Abstract
Blood vessel is one of the most important retinal regions used for identification of retinal diseases like glaucoma, diabetic retinopathy and occlusion through blood vessel features. This paper presented an automated image processing techniques for blood vessel segmentation through image enhancement and dynamic gray-level thresholding. Proposed approach contains of six processes: color channel selection, image complement, image enhancement, optic disk removal, dynamic gray-level thresholding and binarization. Initially, green color channel is selected from original RGB color fundus images for clear visibility of blood vessels followed by image complement techniques to differentiate blood vessel features with other retinal features. Then, complemented image is further enhanced to improve the visibility of blood vessels including thin vessels for accurate extraction, and then, disk structuring element is applied for optic disk removal. Finally, blood vessel is segmented by applying image binarization using dynamic gray-level thresholding. Proposed approach achieved good results in terms of accuracy and specificity of 95.51 and 99.14% on DRIVE dataset and 95.67 and 98.33% on HRF dataset. Also, experimental results were compared with the state-of-the-art methods and represent our proposed method achieved high accuracy and very much helpful for the ophthalmologist for disease identification during earlier stage.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Jebaseeli TJ, Deva Durai CA, Peter JD (2019) Retinal blood vessel segmentation from diabetic retinopathy images using tandem PCNN model and deep learning based SVM. Optik 199(March 2018):163328
Câmara Neto L, Ramalho GLB, Rocha Neto JFS, Veras RMS, Medeiros FNS (2017) An unsupervised coarse-to-fine algorithm for blood vessel segmentation in fundus images. Expert Syst Appl 78:182–192
Vostatek P, Claridge E, Uusitalo H, Hauta-Kasari M, Fält P, Lensu L (2017) Performance comparison of publicly available retinal blood vessel segmentation methods. Comput Med Imaging Graph 55:2–12
Jyotiprava Dash NB (2017) A method for blood vessel segmentation in retinal images using morphological reconstruction. IEEE xplore
Wankhede PR, Khanchandani KB (2020) Feature extraction in retinal images using automated methods. Int J Sci Technol Res 9(3):5326–5333
Imran A, Li J, Pei Y, Yang J-J, Wang Q (2019) Comparative analysis of vessel segmentation techniques in retinal images. IEEE Access 7:114862–114887
Moccia S, De Momi E, El S, Mattos LS (2018) Blood vessel segmentation algorithms—review of methods, datasets and evaluation metrics. Comput Meth Prog Biomed 158:71–91
Sharma A, Rani S (2016) An automatic segmentation and detection of blood vessels and optic disc in retinal images. In: International conference on communication and signal processing, ICCSP 2016, pp 1674–1678
Mano A. Contrast enhanced superpixel based segmentation of retinal images
Shaik M (2016) Blood vessel segmentation in retinal images using multiscale image enhancement. Local Entropy Thresh Cluster 1(1):38–43
Biswal B, Pooja T, Subrahmanyam NB (2018) Robust retinal blood vessel segmentation using hybrid active contour model. IET Image Proc 12(3):389–399
Borah KJ, Borbhuyan AA, Rahman SS, Baruah A (2016) Wavelet based blood vessel segmentation in retinal image analysis. Int J Eng Res Technol V5(11):324–327
Ramani RG, Shanthamalar JJ (2020) Improved image processing techniques for optic disc segmentation in retinal fundus images. Biomed Sig Process Control 58:101832
Wang X, Jiang X, Ren J (2019) Blood vessel segmentation from fundus image by a cascade classification framework. Pattern Recogn 88:331–341
Samuel PM, Veeramalai T (2019) Multilevel and multiscale deep neural network for retinal blood vessel segmentation. Symmetry 11(7)
Bandara AMRR, Giragama PWGRMPB (2018) A retinal image enhancement technique for blood vessel segmentation algorithm. In: 2017 IEEE international conference on industrial and information systems, ICIIS 2017—Proceedings, vol 2018, Janua, pp 1–5
Sabaz F, Atila U (2017) ROI detection and vessel segmentation in retinal image. Int Arch Photogram Remote Sens Spatial Inf Sci—ISPRS Arch 42(4W6):85–89
Kasmin F, Abdullah A, Prabuwono AS (2017) Retinal blood vessel segmentation using ensemble of single oriented mask filters. Int J Electr Comp Eng 7(3):1414–1422
Xue LY, Lin JW, Cao XR, Yu L (2018) Retinal blood vessel segmentation using saliency detection model and region optimization. J Algo Comput Technol 12(1):3–12
Curran K, Souahlia A, Belatreche A, Benyettou A (2017) Blood vessel segmentation in retinal images using echo state networks. In: 2017 Ninth international conference on advanced computational intelligence (ICACI), pp 1–8
Ali A, Zaki WMDW, Hussain A (2019) Retinal blood vessel segmentation from retinal image using B-COSFIRE and adaptive thresholding. Indo J Electr Eng Comp Sci 13(3):1199–1207
Oliveira WS, Teixeira JV, Ren TI, Cavalcanti GDC, Sijbers J (2016) Unsupervised retinal vessel segmentation using combined filters. PLoS ONE 11(2):1–21
Ganesan K, Naik G, Adapa D, Raj ANJ, Alisetti SN, Zhuang Z (2020) A supervised blood vessel segmentation technique for digital fundus images using Zernike moment based features. PLoS ONE 15(3):1–23
Memari N, Ramli AR, Bin Saripan MI, Mashohor S, Moghbel M (2019) Retinal blood vessel segmentation by using matched filtering and fuzzy c-means clustering with integrated level set method for diabetic retinopathy assessment. J Med Biol Eng 39(5):713–731
Christodoulidis A, Hurtut T, Ben Tahar H, Cheriet F (2016) A multi-scale tensor voting approach for small retinal vessel segmentation in high resolution fundus images. Comput Med Imag Graphics 52:28–43
Shukla AK, Pandey RK, Pachori RB (2020) A fractional filter based efficient algorithm for retinal blood vessel segmentation. Biomed Sig Process Control 59(1–16):101883
Cheng Y, Ma M, Zhang L, Jin CJ, Ma Li, Zhou Y (2020) Retinal blood vessel segmentation based on densely connected U-Net. Math Biosci Eng 17:3088–3108
Acknowledgements
This work was supported by Centre For Research, Anna University, under the Anna Centenary Research Fellowship, Anna University, Chennai, India (Reference: CFR/ACRF/2018/AR1).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Shanthamalar, J.J., Ramani, R.G. (2022). Automatic Blood Vessel Segmentation in Retinal Fundus Images Using Image Enhancement and Dynamic Gray-Level Thresholding. In: Chaki, N., Devarakonda, N., Cortesi, A., Seetha, H. (eds) Proceedings of International Conference on Computational Intelligence and Data Engineering. Lecture Notes on Data Engineering and Communications Technologies, vol 99. Springer, Singapore. https://doi.org/10.1007/978-981-16-7182-1_27
Download citation
DOI: https://doi.org/10.1007/978-981-16-7182-1_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7181-4
Online ISBN: 978-981-16-7182-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)