A new approach for sensitivity improvement of retinal blood vessel segmentation in high-resolution fundus images based on phase stretch transform

(1) * Kartika Firdausy Mail (Department of Electrical Engineering, Universitas Ahmad Dahlan & Department of Electrical and Information Engineering, Universitas Gadjah Mada, Indonesia)
(2) Oyas Wahyunggoro Mail (Department of Electrical and Information Engineering, Universitas Gadjah Mada)
(3) Hanung Adi Nugroho Mail (Department of Electrical and Information Engineering, Universitas Gadjah Mada, Indonesia)
(4) Muhammad Bayu Sasongko Mail (Department of Ophthalmology, Universitas Gadjah Mada, Indonesia)
*corresponding author


The eye-fundus photograph is widely used for eye examinations. Accurate identification of retinal blood vessels could reveal information that is helpful for clinical diagnoses of many health disorders. Although several methods have been proposed to segment images of retinal blood vessels, the sensitivity of these methods is plausible to be improved. The algorithm’s sensitivity refers to the algorithm’s ability to identify retinal vessel pixels correctly. Furthermore, the resolution and quality of retinal images are improving rapidly. Consequently, new segmentation methods are in demand to overcome issues from high-resolution images. This study presented improved performance of retinal vessel segmentation using a novel edge detection scheme based on the phase stretch transform (PST) function as its kernel. Before applying the edge detection stage, the input retinal images were pre-processed. During the pre-processing step, non-local means filtering on the green channel image, followed by contrast limited adaptive histogram equalization (CLAHE) and median filtering, were applied to enhance the retinal image. After applying the edge detection stage, the post-processing steps, including the CLAHE, median filtering, thresholding, morphological opening, and closing, were implemented to obtain the segmented image. The proposed method was evaluated using images from the high-resolution fundus (HRF) public database and yielded promising results for sensitivity improvement of retinal blood vessel detection. The proposed approach contributes to a better segmentation performance with an average sensitivity of 0.813, representing a clear improvement over several benchmark techniques


retinal fundus images; retinal blood vessel; segmentation; sensitivity; phase stretch transform




Article metrics

Abstract views : 206 | PDF views : 43




Full Text



[1] V. Lakshminarayanan, H. Kheradfallah, A. . Sarkar, and J. J. Balaji, “Automated detection and diagnosis of diabetic retinopathy: a comprehensive survey,” Journal of Imaging, vol. 7, no. 165, pp. 1–26, 2021, doi: 10.3390/jimaging7090165.

[2] Z. Fan et al., “Accurate retinal vessel segmentation via octave convolution neural network,” arXiv:1906.12193, pp. 1–10, 2019, doi: 10.48550/arXiv.1906.12193.

[3] T. Araujo, A. M. Mendonca, and A. Campilho, “Parametric model fitting-based approach for retinal blood vessel caliber estimation in eye fundus images,” PLoS ONE, vol. 13, no. 4, pp. 1–27, 2018, doi: 10.1371/journal.pone.0194702.

[4] S. Stolte and R. Fang, “A survey on medical image analysis in diabetic retinopathy,” Medical Image Analysis, vol. 64, no. 101742, pp. 1–27, 2020, doi: 10.1016/j.media.2020.101742.

[5] S. Biswas, M. I. A. Khan, M. T. Hossain, A. Biswas, T. Nakai, and J. Rohdin, “Which color channel is better for diagnosing retinal diseases automatically in color fundus photographs?,” Life, vol. 12, no. 7, pp. 1–38, 2022, doi: 10.3390/life12070973.

[6] M. Arhami, A. Desiani, S. Yahdin, A. I. Putri, R. Primartha, and H. Husaini, “Contrast enhancement for improved blood vessels retinal segmentation using top-hat transformation and otsu thresholding,” International Journal of Advances in Intelligent Informatics, vol. 8, no. 2, pp. 210–223, 2022, doi: 10.26555/ijain.v8i2.779.

[7] M. Tavakoli, A. Mehdizadeh, R. Pourreza Shahri, and J. Dehmeshki, “Unsupervised automated retinal vessel segmentation based on Radon line detector and morphological reconstruction,” IET Image Processing, vol. 15, no. 7, pp. 1484–1498, 2021, doi: 10.1049/ipr2.12119.

[8] A. Krestanova, J. Kubicek, and M. Penhaker, “Recent techniques and trends for retinal blood vessel extraction and tortuosity evaluation: a comprehensive review,” IEEE Engineering in Medicine and Biology Society Section, vol. 8, pp. 197787–197816, 2020, doi: 10.1109/ACCESS.2020.3033027.

[9] A. Ali, W. M. D. Wan Zaki, and A. Hussain, “Retinal blood vessel segmentation from retinal image using B-COSFIRE and adaptive thresholding,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 13, no. 3, pp. 1199–1207, 2019, doi: 10.11591/ijeecs.v13.i3.

[10] F. Tian, Y. Li, J. Wang, and W. Chen, “Blood vessel segmentation of fundus retinal images based on improved frangi and mathematical morphology,” Computational and Mathematical Methods in Medicine, vol. 2021, pp. 1–11, 2021, doi: 10.1155/2021/4761517.

[11] A. Budai, R. Bock, A. Maier, J. Hornegger, and G. Michelson, “Robust vessel segmentation in fundus images,” International Journal of Biomedical Imaging, vol. 2013, pp. 1–11, 2013, doi: 10.1155/2013/154860.

[12] J. Odstrcilik et al., “Retinal vessel segmentation by improved matched filtering: evaluation on a new high-resolution fundus image database,” IET Image Processing, vol. 7, no. 4, pp. 373–383, 2013, doi: 10.1049/iet-ipr.2012.0455.

[13] R. Annunziata, A. Garzelli, L. Ballerini, A. Mecocci, and E. Trucco, “Leveraging multiscale hessian-based enhancement with a novel exudate inpainting technique for retinal vessel segmentation,” IEEE Journal of Biomedical and Health Informatics, vol. 20, no. 4, pp. 1129–1138, 2016, doi: 10.1109/JBHI.2015.2440091.

[14] J. I. Orlando, E. Prokofyeva, and M. B. Blaschko, “A discriminatively trained fully connected conditional random field model for blood vessel segmentation in fundus images,” IEEE Transactions on Biomedical Engineering, vol. 64, no. 1, pp. 16–27, 2017, doi: 10.1109/TBME.2016.2535311.

[15] L. Zhou, Q. Yu, X. Xu, Y. Gu, and J. Yang, “Improving dense conditional random field for retinal vessel segmentation by discriminative feature learning and thin-vessel enhancement,” Computer Methods and Programs in Biomedicine, vol. 2017, no. 148, pp. 13–25, 2017, doi: 10.1016/j.cmpb.2017.06.016.

[16] D. A. Dharmawan, B. P. Ng, and S. Rahardja, “A modified dolph-chebyshev type II function matched filter for retinal vessels segmentation,” Symmetry, vol. 10, no. 7, pp. 1–16, 2018, doi: 10.3390/sym10070257.

[17] R. Sundaram, K. S. Ravichandran, P. Jayaraman, and B. Venkatraman, “Extraction of blood vessels in fundus images of retina through hybrid segmentation approach,” Mathematics, vol. 7, no. 169, pp. 1–17, 2019, doi: 10.3390/math7020169.

[18] C. Wang and Y. Li, “Blood vessel segmentation from retinal images,” in Proc. of the 2020 IEEE 20th International Conf. on Bioinformatics and Bioengineering (BIBE), Cincinnati, USA, 2020, pp. 759–766. doi: 10.1109/BIBE50027.2020.00129.

[19] A. Ali, A. Hussain, W. M. D. W. Zaki, W. H. W. A. Halim, W. N. M. Isa, and N. Hashim, “Improved retinal vessel segmentation using the enhanced pre-processing method for high resolution fundus images,” F1000Research, pp. 1–9, 2021, doi: 10.12688/f1000research.73397.1.

[20] R. J. Chalakkal, W. H. Abdulla, and S. C. Hong, “Fundus retinal image analyses for screening and diagnosing diabetic retinopathy, macular edema, and glaucoma disorders,” in Diabetes and Fundus OCT, vol. 1, Elsevier, 2020, pp. 59–111. doi: 10.1016/B978-0-12-817440-1.00003-6.

[21] M. H. Asghari and B. Jalali, “Edge detection in digital images using dispersive phase stretch transform,” International Journal of Biomedical Imaging, vol.2015, no. 687819, pp. 1–6, 2015, doi: 10.1155/2015/687819.

[22] M. Suthar, H. Asghari, and B. Jalali, “Feature Enhancement in Visually Impaired Images,” IEEE Access, vol. 6, pp. 1407–1415, 2018, doi: 10.1109/access.2017.2779107.

[23] M. Suthar and B. Jalali, “Phase-Stretch Adaptive Gradient-Field Extractor (PAGE),” in Coding Theory, London, UK: IntechOpen, 2020, pp. 1–16. [Online]. Available: http://dx.doi.org/10.5772/intechopen.90361

[24] T. A. Soomro, J. Gao, L. Zheng, A. J. Afifi, S. Soomro, and M. Paul, “Retinal blood vessels extraction of challenging images,” in Data Mining, Singapore: Springer, 2019, pp. 347–359. [Online]. Available: https://doi.org/10.1007/978-981-13-6661-1_27

[25] A. P. S. Yadav, A. P. Singh, and S. Ahmad, “An improved non-local means filter for image denosing,” Journal of Critical Review, vol. 7, no. 15, pp. 2842–2845, 2020, doi: 10.31838/jcr.07.15.388.

[26] K. Chen, X. Lin, X. Hu, J. Wang, H. Zhong, and L. Jiang, “An enhanced adaptive non-local means algorithm for Rician noise reduction in magnetic resonance brain images,” BMC Medical Imaging, vol. 20, no. 2, pp. 1–9, 2020, doi: 10.1186/s12880-019-0407-4.

[27] G. Wang, Y. Liu, W. Xiong, and Y. Li, “An improved non-local means filter for color image denoising,” Optik, vol. 173, pp. 157–173, 2018, doi: 10.1016/j.ijleo.2018.08.013.

[28] Y. C. Heo, K. Kim, and Y. Lee, “Image denoising using non-local means approach in magnetic resonance imaging: a systematic review,” Applied Sciences, vol. 10, no. 20, pp. 1–16, 2020, doi: 10.3390/app10207028.

[29] Erwin and T. Yuningsih, “Detection of blood vessels in optic disc with maximum principal curvature and wolf thresholding algorithms for vessel segmentation and prewitt edge detection and circular hough transform for optic disc detection,” Iranian Journal of Science and Technology, Transactions of Electrical Engineering, vol. 45, no. 2, pp. 435–446, 2021, doi: 10.1007/s40998-020-00367-9.

[30] O. Ramos-Soto et al., “An efficient retinal blood vessel segmentation in eye fundus images by using optimized top-hat and homomorphic filtering,” Computer Methods and Programs in Biomedicine, vol. 201, p. 105949, Apr. 2021, doi: 10.1016/j.cmpb.2021.105949.

[31] Y. S. Cheng, S. H. Lin, C. Y. Hsiao, and C. J. Chang, “Detection of choroidal neovascularization by optical coherence tomography angiography with assistance from use of the image segmentation method,” Applied Sciences, vol. 10, no. 1, pp. 1–12, 2020, doi: 10.3390/app10010137.

[32] K. Mittal and V. M. A. Rajam, “Computerized retinal image analysis - a survey,” Multimedia Tools and Applications, vol. 79, pp. 1–33, 2020, doi: 10.1007/s11042-020-09041-y.

[33] S. Joshi and P. T. Karule, “Review of preprocessing techniques for fundus image analysis,” Advances in Modelling and Analysis B, vol. 60, no. 3, pp. 593–612, 2018, doi: 10.18280/ama_b.600306.

[34] W. Patil and P. Daigavane, “Screening and detection of diabetic retinopathy by using engineering concepts,” in Diabetes and Fundus OCT, vol. 1, Elsevier, 2020, pp. 285–319. [Online]. Available: https://doi.org/10.1016/B978-0-12-817440-1.00011-5

[35] H. A. Nugroho, T. Kirana, V. Pranowo, and A. H. T. Hutami, “Optic cup segmentation using adaptive threshold and morphological image processing,” Communications in Science and Technology, vol. 4, no. 2, pp. 63–67, 2019, doi: 10.21924/cst.4.2.2019.125.

[36] A. M. Ashir, S. Ibrahim, M. Abdulghani, A. A. Ibrahim, and M. S. Anwar, “Diabetic retinopathy detection using local extrema quantized haralick features with long short-term memory network,” International Journal of Biomedical Imaging, vol. 2021, pp. 1–12, Apr. 2021, doi: 10.1155/2021/6618666.

[37] A. A. Abdulsahib, M. A. Mahmoud, M. A. Mohammed, H. H. Rasheed, S. A. Mostafa, and M. A. Maashi, “Comprehensive review of retinal blood vessel segmentation and classifcation techniques: intelligent solutions for green computing in medical images, current challenges, open issues, and knowledge gaps in fundus medical images,” Network Modeling and Analysis in Health Informatics and Bioinformatics, vol. 10, no. 20, pp. 1–32, 2021, doi: 10.1007/s13721-021-00294-7.

[38] A. Imran, J. Li, Y. Pei, J. J. Yang, and Q. Wang, “Comparative analysis of vessel segmentation techniques in retinal images,” IEEE Access, vol. 7, pp. 114862–114887, 2019, doi: 10.1109/ACCESS.2019.2935912.

[39] K. Firdausy, O. Wahyunggoro, H. A. Nugroho, M. B. Sasongko, and R. Hidayat, “Impact of different degree of smoothing on non-local means based filter for retinal vessel modeling,” in Proc. of the 2019 IEEE 5th International Conf. on Science in Information Technology (ICSITech 2019), Yogyakarta, Indonesia, 2019, pp. 118–122. doi: 10.1109/ICSITech46713.2019.8987555.

[40] R. B. Q. Ang, H. Nisar, M. B. Khan, and C. Y. Tsai, “Image Segmentation of Activated Sludge Phase Contrast Images Using Phase Stretch Transform,” Microscopy, vol. 68, no. 2, pp. 144–158, 2018, doi: 10.1093/jmicro/dfy134.

[41] P. Konatham, M. Venigalla, L. P. Amaraneni, and K. S. Vani, “Automatic detection of optic disc for diabetic retinopathy,” International Journal of Innovative Technology and Exploring Engineering, vol. 9, no. 7, pp. 1013–1015, 2020, doi: 10.35940/ijitee.F4390.059720.

[42] J. Darvish and M. Ezoji, “Morphological exudate detection in retinal images using PCA-based optic disc removal,” Journal of AI and Data Mining, vol. 7, no. 4, pp. 487–493, 2019, doi: 10.22044/jadm.2019.1488.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

International Journal of Advances in Intelligent Informatics
ISSN 2442-6571  (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
   andri.pranolo.id@ieee.org (publication issues)

View IJAIN Stats

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0