ASDNet: Attention Based Semi-supervised Deep Networks for Medical Image Segmentation

  • Dong Nie
  • Yaozong Gao
  • Li Wang
  • Dinggang ShenEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11073)


Segmentation is a key step for various medical image analysis tasks. Recently, deep neural networks could provide promising solutions for automatic image segmentation. The network training usually involves a large scale of training data with corresponding ground truth label maps. However, it is very challenging to obtain the ground-truth label maps due to the requirement of expertise knowledge and also intensive labor work. To address such challenges, we propose a novel semi-supervised deep learning framework, called “Attention based Semi-supervised Deep Networks” (ASDNet), to fulfill the segmentation tasks in an end-to-end fashion. Specifically, we propose a fully convolutional confidence network to adversarially train the segmentation network. Based on the confidence map from the confidence network, we then propose a region-attention based semi-supervised learning strategy to include the unlabeled data for training. Besides, sample attention mechanism is also explored to improve the network training. Experimental results on real clinical datasets show that our ASDNet can achieve state-of-the-art segmentation accuracy. Further analysis also indicates that our proposed network components contribute most to the improvement of performance.


  1. 1.
    Bai, W., et al.: Semi-supervised learning for network-based cardiac MR image segmentation. In: Descoteaux, M., et al. (eds.) MICCAI 2017. LNCS, vol. 10434, pp. 253–260. Springer, Cham (2017). Scholar
  2. 2.
    Baur, C., Albarqouni, S., Navab, N.: Semi-supervised deep learning for fully convolutional networks. In: Descoteaux, M. (ed.) MICCAI 2017. LNCS, vol. 10435, pp. 311–319. Springer, Cham (2017). Scholar
  3. 3.
    Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)Google Scholar
  4. 4.
    Guo, Y., et al.: Deformable MR prostate segmentation via deep feature learning and sparse patch matching. IEEE TMI 35, 1077–1089 (2016)Google Scholar
  5. 5.
    Hung, W.-C., et al.: Adversarial learning for semi-supervised semantic segmentation. arXiv preprint arXiv:1802.07934 (2018)
  6. 6.
    Lin, T.-Y., et al.: Focal loss for dense object detection. arXiv preprint arXiv:1708.02002 (2017)
  7. 7.
    Litjens, G.: Evaluation of prostate segmentation algorithms for MRI: the PROMISE12 challenge. MedIA 18(2), 359–373 (2014)Google Scholar
  8. 8.
    Long, J., et al.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440 (2015)Google Scholar
  9. 9.
    Milletari, F., et al.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 3DV, pp. 565–571. IEEE (2016)Google Scholar
  10. 10.
    Nie, D., et al.: Medical image synthesis with context-aware generative adversarial networks. In: Descoteaux, M., et al. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 417–425. Springer, Cham (2017). Scholar
  11. 11.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). Scholar
  12. 12.
    Sudre, C.H., et al.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. DLMIA/ML-CDS -2017. LNCS, vol. 10553, pp. 240–248. Springer, Cham (2017). Scholar
  13. 13.
    Yu, L., et al.: Volumetric ConvNets with mixed residual connections for automated prostate segmentation from 3D MR images. In: AAAI (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Dong Nie
    • 1
    • 2
  • Yaozong Gao
    • 3
  • Li Wang
    • 2
  • Dinggang Shen
    • 2
    Email author
  1. 1.Department of Computer ScienceUniversity of North Carolina at Chapel HillChapel HillUSA
  2. 2.Department of Radiology and BRICUniversity of North Carolina at Chapel HillChapel HillUSA
  3. 3.Shanghai United Imaging Intelligence Co., Ltd.ShanghaiChina

Personalised recommendations