Call For Papers
Contact Us

  Automated Blood Vessels Segmentation Method for Retinal Fundus Image Based on Mathematical Morphology Operations and Kirsch's Template  
  Authors : Mahoro Adidja; Hamzeh Abdillahi Robleh
  Cite as:


Automated retinal Blood vessels analysis is currently a highly important tool and inevitable step in development of computerized systems in medical imaging field. Assessing the structure and appearance of the retinal blood vessels in retinal fundus image plays a significant role in diagnostic, screening, evaluation and treatment of many ophthalmologic conditions and diseases such as diabetic retinopathy, hypertensive retinopathy, glaucoma, and age related macular degeneration. In this paper, we present blood vessels segmentation approach, which can be used in computer based retinal image analysis to extract retinal blood vessels network. This method is conducted in 3 phases: 1) Pre-processing, where the retinal color fundus image is converted to grayscale image and enhanced using Contrast Limited Adaptive Histogram Equalization, 2) Extraction of retinal blood vessels using morphological operations and Kirsch's template, and finally, 3) Post-processing carried out using 2D median filter to remove noise and isolated pixels. Furthermore, the performance of the proposed algorithm is tested and analyzed on DRIVE dataset and compared with other existing standard methods using a number of measures like accuracy, sensitivity, specificity and time required to process a single image. We achieved 94.60% accuracy, 74.91% sensitivity, and 96.49% specificity; which are higher than many of the state of the art methods compared with. The proposed segmentation approach is also very efficient with time complexity that is significantly lower than the existing methods.


Published In : IJCSN Journal Volume 9, Issue 3

Date of Publication : June 2020

Pages : 114-122

Figures :08

Tables : 03


Mahoro Adidja : Department of Computer Science and Technology, School of Artificial Intelligence and Computer Science, Jiangnan University, 1800 Lihu Boulevard, Wuxi, Jiangsu 214122, People’s Republic of China.

Hamzeh Abdillahi Robleh : Department of Computer Science and Technology, School of Artificial Intelligence and Computer Science, Jiangnan University, 1800 Lihu Boulevard, Wuxi, Jiangsu 214122, People’s Republic of China.


Image Processing, Retinal Blood Vessels, Morphological Operation, Kirsch’s Template

Retinal image is being used by ophthalmologists to aid in screening, diagnosis and identification of ophthalmologic disorders. Most times, extraction of retinal blood vessel network is a key challenge for proper analysis, visualization and quantitative comparison. The present study developed an automated method for extraction of retinal blood vessels from retinal fundus image within a short time using morphological operations method coupled with Kirsch’s template. The proposed framework was validated on the publicly available retinal image dataset DRIVE.The results obtained were compared with some other existing standard methods tested and evaluated on the same DRIVE dataset. Based on the achieved results, the proposed methods is promising comparing to other existing standard methods used similar dataset in term of accuracy, sensitivity, specificity and time taken to process a single image. This showed that it is possible to extract retinal blood vessels with high accuracy within a short time.


[1] T. W. Ryan, “Image Segmentation Algorithms Overview,” Computer Visionn and Pattern Recognition, 2017. [2] A. J. Panchasara Chandni, “Application of Image Segmentation Techniques on Medical Reports,” Int. J. Comput. Sci. Inf. Technol, 2015. [3] M. Forouzanfar, N. Forghani, and M. Teshnehlab, “Parameter optimization of improved fuzzy c means clustering algorithm for brain MR image segmentation,”, Engineering Applications of Artificial Intelligence vol. 23, pp. 160 162, 2010. [4] J. A. Delmerico, P. David, and J. J. Corso, “Building Facade Detection, Segmentation, and Parameter Estimation for Mobile Robot Localization and Guidance,” International Conference on Intelligent Robots and Systems pp. 1632 1639, 2011. [5] Z. Liu, S. Member, S. Member, Q. Zhang, and N. Zheng, “Joint Video Object Discovery and Segmentation by Coupled Dynamic Markov Networks,” IEEE transactions on image processing 12, pp. 1 15, 2018. [6] G. Sharp et al., “Vision 20/20: Perspectives on automated image segmentation forradiotherapy,” Am. Assoc. Phys. Med., vol. 41, no. 5, pp. 1 13, 2014. [7] Rento P. Elisa R, “Analysis of Disease using Retinal Blood Vessels Detection,” Int. J. Eng. Comput. Sci., pp. 19644 19647, 2016. [8] Rento P. Elisa R, “A multi orientation analysis approach to retinal vessel tracking,” J. Math. Imaging Vis., 2014. [9] A. Imran, J. Li, Y. Pei, J. Yang, and Q. Wang, “Comparative Analysis of Vessel Segmentation Techniques in Retinal Images,” IEEE Access, vol. 7, pp. 114862 114887, 2019. [10] L. P. Sa, “A fast, efficient and automated method to extract vessels from fundus images,” J. Vis., pp. 263 270, 2010. [11] I. Chanwimaluang and G. Fan, “An Efficient Algorithm For Extraction Of Anatomical Structures In Retinal image,” Int. Conf. image Process., 2003. [12] N. P. Singh, R. Kumar, and R. Srivastava, “Local Entropy Thresholding Based Fast Retinal Vessels Segmentation by Modifying Matched Filter,” Int. Conf. Comput. Commun. Autom., 2015. [13] C. Wu, G. Agam, and P. Stanchev, “A general framework for vessel segmentation in retinal images,” IEEE Int. Symp. Comput. Intell. Robot. Autom. (CIRA), 2017. [14] T. Yedidya and R. Hartley, “Tracking of Blood Vessels in Retinal Images Using Kalman Filter,” IEEE Int. Conf. 2008 Digit. image Comput. Appl., 2008. [15] Petar Sekulić et al., “Retinal blood vessels segmentation using support vector machine and modified line detector,”International Scientific Professional Conference Information Technology 2017. [16] L. Xu and S. Luo, “A novel method for blood vessel detection from retinal images,” Biomed. Eng. Online, 2010. [17] G. G. Gardner, D. Keating, T. H. Williamson, and A. T. Elliott, “Automatic detection of diabetic retinopathy using an artificial neural network : a screening tool,” Br. Journal Ophthalmol., 1996. [18] K. et Al., “Deep Retinal Image Understanding,” Comput. Vis. Pattern Recognit., 2016. [19] J. Almotiri, K. Elleithy, and A. Elleithy, “Retinal Vessels Segmentation Techniques and Algorithms: A Survey,” Appl. Sci., p. 155, 2018. [20] N. Memari, et al. “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., 2018. [21] X. Yin, B. W. Ng, J. He, Y. Zhang, and D. Abbott, “Unsupervised Segmentation of Blood Vessels from Colour Retinal Fundus Images,”international conference on health information sciences pp. 194 195, 2014. [22] W. S. Oliveira, J. V. Teixeira, T. I. Ren, and G. D. C. Cavalcanti, “Unsupervised Retinal Vessel Segmentation Using Combined Filters,” PLoS One, pp. 1 21, 2016. [23] B. Sindhu and J. B. Jeeva, “Automated Retinal Vessel Segmentation Using Morphological Operation And Threshold,” Int. J. Sci. Eng. Res., 2013. [24] A. Kundu, “Retinal vessel segmentation using Morphological Angular Scale Space,” 2012 Third Int. Conf. Emerg. Appl. Inf. Technol., 2012. [25] N. Singla, “Blood Vessel Contrast Enhancement Techniques for Retinal Images,” Int. J. Adv. Res. Comput. Sci., 2017. [26] A. W. Setiawan, T. R. Mengko, O. S. Santoso, and A. B. Suksmono, “Color Retinal Image Enhancement using CLAHE,” Int. Conf. ICT Smart Soc., 2013. [27] P. Singh, “Non Uniform Background Removal using Morphology based Structuring Element for Particle Analysis,” Int. J. Comput. Appl., 2011. [28] N. Ramesh, “Contrast stretching enhancementtechniques for acute leukemia image,” Publ. Probl. Appl. Eng. Res., pp. 190 194, 2013. [29] S. S. Al amri, N. V Kalyankar, and S. D. Khamitkar, “Linear and Non linear Contrast Enhancement Image,” Int. J. Comput. Sci. Netw. Secur., pp. 139 143, 2010. [30] P. Dai, H. Luo, H. Sheng, Y. Zhao, L. Li, and J. Wu, “A New Approach to Segment Both Main and Peripheral Retinal Vessels Based on Gray Voting and Gaussian Mixture Model,” PLoS One, 2015. [31] M. Vlachos and E. Dermatas, “Computerized Medical Imaging and Graphics Multi scale retinal vessel segmentation using line tracking,” Comput. Med. Imaging Graph., 2010. [32] W. A. Mustafa, A. S. Mahmud, and W. Khairunizam, “Blood Vessel Extraction Using Combination of Kirsch ’ s Templates and Fuzzy C Means (FCM) on Retinal Images,” IOP Conf. Ser. Mater. Sci. Eng., 2019. [33] Rento P. Elisa R, “Fast detection and segmentation in retinal blood vessels using Gabor filters,” in Signal Processing and Communications Applications Conference,, pp. 104 108, 2014. [34] A. M. Mendonça, S. Member, and A. Campilho, “Segmentation of Retinal Blood Vessels by Combining the Detection of Centerlines and Morphological Reconstruction,” IEEE Trans. Med. imaging, 2006. [35] G. Azzopardi, N. Strisciuglio, M. Vento, and N. Petkov, “Trainable COSFIRE filters for vessel delineation with application to retinal images,” Med. Image Anal., 2015. [36] P. Bankhead, C. N. Scholfield, J. G. Mcgeown, and T. M. Curtis, “Fast Retinal Vessel Detection and Measurement Using Wavelets and Edge Location Refinement,” PLoS One, 2012. [37] A. Hassanien, " Applications of Intelligent Optimization in Biology and Medicine." Springer International Publishing, 2016.