Semi-supervised Segmentation of Optic Cup in Retinal Fundus Images Using Variational Autoencoder

  • Suman SedaiEmail author
  • Dwarikanath Mahapatra
  • Sajini Hewavitharanage
  • Stefan Maetschke
  • Rahil Garnavi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10434)


Accurate segmentation of optic cup and disc in retinal fundus images is essential to compute the cup to disc ratio parameter, which is important for glaucoma assessment. The ill-defined boundaries of optic cup makes the segmentation a lot more challenging compared to optic disc. Existing approaches have mainly used fully supervised learning that requires many labeled samples to build a robust segmentation framework. In this paper, we propose a novel semi-supervised method to segment the optic cup, which can accurately localize the anatomy using limited number of labeled samples. The proposed method leverages the inherent feature similarity from a large number of unlabeled images to train the segmentation model from a smaller number of labeled images. It first learns the parameters of a generative model from unlabeled images using variational autoencoder. The trained generative model provides the feature embedding of the images which allows the clustering of the related observation in the latent feature space. We combine the feature embedding with the segmentation autoencoder which is trained on the labeled images for pixel-wise segmentation of the cup region. The main novelty of the proposed approach is in the utilization of generative models for semi-supervised segmentation. Experimental results show that the proposed method successfully segments optic cup with small number of labeled images, and unsupervised feature embedding learned from unlabeled data improves the segmentation accuracy. Given the challenge of access to annotated medical images in every clinical application, the proposed framework is a key contribution and applicable for segmentation of different anatomies across various medical imaging modalities.


Semisupervised learning Variational inference Optic cup segmentation 


  1. 1.
    Chakravarty, A., Sivaswamy, J.: Coupled sparse dictionary for depth-based cup segmentation from single color fundus image. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8673, pp. 747–754. Springer, Cham (2014). doi: 10.1007/978-3-319-10404-1_93CrossRefGoogle Scholar
  2. 2.
    Joshi, G.D., Sivaswamy, J., Krishnadas, S.R.: Depth discontinuity-based cup segmentation from multiview color retinal images. IEEE Trans. Biomed. Eng. 59(6), 1523–1531 (2012)CrossRefGoogle Scholar
  3. 3.
    Sønderby, C.K., Raiko, T., Maaløe, L., Sønderby, S.K., Winther, O.: Ladder variational autoencoders. arXiv e-prints, February 2016Google Scholar
  4. 4.
    Kingma, D.P., Rezende, D.J., Mohamed, S., Welling, M.: Semi-supervised learning with deep generative models. arXiv e-prints, June 2014Google Scholar
  5. 5.
    Kingma, D.P., Welling, M.: Auto-encoding variational Bayes (2013). CoRR, abs/1312.6114Google Scholar
  6. 6.
    Liu, J., Wong, D.W.K., Lim, J.H., Li, H., Tan, N.M., Zhang, Z., Wong, T.Y., Lavanya, R.: ARGALI: an automatic cup-to-disc ratio measurement system for glaucoma analysis using level-set image processing. In: Lim, C.T., Goh, J.C.H. (eds.) 13th International Conference on Biomedical Engineering. IFMBE Proceedings, vol. 23, pp. 559–562. Springer, Heidelberg (2009). doi: 10.1007/978-3-540-92841-6_137CrossRefGoogle Scholar
  7. 7.
    Liu, Y., Xing, Z., Deng, C., Li, P., Guo, M.: Automatically detecting lung nodules based on shape descriptor and semi-supervised learning. In: 2010 International Conference on Computer Application and System Modeling (ICCASM 2010), vol. 1, pp. V1-647–V1-650, October 2010Google Scholar
  8. 8.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on CVPR, pp. 3431–3440 (2015)Google Scholar
  9. 9.
    Maaløe, L., Sønderby, C.K., Sønderby, S.K., Winther, O.: Auxiliary deep generative models. arXiv e-prints, February 2016Google Scholar
  10. 10.
    Maninis, K.-K., Pont-Tuset, J., Arbeláez, P., Van Gool, L.: Deep retinal image understanding. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 140–148. Springer, Cham (2016). doi: 10.1007/978-3-319-46723-8_17CrossRefGoogle Scholar
  11. 11.
    Portela, N.M., Cavalcanti, G.D.C., Ren, T.I.: Semi-supervised clustering for MR brain image segmentation. Expert Syst. Appl. 41(4), 1492–1497 (2014)CrossRefGoogle Scholar
  12. 12.
    Quigley, H.A., Broman, A.T.: The number of people with glaucoma worldwide in 2010 and 2020. Br. J. Ophthalmol. 90(3), 262–267 (2006)CrossRefGoogle Scholar
  13. 13.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation (2015). CoRR, abs/1505.04597Google Scholar
  14. 14.
    Sedai, S., Roy, P., Mahapatra, D., Garnavi, R.: Segmentation of optic disc and optic cup in retinal fundus images using coupled shape regression. In: Proceedings of the OMIA Workshop, pp. 1–8 (2016)Google Scholar
  15. 15.
    Xu, Y., Duan, L., Lin, S., Chen, X., Wong, D.W.K., Wong, T.Y., Liu, J.: Optic cup segmentation for glaucoma detection using low-rank superpixel representation. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8673, pp. 788–795. Springer, Cham (2014). doi: 10.1007/978-3-319-10404-1_98CrossRefGoogle Scholar
  16. 16.
    You, X., Peng, Q., Yuan, Y., Cheung, Y., Lei, J.: Segmentation of retinal blood vessels using the radial projection and semi-supervised approach. Pattern Recogn. 44(10–11), 2314–2324 (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Suman Sedai
    • 1
    Email author
  • Dwarikanath Mahapatra
    • 1
  • Sajini Hewavitharanage
    • 1
  • Stefan Maetschke
    • 1
  • Rahil Garnavi
    • 1
  1. 1.IBM ResearchMelbourneAustralia

Personalised recommendations