Skip to main content

Advertisement

SpringerLink
Log in

Construction and verification of color fundus image retinal vessels segmentation algorithm under BP neural network

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

For the purpose of analyzing the application of back propagation (BP) neural network model in retinal vascular segmentation of color fundus images, in this study, the traditional BP neural network was first improved by adopting the additional momentum method. Second, adaptive histogram, morphological background subtraction, Gauss preprocessing matching filter and Heisen matrix were used to enhance the image and extract the features. Third, the retinal vascular segmentation algorithm for color fundus images was constructed based on optimized BP neural network. Finally, the DRIVE and MESSIDOR data sets of color fundus images were introduced to compare the proposed algorithm with the convolutional neural network (CNN) and pulse-coupled neural network (PCNN) algorithms in terms of performance. In addition, the three algorithms were also compared in terms of the sensitivity (Se), specificity (Sp), accuracy (Ac), average operation time for each image and F1 value. The results show that the BP neural network algorithm proposed in this study shows obvious advantage over the other two algorithms in the segmentation of color fundus images. In the DRIVE data set, the Se (81.37%), Sp (90.55%) and Ac (95.82%) of BP algorithm are the highest among the three; in the MESSIDOR data set, the Se (85.22%), Sp (91.08%) and Ac (96.16%) of BP algorithm are also highest; in the DRIVE and MESSIDOR data sets, the operation time of BP algorithm is (28.46 ± 3.19 ms; 24.73 ± 4.81 ms, respectively), which are significantly less than the other two algorithms. Besides, the F1 value of the proposed algorithm is obviously higher than that the other two algorithms. As a result, it is concluded that compared with the CNN algorithm and the PCNN algorithm, the proposed algorithm is more effective in the retinal vascular segmentation of color fundus images; the capillaries have better connectivity, and the proposed algorithm can improve the segmentation Ac while reducing the operation time.

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. Xiao Z, Zhang X, Geng L et al (2019) Research on the method of color fundus image optic cup segmentation based on deep learning. Symmetry 11(7):933

    Article  Google Scholar 

  2. Nikkhah H, Karimi S, Ahmadieh H et al (2018) Intravitreal Injection of Anti-vascular Endothelial Growth Factor Agents for Ocular Vascular Diseases: Clinical Practice Guideline. J Ophthal Vis Res 13(2):158–169

    Article  Google Scholar 

  3. Geetha R, Sugirtharani S, Lakshmi B (2017) Automatic detection of glaucoma in retinal fundus images through image processing and data mining techniques. Int J Comput Appl 166(8):38–43

    Google Scholar 

  4. Sawides L, Adrián GR, Castro AD et al (2018) High-speed visual stimuli generator to estimate the minimum presentation time required for an orientation discrimination task. Biomed Opt Expr 9(6):2640

    Article  Google Scholar 

  5. Xu K, Feng D, Mi H (2017) Deep CNN-based early automated detection of diabetic retinopathy using fundus image. Molecules 22(12):2054

    Article  Google Scholar 

  6. Memari N, Ramli AR, Saripan MIB et al (2017) Supervised retinal vessel segmentation from color fundus images based on matched filtering and AdaBoost classifier. PLoS ONE 12(12):e0188939

    Article  Google Scholar 

  7. Xie LY, Chen C, Kong WJ et al (2019) A comparative study on retinal thickness of the macular region among AIDS patients with normal ocular fundus, HIV-related microvascular retinopathy patients and cytomegalovirus retinitis patients. Medicine 98(26):e16073

    Article  Google Scholar 

  8. Qureshi I, Ma J, Shaheed K (2019) A hybrid proposed fundus image enhancement framework for diabetic retinopathy. Algorithms 12(1):14

    Article  Google Scholar 

  9. Guo Y, Budak Ü, Şengür A et al (2017) A retinal vessel detection approach based on shearlet transform and indeterminacy filtering on fundus images. Symmetry 9(10):235

    Article  Google Scholar 

  10. Cardoso CRL, Leite NC, Dib E et al (2017) Predictors of development and progression of retinopathy in patients with type 2 diabetes: importance of blood pressure parameters. Sci Rep 7(1):1–10

    Article  Google Scholar 

  11. Peragallo JH, Keller S, van der Knaap MS et al (2018) Retinopathy and optic atrophy: expanding the phenotypic spectrum of pathogenic variants in the AARS2 gene. Ophthal genet 39(1):99–102

    Article  Google Scholar 

  12. Pan CW, Wang S, Xu CL et al (2018) Combined effect of glycemic and blood pressure control on diabetic retinopathy among Chinese with type-2 diabetes mellitus. Diabetol Metab Syndr 10(1):73

    Article  Google Scholar 

  13. Bek T, Jørgensen CM (2016) The systemic blood pressure and oxygen saturation in retinal arterioles predict the effect of intravitreal anti-VEGF treatment on diabetic maculopathy. Investig Ophthalmol Vis Sci 57(13):5429–5434

    Article  Google Scholar 

  14. Triwijoyo BK, Budiharto W, Abdurachman E (2017) The Classification of Hypertensive Retinopathy using CNN. Proc Comput Sci 116:166–173

    Article  Google Scholar 

  15. Gerrits N, Elen B, Van Craenendonck T et al (2020) Age and sex affect deep learning prediction of cardiometabolic risk factors from retinal images. Sci Rep 10(1):1–9

    Article  Google Scholar 

  16. Shanthi T, Sabeenian RS (2019) Modified Alexnet architecture for classification of diabetic retinopathy images. Comput Electr Eng 76:56–64

    Article  Google Scholar 

  17. Bengi EK (2019) Neutrophil-to-lymphocyte ratio in ocular diseases: a systematic review. Int J Ophthalmol 12(12):1951–1958

    Article  Google Scholar 

  18. Jensen PS, Aalkjaer C, Bek T (2017) Differential effects of nitric oxide and cyclo-oxygenase inhibition on the diameter of porcine retinal vessels with different caliber during hypoxia ex vivo. Exp Eye Res 160:38–44

    Article  Google Scholar 

  19. Feldman TB, Yakovleva MA, Larichev AV et al (2018) Spectral analysis of fundus autofluorescence pattern as a tool to detect early stages of degeneration in the retina and retinal pigment epithelium. Eye 32(9):1440–1448

    Article  Google Scholar 

  20. Nicholson L, Sivapathasuntharam C, Zola M et al (2017) Retinal Oximetry Differences Between Optic Disc Collateral Vessels and New Vessels. Jama ophthalmol 135(9):1003–1004

    Article  Google Scholar 

  21. Gohar M, Anwar S, Ali M et al (2020) Partial bicasting with buffering for proxy mobile IPV6 mobility management in CoAP-based IoT networks. Electronics 9(4):598

    Article  Google Scholar 

  22. Srinidhi CL, Aparna P, Rajan J (2018) A visual attention guided unsupervised feature learning for robust vessel delineation in retinal images. Biomed Signal Process Control 44:110–126

    Article  Google Scholar 

  23. Zapata MA, Royo-Fibla D, Font O et al (2020) Artificial intelligence to identify retinal fundus images, quality validation, laterality evaluation, macular degeneration and suspected glaucoma. Clin Ophthalmol (Auckland, NZ) 14:419

    Article  Google Scholar 

  24. Pal S, Chatterjee S, Dey D et al (2019) Morphological operations with iterative rotation of structuring elements for segmentation of retinal vessel structures. Multidimen Syst Signal Process 30(1):373–389

    Article  Google Scholar 

  25. Mohammed MA, Abd Ghani MK, Arunkumar N et al (2020) Decision support system for nasopharyngeal carcinoma discrimination from endoscopic images using artificial neural network. J Supercomput 76(2):1086–1104

    Article  Google Scholar 

  26. Khorsand R, Safi-Esfahani F, Nematbakhsh N et al (2017) ATSDS: adaptive two-stage deadline-constrained workflow scheduling considering run-time circumstances in cloud computing environments. J Supercomput 73(6):2430–2455

    Article  Google Scholar 

  27. Liu TYA, Johnson TV, Barnett BP et al (2018) Evolution of leukemic retinal hemorrhages documented by spectral-domain oct and color fundus photography. Ophthalmol Retina 2(5):494–501

    Article  Google Scholar 

  28. Maria F, Daniel R, Valentina DI et al (2018) Automatic segmentation of pigment deposits in retinal fundus images of Retinitis Pigmentosa. Comput Med Imaging Gr: Off J Comput Med Imaging Soc 66:73–81

    Article  Google Scholar 

  29. Jiang F, Bharanitharan K, Barma S et al (2015) Game theory based no-reference perceptual quality assessment for stereoscopic images. J Supercomput 71(9):3337–3352

    Article  Google Scholar 

  30. Wang KH, Chen CM, Fang W et al (2018) On the security of a new ultra-lightweight authentication protocol in IoT environment for RFID tags. J Supercomput 74(1):65–70

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Xidian University, Xi’an, 710000, China

    Zhao Liu

Authors
  1. Zhao Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhao Liu.

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

Liu, Z. Construction and verification of color fundus image retinal vessels segmentation algorithm under BP neural network. J Supercomput 77, 7171–7183 (2021). https://doi.org/10.1007/s11227-020-03551-0

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-020-03551-0

Keywords

Search

Navigation