Transitioning Between Convolutional and Fully Connected Layers in Neural Networks

  • Shazia Akbar
  • Mohammad Peikari
  • Sherine Salama
  • Sharon Nofech-Mozes
  • Anne Martel
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10553)

Abstract

Digital pathology has advanced substantially over the last decade however tumor localization continues to be a challenging problem due to highly complex patterns and textures in the underlying tissue bed. The use of convolutional neural networks (CNNs) to analyze such complex images has been well adopted in digital pathology. However in recent years, the architecture of CNNs have altered with the introduction of inception modules which have shown great promise for classification tasks. In this paper, we propose a modified “transition” module which learns global average pooling layers from filters of varying sizes to encourage class-specific filters at multiple spatial resolutions. We demonstrate the performance of the transition module in AlexNet and ZFNet, for classifying breast tumors in two independent datasets of scanned histology sections, of which the transition module was superior.

Keywords

Convolutional neural networks Histology Transition Inception Breast tumor 

Notes

Acknowledgements

This work has been supported by grants from the Canadian Breast Cancer Foundation, Canadian Cancer Society (grant 703006) and the National Cancer Institute of the National Institutes of Health (grant number U24CA199374-01).

References

  1. 1.
    Lasagne. http://lasagne.readthedocs.io/en/latest/. Accessed 18 Feb 2017
  2. 2.
    Buyssens, P., Elmoataz, A., Lézoray, O.: Multiscale convolutional neural networks for vision–based classification of cells. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7725, pp. 342–352. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-37444-9_27 CrossRefGoogle Scholar
  3. 3.
    Jin, X., Chi, J., Peng, S., Tian, Y., Ye, C., Li, X.: Deep image aesthetics classification using inception modules and fine-tuning connected layer. In: 8th International Conference on Wireless Communications and Signal Processing (WCSP) (2016)Google Scholar
  4. 4.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105 (2012)Google Scholar
  5. 5.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  6. 6.
    Liao, Z., Carneiro, G.: Competitive multi-scale convolution. CoRR abs/1511.05635 (2015). http://arxiv.org/abs/1511.05635
  7. 7.
    Lin, M., Chen, Q., Yan, S.: Network in network. In: Proceedings of ICLR (2014)Google Scholar
  8. 8.
    Litjens, G., Sánchez, C.I., Timofeeva, N., Hermsen, M., Nagtegaal, I., Kovacs, I., Hulsbergen-van de Kaa, C., Bult, P., van Ginneken, B., van der Laak, J.: Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis. Sci. Rep. 6, 26286 (2016)CrossRefGoogle Scholar
  9. 9.
    Spanhol, F., Oliveira, L.S., Petitjean, C., Heutte, L.: Breast cancer histopathological image classification using convolutional neural network. In: International Joint Conference on Neural Networks, pp. 2560–2567Google Scholar
  10. 10.
    Spanhol, F.A., Oliveira, L.S., Petitjean, C., Heutte, L.: A dataset for breast cancer histopathological image classification. IEEE Trans. Biomed. Eng. 63, 1455–1462 (2016)CrossRefGoogle Scholar
  11. 11.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetMATHGoogle Scholar
  12. 12.
    Sutskever, I.: Training recurrent neural networks. Thesis (2013)Google Scholar
  13. 13.
    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, Inception-ResNet and the impact of residual connections on learning. arXiv preprint arXiv:1602.07261 (2016)
  14. 14.
    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Computer Vision and Pattern Recognition (CVPR) (2015)Google Scholar
  15. 15.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)Google Scholar
  16. 16.
    Vivanti, R., Ephrat, A., Joskowicz, L., Karaaslan, O.A., Lev-Cohain, N., Sosna, J.: Automatic liver tumor segmentation in follow up CT studies using convolutional neural networks. In: Proceedings of Patch-Based Methods in Medical Image Processing Workshop, MICCAIGoogle Scholar
  17. 17.
    Xu, Y., Li, Y., Wang, Y., Liu, M., Fan, Y., Lai, M., Chang, E.I.C.: Gland instance segmentation using deep multichannel neural networks. CoRR abs/1611.06661 (2016)Google Scholar
  18. 18.
    Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Computer Vision and Pattern Recognition (CVPR) (2013)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Shazia Akbar
    • 1
  • Mohammad Peikari
    • 1
  • Sherine Salama
    • 2
  • Sharon Nofech-Mozes
    • 2
  • Anne Martel
    • 1
  1. 1.Sunnybrook Research InstituteUniversity of TorontoTorontoCanada
  2. 2.Department of PathologySunnybrook Health Sciences CentreTorontoCanada

Personalised recommendations