Skip to main content
SpringerLink
Log in

Discriminative dictionary learning for retinal vessel segmentation using fusion of multiple features

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

In recent years, automated retinal vessel segmentation has become especially essential for the early detection of some ophthalmological and cardiovascular diseases. In this paper, we have presented a new retinal vessel segmentation method via discriminative dictionary learning using fusion of multiple features, which is able to capture both thick and thin vessel structures. In the training stage, we employ six different enhancement algorithms to obtain multiple complementary features that contain rich vascular information. Then, the manually annotated ground-truth vessels are classified into thick or thin vessels as the label information, and the label consistent KSVD based framework is applied to train the dictionary for vessel segmentation. In the testing stage, comprehensive experiments are conducted on three datasets to measure segmentation performance with eight representative evaluation metrics. The average sensitivity reaches 0.7915, 0.7560 and 0.7202 respectively, suggesting that our method can segment tiny vascular structures well.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Abràmoff, M.D., Garvin, M.K., Sonka, M.: Retinal imaging and image analysis. IEEE Rev. Biomed. Eng. 3, 169–208 (2010)

    Article  Google Scholar 

  2. Fraz, M.M., Remagnino, P., Hoppe, A., Uyyanonvara, B., Rudnicka, A.: Blood vessel segmentation methodologies in retinal images: a survey. Comput. Methods Prog. Biol. 108, 407–433 (2012)

    Article  Google Scholar 

  3. Annunziata, R., Garzelli, A., Ballerini, L.: Leveraging multiscale Hessian-based enhancement with a novel exudate inpainting technique for retinal vessel segmentation. IEEE J. Biomed. Health Inf. 20, 1129–1138 (2016)

    Article  Google Scholar 

  4. Yu, H., Barriga, S., Agurto, C., Zamora, G., Bauman, W., Soliz, P.: Fast vessel segmentation in retinal images using multiscale enhancement and second-order local entropy. Proc. SPIE 8315, 83151B-1–83151B-12 (2012)

    Article  Google Scholar 

  5. Azzopardi, G., Strisciuglio, N., Vento, M.: Trainable COSFIRE filters for vessel delineation with application to retinal images. Med. Image Anal. 19, 46–57 (2015)

    Article  Google Scholar 

  6. Zhao, Y., Zhao, J., Yang, J., Liu, Y.: Saliency driven vasculature segmentation with infinite perimeter active contour model. Neurocomputing 259, 201–209 (2017)

    Article  Google Scholar 

  7. Fraz, M.M., Basit, A., Barman, S.A.: Application of morphological bit planes in retinal blood vessel extraction. IET Image Process. 26, 373–383 (2013)

    Google Scholar 

  8. Zhao, Y., Zheng, Y., Liu, Y., Zhao, Y., Luo, L., Yang, S.: Automatic 2D/3D vessel enhancement in multiple modality images using a weighted symmetry filter. IEEE Trans. Med. Imaging 37, 438–450 (2018)

    Article  Google Scholar 

  9. Zhang, J., Dashtbozorg, B., Bekkers, E., Pluim, J.P.W., Duits, R.: Robust retinal vessel segmentation via locally adaptive derivative frames in orientation scores. IEEE Trans. Med. Imaging 35, 2631–2644 (2016)

    Article  Google Scholar 

  10. Soares, J., Leandro, J., Cesar, R., Jelinek, H.F., Cree, M.J.: Retinal vessel segmentation using the 2D Gabor wavelet and supervised classification. IEEE Trans. Med. Imaging 25, 1214–1222 (2006)

    Article  Google Scholar 

  11. Fraz, M.M., Remagnino, P., Hoppe, A., Uyyanonvara, B.: An ensemble classification-based approach applied to retinal blood vessel segmentation. IEEE Trans. Med. Imaging 59, 2538–2548 (2012)

    Google Scholar 

  12. Aslani, S., Sarnel, H.: A new supervised retinal vessel segmentation method based on robust hybrid features. Biomed. Signal Process. Control 30, 1–12 (2016)

    Article  Google Scholar 

  13. Roychowdhury, S., Koozekanani, D.D., Parhi, K.K.: Blood vessel segmentation of fundus images by major vessel extraction and subimage classification. IEEE J. Biomed. Health Inf. 19, 1118–1128 (2015)

    Google Scholar 

  14. Marin, D., Aquino, A., Gegundez-Arias, M.E., Bravo, J.M.: A new supervised method for blood vessel segmentation in retinal images by using gray-level and moment invariants-based features. IEEE Trans. Med. Imaging 30, 146–158 (2011)

    Article  Google Scholar 

  15. Orlando, J.I., Prokofyeva, E., Blaschko, M.B.: A discriminatively trained fully connected conditional random field model for blood vessel segmentation in fundus images. IEEE Trans. Med. Imaging 64, 16–27 (2017)

    Google Scholar 

  16. Li, Q., Feng, B., Xie, L., Liang, P.: A cross-modality learning approach for vessel segmentation in retinal images. IEEE Trans. Med. Imaging 35, 109–118 (2016)

    Article  Google Scholar 

  17. Fu, H., Xu, Y., Wong, D., Liu, J.: Deep vessel: retinal vessel segmentation via deep learning and conditional random field. Proc. MICCAI 9901, 132–139 (2016)

    Google Scholar 

  18. Yan, Z., Yang, X., Cheng, K.: Joint segment-level and pixel-wise losses for deep learning based retinal vessel segmentation. IEEE Trans. Med. Imaging 65, 1912–1923 (2018)

    Google Scholar 

  19. Shao, F., Yang, Y., Jiang, Q.: Automated quality assessment of fundus images via analysis of illumination, naturalness and structure. IEEE Access. 6, 806–817 (2018)

    Article  Google Scholar 

  20. Yang, Y., Shao, F., Fu, Z., Fu, R.: Blood vessel segmentation of fundus images via cross-modality dictionary learning. Appl. Opt. 57, 7287–7295 (2018)

    Article  Google Scholar 

  21. Guen, V.L.: Cartoon + texture image decomposition by the TV-L1 model. IPOL 4, 204–219 (2014)

    Article  Google Scholar 

  22. Frangi, A., Niessen, W., Vincken, K.: Multiscale vessel enhancement filtering. Med. Image Comput. Comput. Assist. Interv. 1496, 130–137 (1998)

    Google Scholar 

  23. Wang, L., Xiao, L., Liu, H., Wei, Z.: Variational Bayesian method for Retinex. IEEE Trans. Image Proces. 23, 3381–3396 (2014)

    Article  MathSciNet  Google Scholar 

  24. Zhou, M., Jin, K., Wang, S., Ye, J., Qian, D.: Color retinal image enhancement based on luminosity and contrast adjustment. IEEE Trans. Biomed. Eng. 65, 521–527 (2018)

    Article  Google Scholar 

  25. Jiang, Z., Lin, Z., Davis, L.: Label consistent K-SVD: learning a discriminative dictionary for recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35, 2651–2664 (2013)

    Article  Google Scholar 

  26. Odstrcilik, J., Kolar, R., Budai, A., Hornegger, J.: Retinal vessel segmentation by improved matched filtering: evaluation on a new high-resolution fundus image database. IET Image Process 7, 373–383 (2013)

    Article  MathSciNet  Google Scholar 

  27. Staal, J., Abramoff, M., Niemeijer, M., Viergever, M.: Ridge-based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging 23, 501–509 (2004)

    Article  Google Scholar 

  28. Hoover, A., Kouznetsova, V., Goldbaum, M.: Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans. Med. Imaging 19, 203–210 (2000)

    Article  Google Scholar 

  29. Fraz, M.M., Remagnino, P., Hoppe, A., Uyyanonvara, B.: Retinal vessel extraction using first-order derivative of Gaussian and morphological processing. Adv. Vis. Comput. 6938, 410–420 (2011)

    Google Scholar 

  30. Vega, R., Sanchez-Ante, G., Falcon-Morales, L.: Retinal vessel extraction using lattice neural networks with dendritic processing. Comput. Biol. Med. 58, 20–30 (2015)

    Article  Google Scholar 

  31. You, X., Peng, Q., Yuan, Y.: Segmentation of retinal blood vessels using radial projection and semi-supervised approach. Pattern Recogn. 44, 2314–2324 (2011)

    Article  Google Scholar 

  32. Al-Diri, B., Hunter, A., Steel, D.: An active contour model for segmenting and measuring retinal vessels. IEEE Trans. Med. Imaging 28, 1488–1497 (2009)

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the Natural Science Foundation of China (Grant 61622109), the Zhejiang Natural Science Foundation of China (Grant R18F010008), and the Natural Science Foundation of Ningbo (2017A610112). It was also sponsored by K.C. Wong Magna Fund in Ningbo University.

Author information

Authors and Affiliations

  1. Faculty of Information Science and Engineering, Ningbo University, Ningbo, China

    Yan Yang, Feng Shao, Zhenqi Fu & Randi Fu

Authors
  1. Yan Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Feng Shao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhenqi Fu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Randi Fu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Feng Shao.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, Y., Shao, F., Fu, Z. et al. Discriminative dictionary learning for retinal vessel segmentation using fusion of multiple features. SIViP 13, 1529–1537 (2019). https://doi.org/10.1007/s11760-019-01501-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-019-01501-9

Keywords

Search

Navigation