Advertisement

Deep Random Walk for Drusen Segmentation from Fundus Images

  • Fang Yan
  • Jia Cui
  • Yu Wang
  • Hong Liu
  • Hui Liu
  • Benzheng Wei
  • Yilong Yin
  • Yuanjie Zheng
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11071)

Abstract

This paper presents a deep random walk technique for drusen segmentation from fundus images. It is formulated as a deep learning architecture which learns deep representations from fundus images and specify an optimal pixel-pixel affinity. Specifically, the proposed architecture is mainly composed of three parts: a deep feature extraction module to learn both semantic-level and low-level representation of image, an affinity learning module to get pixel-pixel affinities for formulating the transition matrix of random walk and a random walk module which propagates manual labels. The power of our technique comes from the fact that the learning procedures for deep image representations and pixel-pixel affinities are driven by the random walk process. The accuracy of our proposed algorithm surpasses state-of-the-art drusen segmentation techniques as validated on the public STARE and DRIVE databases.

Keywords

Drusen segmentation Retinal fundus images Deep feature extraction Affinity learning Random walk 

Notes

Acknowledgements

This work was made possible through support from Natural Science Foundation of China (NSFC) (61572300) and Taishan Scholar Program of Shandong Province in China (TSHW201502038).

References

  1. 1.
    Brandon, L., Hoover, A.: Drusen detection in a retinal image using multi-level analysis. In: Ellis, R.E., Peters, T.M. (eds.) MICCAI 2003. LNCS, vol. 2878, pp. 618–625. Springer, Heidelberg (2003).  https://doi.org/10.1007/978-3-540-39899-8_76CrossRefGoogle Scholar
  2. 2.
    Sarks, S.H., Arnold, J.J., Killingsworth, M.C., Sarks, J.P.: Early drusen formation in the normal and aging eye and their relation to age related maculopathy: a clinicopathological study. Br. J. Ophthalmol. 83(3), 358–368 (1999)CrossRefGoogle Scholar
  3. 3.
    Ren, X., et al.: Drusen segmentation from retinal images via supervised feature learning. IEEE Access PP(99), 1 (2017)Google Scholar
  4. 4.
    Schlanitz, F.G., et al.: Performance of drusen detection by spectral-domain optical coherence tomography. Investig. Ophthalmol. Vis. Sci. 51(12), 6715 (2010)CrossRefGoogle Scholar
  5. 5.
    Zheng, Y., Wang, H., Wu, J., Gao, J.: Multiscale analysis revisited: detection of drusen and vessel in digital retinal images. In: IEEE International Symposium on Biomedical Imaging: From Nano To Macro, pp. 689–692 (2011)Google Scholar
  6. 6.
    Zheng, Y., Vanderbeek, B., Daniel, E., Stambolian, D.: An automated drusen detection system for classifying age-related macular degeneration with color fundus photographs. In: IEEE International Symposium on Biomedical Imaging, pp. 1448–1451 (2013)Google Scholar
  7. 7.
    Barriga, E.S., et al.: Multi-scale am-fm for lesion phenotyping on age-related macular degeneration. In: IEEE International Symposium on Computer-Based Medical Systems, pp. 1–5 (2009)Google Scholar
  8. 8.
    Shin, D.S., Javornik, N.B., Berger, J.W.: Computer-assisted, interactive fundus image processing for macular drusen quantitation. Ophthalmology 106(6), 1119–25 (1999)CrossRefGoogle Scholar
  9. 9.
    Smith, R.T.: Automated detection of macular drusen using geometric background leveling and threshold selection. Arch. Ophthalmol. 123(2), 200–206 (2005)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Shotton, J., et al.: Real-time human pose recognition in parts from single depth images. Commun. ACM 56(1), 1297–1304 (2011)Google Scholar
  11. 11.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)Google Scholar
  12. 12.
    Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: A deep convolutional encoder-decoder architecture for scene segmentation. IEEE Trans. Pattern Anal. Mach. Intell. PP(99), 1 (2017)Google Scholar
  13. 13.
    Lin, G., Milan, A., Shen, C., Reid, I.D.: Refinenet: multi-path refinement networks for high-resolution semantic segmentation. In: CVPR, vol. 1, no. 2, 5 p. (2017)Google Scholar
  14. 14.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Comput. Sci. arXiv preprint arXiv:1409.1556 (2014)
  15. 15.
    Xu, N., Price, B., Cohen, S., Huang, T.: Deep image matting. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 311–320 (2017)Google Scholar
  16. 16.
    Bertasius, G., Torresani, L., Yu, S.X., Shi, J.: Convolutional random walk networks for semantic image segmentation, pp. 6137–6145 (2016)Google Scholar
  17. 17.
    Rapantzikos, K., Zervakis, M., Balas, K.: Detection and segmentation of drusen deposits on human retina: potential in the diagnosis of age-related macular degeneration. Med. Image Anal. 7(1), 95–108 (2003)CrossRefGoogle Scholar
  18. 18.
    Liu, H., Xu, Y., Wong, D.W.K., Liu, J.: Effective drusen segmentation from fundus images for age-related macular degeneration screening. In: Asian Conference on Computer Vision, pp. 483–498 (2014)Google Scholar
  19. 19.
    Briggs, D.A.H.: Handling uncertainty in cost-effectiveness models. Pharmacoeconomics 17(5), 479 (2000)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Fang Yan
    • 1
  • Jia Cui
    • 1
  • Yu Wang
    • 1
  • Hong Liu
    • 1
    • 2
  • Hui Liu
    • 3
  • Benzheng Wei
    • 4
  • Yilong Yin
    • 5
  • Yuanjie Zheng
    • 1
    • 2
    • 6
    • 7
  1. 1.School of Information Science and EngineeringShandong Normal UniversityJinanChina
  2. 2.Shandong Provincial Key Lab for Distributed Computer Software Novel TechnologyJinanChina
  3. 3.Department of Biomedical EngineerDalian University of TechnologyDalianChina
  4. 4.College of Science and TechnologyShandong University of Traditional Chinese MedicineJinanChina
  5. 5.School of Computer Science and TechnologyShandong UniversityJinanChina
  6. 6.Institute of Biomedical SciencesShandong Normal UniversityJinanChina
  7. 7.Key Lab of Intelligent Computing and Information Security in Universities of ShandongJinanChina

Personalised recommendations