Convolutional Attention on Images for Locating Macular Edema

Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1065)


Neural networks have become a standard for classifying images. However, by their very nature, their internal data representation remains opaque. To solve this dilemma, attention mechanisms have recently been introduced. They help to highlight regions in input data that have been used for a network’s classification decision. This article presents two attention architectures for the classification of medical images. Firstly, we are explaining a simple architecture which creates one attention map that is used for all classes. Secondly, we introduce an architecture that creates an attention map for each class. This is done by creating two U-nets - one for attention and one for classification - and then multiplying these two maps together. We show that our architectures well meet the baseline of standard convolutional classifications while at the same time increasing their explainability.


Neural networks Convolutional neural networks Attention 


  1. 1.
    Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. CoRR abs/1409.0473 (2014).
  2. 2.
    Chan, W., Jaitly, N., Le, Q.V., Vinyals, O.: Listen, attend and spell. CoRR abs/1508.01211 (2015).
  3. 3.
    Chorowski, J., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. CoRR abs/1506.07503 (2015).
  4. 4.
    Ciresan, D.C., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. CoRR abs/1202.2745 (2012).
  5. 5.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/1512.03385 (2015).
  6. 6.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp. 1026–1034 (2015)Google Scholar
  7. 7.
    Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. CoRR abs/1502.03167 (2015).
  8. 8.
    Jin, Q., Meng, Z., Sun, C., Wei, L., Su, R.: Ra-unet: a hybrid deep attention-aware network to extract liver and tumor in CT scans. CoRR abs/1811.01328 (2018).
  9. 9.
    Kim, Y., Denton, C., Hoang, L., Rush, A.M.: Structured attention networks. CoRR abs/1702.00887 (2017).
  10. 10.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp. 1097–1105 (2012)Google Scholar
  11. 11.
    Lian, S., Luo, Z., Zhong, Z., Lin, X., Su, S., Li, S.: Attention guided U-net for accurate iris segmentation. J. Vis. Commun. Image Represent. 56, 296–304 (2018). Scholar
  12. 12.
    Luong, M., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. CoRR abs/1508.04025 (2015).
  13. 13.
    Oktay, O., et al.: Attention U-Net: Learning Where to Look for the Pancreas. arXiv e-prints arXiv:1804.03999 (Apr 2018)
  14. 14.
    Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. CoRR abs/1505.04597 (2015).
  15. 15.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014).
  16. 16.
    Vaswani, A., et al.: Attention is all you need. CoRR abs/1706.03762 (2017).
  17. 17.
    Wang, F., et al.: Residual attention network for image classification. CoRR abs/1704.06904 (2017).
  18. 18.
    Wang, L., Yin, B., Guo, A., Ma, H., Cao, J.: Skip-connection convolutional neural network for still image crowd counting. Appl. Intell. 48(10), 3360–3371 (2018). Scholar
  19. 19.
    Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. CoRR abs/1502.03044 (2015).
  20. 20.
    Yamashita, T., Yamashita, J., Furukawa, H., Yamauchi, Y.: Multiple skip connections and dilated convolutions for semantic segmentation (2017)Google Scholar
  21. 21.
    Zeiler, M.D., Fergus, R.: Visualizing and Understanding Convolutional Networks. ArXiv e-prints (Nov 2013).

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Universität LeipzigLeipzigGermany
  2. 2.Klinik und Poliklinik für Augenheilkunde, Universitätsklinikum LeipzigLeipzigGermany

Personalised recommendations