
    • 1
  • Nikolaos Papandreou
    • 1
  • Sonali Andani
    • 1
  • Pushpak Pati
    • 1
  • Jan Hendrik Rüschoff
    • 2
  • Peter Wild
    • 3
  • Maria Gabrani
    • 1
  • Haralampos Pozidis
    • 1
  1. 1.IBM Research – ZurichRüschlikonSwitzerland
  2. 2.Senckenberg Institute of Pathology, Universitätsklinikum FrankfurtFrankfurt am MainGermany
  3. 3.Institute of Pathology and Molecular Pathology, UniversitätsSpital ZürichZürichSwitzerland

Personalised recommendations