Retinal image registration from artery–venous subtree by graph theoretical characterization of retinal vascular network

Abstract

There are many approaches exist in literature to register retinal images from their RGB fundus stages. Previous approaches need to take special care upon transformations like rotation and translation. In this paper, an image registration method has been proposed which is robust against transformation and does not need extra burden to handle it. In particular, our proposed approach consists of three major stages. At the first stage, vascular network has been segregated into many other coloured sub-categories on the segmented fundus image. The second stage is to find out arterial and venous segments among the coloured sub-categories of the network by following the proposed artery-vein (A/V) classification method. Finally, each arterial and venous segments are combined together to form arterial and venous subtrees which resembles a binary tree. Finding inorder traversal of each such subtrees complete the process for image registration. We evaluate the approach with ground truth images of a public database called RITE. The work shows an arterial-venous classification rate as \(89\%\) using an automated vessel segmented image as input which is comparable with other existing methods.

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

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

References

  1. 1.

    Can A, Stewart CV, Roysam B, Tanenbaum HL (2002) A feature-based, robust, hierarchical algorithm for registering pairs of images of the curved human retina. IEEE Trans Pattern Anal Mach Intell 24(3):347364

    Google Scholar 

  2. 2.

    Dashtbozorg B, Maria Mendona A, Campilho A (2014) An automatic graph-based approach for artery/vein classification in retinal images. IEEE Trans Image Process 23(3):1073–1083

    MathSciNet  Article  Google Scholar 

  3. 3.

    Deng K, Tian J, Zheng J, Zhang X, Dai X, Xu M (2010) Retinal fundus image registration via vascular structure graph matching. Int J Biomed Imaging 13(3):14

    Google Scholar 

  4. 4.

    Dutta Roy N, Biswas A (2015) Detection of bifurcation angles in retinal fundus images. In: Proceedings of ICAPR 2015, IEEE Xplore Digital Library

  5. 5.

    Dutta Roy N., Biswas A (2018) Finding center of optic disc from fundus images for image characterization and analysis. In: Proceedings of ISMAC-CVB. Springer’s lecture notes in computational vision and biomechanics

  6. 6.

    Dutta Roy N, Goswami S, Goswami S, De S, Biswas A (2016) Extraction of distinct bifurcation points from retinal fundus images. In: Proceedings of ICIC2 2016. Springer’s AISC series

    Google Scholar 

  7. 7.

    Dutta Roy N, Someswar M, Dalmia H, Biswas A (2014) Identification of distinct blood vessels in retinal fundus images. In: Proceedings of compIMAGE 2014. Springer’s lecture notes in computer science, vol 8641, pp 106–114

    Google Scholar 

  8. 8.

    Estrada R, Allingham M, Mettu PS, Cousins Scott W, Tomasi C, Farsiu S (2015) Retinal artery–vein classification via topology estimation. IEEE Trans Med Imaging 34(12):2518–2534

    Article  Google Scholar 

  9. 9.

    Guo Z, Hall RW (1989) Parallel thinning with two-sub iteration algorithms. Commun ACM 2(3):359373

    Google Scholar 

  10. 10.

    Hu Q, Abramoff MD, Garvin MK (2015) Automated construction of arterial and venous trees in retinal images. J Med Imaging 2(4):044001044001

    Article  Google Scholar 

  11. 11.

    Hu Q, Garvin MK, Abrmoff MD (2015) Rite dataset. http://www.medicine.uiowa.edu/eye/RITE/. Accessed Aug 2015

  12. 12.

    Joshi VS, Reinhardt JM, Garvin MK, Abramoff MD (2014) Automated method for identification and artery–venous classification of vessel trees in retinal vessel networks. PLoS ONE 9(2):e88061

    Article  Google Scholar 

  13. 13.

    Niemeijer M, van Ginneken B, Abrmoff MD (2010) Automatic determination of the artery vein ratio in retinal images. Proc SPIE 7624:76240I

    Article  Google Scholar 

  14. 14.

    Oinonen H, Forsvik H, Ruusuvuori P, Yli-Harja O, Voipio V, Huttunen H (2010) Identity verification based on vessel matching from fundus images. In: Proceedings of international conference on image processing, pp 4089–4092

  15. 15.

    Parekar J, Porwal P, Kokare M (2016) Automatic retinal image registration using fully connected vascular tree. In: Proceedings of signal and information processing (IConSIP 2016), IEEE Xplore Digital Library

  16. 16.

    Rothaus K, Jiang X, Rhiem P (2009) Separation of the retinal vascular graph in arteries and veins based upon structural knowledge. Image Vis Comput 27(7):864875

    Article  Google Scholar 

  17. 17.

    The drive database. Image sciences institute, university medical center Utrecht, The Netherlands. https://www.isi.uu.nl/Research/Databases/DRIVE/index.html. Accessed July 2007

  18. 18.

    Welikala RA, Foster P, Whincup PH, Owen CG, Strachan DP, Barman SA (2017) Automated arteriole and venule classification using deep learning for retinal images from the uk biobank cohort. Comput Biol Med 90:2332

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Nilanjana Dutta Roy.

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

Verify currency and authenticity via CrossMark

Cite this article

Dutta Roy, N., Biswas, A. Retinal image registration from artery–venous subtree by graph theoretical characterization of retinal vascular network. Innovations Syst Softw Eng 16, 79–86 (2020). https://doi.org/10.1007/s11334-019-00335-5

Download citation

Keywords

  • Artery-venous subtree
  • Inorder traversal of binary tree
  • Retinal vascular network
  • Digital template
  • Image registration and verification