Stain Colour Normalisation to Improve Mitosis Detection on Breast Histology Images

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10553)


The mitosis count, one of the main components considered for grading breast cancer on histology images, is used to assess tumour proliferation. On breast histology sections, different coloured stains are used to highlight existing cellular components. To keep the wealth of information in the stain colour representation and decrease the sensitivity of detection and classification models to stain variations, the RGB Histogram Specification method is used as a preprocessing step in the training of a modified deep convolutional neural network. Different models are trained on raw and stain normalised images using different databases. Evaluation results show more stable detection performance for various imaging conditions. Combining different data sources and employing stain colour normalisation and transfer learning, a network is trained that can be used for the general mitosis detection task and dealing with staining and scanner variations.


  1. 1.
    Albarqouni, S., Baur, C., Achilles, F., Belagiannis, V., Demirci, S., Navab, N.: AggNet: deep learning from crowds for mitosis detection in breast cancer histology images. IEEE Trans. Med. Imaging 35(5), 1313–1321 (2016)CrossRefGoogle Scholar
  2. 2.
    Assessment of Mitosis Detection Algorithms (AMIDA13), MICCAI Grand Challenge (2013).
  3. 3.
    Bloom, H.J.G., Richardson, W.W.: Histological grading and prognosis in breast cancer: a study of 1409 cases of which 359 have been followed for 15 years. Br. J. Cancer. 11(3), 359–377 (1957)CrossRefGoogle Scholar
  4. 4.
    Chang, H., Loss, L.A., Parvin, B.: Nuclear segmentation in H&E sections via multi-reference graph cut (MRGC). In: International Symposium Biomedical Imaging (2012)Google Scholar
  5. 5.
    Chen, H., Dou, Q., Wang, X., Qin, J., Heng, P.-A.: Mitosis detection in breast cancer histology images via deep cascaded networks. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pp. 1160–1166 (2016)Google Scholar
  6. 6.
    Cireşan, D.C., Giusti, A., Gambardella, L.M., Schmidhuber, J.: Mitosis detection in breast cancer histology images with deep neural networks. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8150, pp. 411–418. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-40763-5_51 CrossRefGoogle Scholar
  7. 7.
    Detection of mitosis and evaluation of nuclear atypia score in Breast Cancer Histological Images. In: International Conference for Pattern Recognition (ICPR) (2014).
  8. 8.
    Jain, A.K.: Fundamentals of digital image processing. Prentice-Hall Inc., Upper Saddle River (1989)MATHGoogle Scholar
  9. 9.
    Janowczyk, A., Madabhushi, A.: Deep learning for digital pathology image analysis: a comprehensive tutorial with selected use cases. J. Pathol. Inf. 7 (2016)Google Scholar
  10. 10.
    Stewart, B.W.K.P., Christopher P.W.: International Agency for Research on Cancer, WHO: World Cancer Report (2014)Google Scholar
  11. 11.
    Tajbakhsh, N., Shin, J.Y., Gurudu, S.R., Hurst, R.T., Kendall, C.B., Gotway, M.B., Liang, J.: Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans. Med. Imaging 35(5), 1299–1312 (2016)CrossRefGoogle Scholar
  12. 12.
    Veta, M., Pluim, J.P., 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
  13. 13.
    Wang, H., Cruz-Roa, A., Basavanhally, A., Gilmore, H., Shih, N., Feldman, M., Tomaszewski, J., Gonzalez, F., Madabhushi, A.: Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection. In: SPIE Medical Imaging, p. 90410B (2014). doi: 10.1117/12.2043902

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Department of Computer ScienceAberystwyth UniversityAberystwythUK

Personalised recommendations