Abstract
To improve the accuracy of retinal vessel segmentation, a retinal vessel segmentation algorithm for color fundus images based on back-propagation (BP) neural network is proposed according to the characteristics of retinal blood vessels. Four kinds of green channel image enhancement results of adaptive histogram equalization, morphological processing, Gaussian matched filtering, and Hessian matrix filtering are used to form feature vectors. The BP neural network is input to segment blood vessels. Experiments on the color fundus image libraries DRIVE and STARE show that this algorithm can obtain complete retinal blood vessel segmentation as well as connected vessel stems and terminals. When segmenting most small blood vessels, the average accuracy on the DRIVE library reaches 0.9477, and the average accuracy on the STARE library reaches 0.9498, which has a good segmentation effect. Through verification, the algorithm is feasible and effective for blood vessel segmentation of color fundus images and can detect more capillaries.
Similar content being viewed by others
References
Schmidt TG, Linderman RE, Strampe MR et al (2019) The utility of frame averaging for automated algorithms in analyzing retinal vascular biomarkers in AngioVue OCTA. Transl Vis Sci Technol 8(1):10–10
Khan MAU, Khan TM, Soomro TA et al (2019) Boosting sensitivity of a retinal vessel segmentation algorithm. Pattern Anal Appl 22(2):583–599
Wang W, Wang W, Hu Z (2019) Retinal vessel segmentation approach based on corrected morphological transformation and fractal dimension. IET Image Proc 13(13):2538–2547
Zhao S, Liu T, Liu B et al (2020) Attention residual convolution neural network based on U-net (AttentionResU-Net) for retina vessel segmentation. E&ES 440(3):032138
Liu ZF, Zhang YZ, Liu PZ et al (2018) Retinal vessel segmentation using densely connected convolution neural network with colorful fundus images. J Med Imaging Health Inf 8(6):1300–1307
Feucht N, Maier M, Lepennetier G et al (2019) Optical coherence tomography angiography indicates associations of the retinal vascular network and disease activity in multiple sclerosis. Multiple Sclerosis J 25(2):224–234
Stamov G, Stamova I, Martynyuk A et al (2020) Design and practical stability of a new class of impulsive fractional-like neural networks. Entropy 22(3):337
Zambra M, Maritan A, Testolin A (2020) Emergence of network motifs in deep neural networks. Entropy 22(2):204
Moldovan A, Caţaron A, Andonie R (2020) Learning in feedforward neural networks accelerated by transfer entropy. Entropy 22(1):102
Tang X, Zhang X (2020) Conditional adversarial domain adaptation neural network for motor imagery EEG decoding. Entropy 22(1):96
Du K, Wan P, Wang Y et al (2020) Spectrum sensing method based on information geometry and deep neural network. Entropy 22(1):94
Liu H, Liu J, Yang W et al (2020) Analysis and prediction of land use in Beijing-Tianjin-Hebei region: a study based on the improved convolutional neural network model. Sustainability 12(7):3002
Hwang JK, Duhirwe PN, Yun GY et al (2020) A novel hybrid deep neural network model to predict the refrigerant charge amount of heat pumps. Sustainability 12(7):2914
Kachba Y, Chiroli DMG, Belotti JT et al (2020) Artificial neural networks to estimate the influence of vehicular emission variables on morbidity and mortality in the largest metropolis in South America. Sustainability 12(7):2621
Chung J, Kim HJ (2020) An automobile environment detection system based on deep neural network and its implementation using IoT-enabled in-vehicle air quality sensors. Sustainability 12(6):2475
Yang Y, Zheng X, Sun Z (2020) Coal resource security assessment in china: a study using entropy-weight-based TOPSIS and BP neural network. Sustainability 12(6):2294
Huang J, Kang J, Wang H et al (2020) A novel approach to measuring urban waterlogging depth from images based on mask region-based convolutional neural network. Sustainability 12(5):2149
Han Y, Zhou L, Gao P et al (2020) Research on BP neural network-based dynamic travel time prediction method. J Ocean Univ China (Nat Sci Ed) 50(2):142–154
Zhang H, Zheng NS, Feng QL (2019) BP neural network assisted NDVI inversion of GNSS reflected signal. Sci Technol Eng 19(36):81–86
Wu P, Xu JY, Wang YR, Yu B (2019) An elevator noise evaluation method based on BP neural network. Digital Technol Appl 37(12):76–78
Cheng Y, Ma M, Zhang L et al (2020) Retinal blood vessel segmentation based on Densely connected U-net. Math Biosci Eng 17(4):3088
Escobar MA, Guzmán Sepúlveda JR, Michel P et al (2019) Una propuesta para medir la similaridad entre imágenes segmentadas de la red vascular de la retina. Nova Sci 11(22):224–245
Hassan G, Hassanien AE (2018) Retinal fundus vasculature multilevel segmentation using whale optimization algorithm. SIViP 12(2):263–270
Singh L, Sree SR, Likhita P et al (2019) Robust retinal blood vessel segmentation to detect diabetic retinopathy. Int J Appl Res Inf Technol Comput 10(3):111–123
Al Sariera TM, Rangarajan L (2018) Extraction of blood vessels in retina. J Inf Technol Res (JITR) 11(4):122–136
Yan H, Wang LJ, Gao L et al (2019) Evaluation of fault sealing based on BP neural network. Complex Oil Gas Reservoirs 12(4):15–18
Almotiri J, Elleithy K, Elleithy A (2018) Retinal vessels segmentation techniques and algorithms: a survey. Appl Sci 8(2):155
Bozic I, Li X, Tao Y (2018) Quantitative biometry of zebrafish retinal vasculature using optical coherence tomographic angiography. Biomed. Optics Express 9(3):1244–1255
Samuel PM, Veeramalai T (2019) Multilevel and multiscale deep neural network for retinal blood vessel segmentation. Symmetry 11(7):946
Acknowledgements
This work was supported by Baotou Medical College "learning program," "learning program," and "practice program" in 2018 (Grant Number: 2018BYWWJ-ZX-04); innovation and entrepreneurship training program for college students of Baotou Medical College in 2019 (Grant Number: BYDCXL-201922); Bud program of Baotou Medical College in 2019 (Grant Number: 2019BYJJ-HL-11); Baotou Medical and Health Science and Technology in 2019 (Grant Number: wsjj2019040); and Baotou Medical College BeanStalk project in 2020 (Grant Number: 2020BYJJ-11); and Inner Mongolia Natural Science Foundation (Grant Number: 2020MS06001).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Tang, S., Yu, F. Construction and verification of retinal vessel segmentation algorithm for color fundus image under BP neural network model. J Supercomput 77, 3870–3884 (2021). https://doi.org/10.1007/s11227-020-03422-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-020-03422-8