Abstract
Purpose
Diabetic retinopathy (DR) is a retinal pathology and a result of long-term diabetes. It affects the small retinal vessels, producing changes in diameter, width, and tortuosity. DR is the major cause of blindness among working people. Thus, early and accurate diagnosis is greatly important to avoid vision loss.
Methods
In this work, we describe a new system for DR detection using color fundus images. This system is divided into four main parts: first, a preprocessing step is performed to extract the green channel and apply geometrical transformations for data augmentation. Secondly, the retinal vessels are extracted using a new convolutional neural network (CNN). Then, six morphological features are computed from binary segmented vessel images. Finally, five supervised classifiers (SVM, KNN, CART, PLDA, and ANN) are employed for DR classification.
Results
To evaluate our proposed system, we used three public databases: DRIVE, HRF, and Messidor. The experimental results demonstrate that SVM classifier achieved the best performance for binary DR classification on HRF and Messidor datasets, outperforming the state-of-the-art.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abdelmaksoud E, El-Sappagh S, Barakat S, Abuhmed T, Elmogy M. Automatic diabetic retinopathy grading system based on detecting multiple retinal lesions. IEEE Access. 2021;9:15939–60. https://doi.org/10.1109/ACCESS.2021.3052870.
Anas B, Sun G, Li Y, Mazhar S, Khan AQ. Diabetic retinopathy detection and classification using mixed models for a disease grading database. IEEE. Access. 2021;9:23544–53. https://doi.org/10.1109/ACCESS.2021.3056186.
Aziza EZ, El Amine LM, Mohamed M, Abdelhafid B. Decision tree CART algorithm for diabetic retinopathy classification. In: 2019 6th International Conference on Image and Signal Processing and their Applications (ISPA). 2019. p. 1–5. https://doi.org/10.1109/ISPA48434.2019.8966905.
Baget-Bernaldiz M, Romero-Aroca P, Santos-Blanco E, Navarro-Gil R, Valls A, Antonio M, Rashwan HA, Domenec P. Testing a deep learning algorithm for detection of diabetic retinopathy in a Spanish diabetic population and with MESSIDOR database. Diagnostics. 2021;11(8):1385. https://doi.org/10.3390/diagnostics11081385.
Bhavsar H, Panchal MH. A review on support vector machine for data classification. Int J Adv Res Comput Eng Technol. 2012;1(10):185–9.
Boudegga H, Elloumi Y, Akil M, Hedi Bedoui M, Kachouri R, Ben AA. Fast and efficient retinal blood vessel segmentation method based on deep learning network. Comput Med Imaging Graph. 2021;90:101902. https://doi.org/10.1016/j.compmedimag.2021.101902.
Boyd SR, Advani A, Altomare F, Stockl F. Retinopathy. Can. J. Diabetes. 2013;37:137–41. https://doi.org/10.1016/j.jcjd.2013.01.038.
Brownlee J. Classification and regression trees for machine learning. Machine Learning Mastery. 2016; https://machinelearningmastery.com/classification-and-regression-trees-for-machine-learning/. Accessed 15 Nov 2021.
Brownlee J. A gentle introduction to k-fold cross-validation. 2020. https://machinelearningmastery.com/k-fold-cross-validation/. Accessed 15 Nov 2021.
Budai A, Bock R, Maier A, Hornegger J, Michelson G. Robust vessel segmentation in fundus images. Int J Biomed Imaging. 2013;2013:154860. https://doi.org/10.1155/2013/154860.
Coomans D, Massart DL. Alternative k-nearest neighbour rules in supervised pattern recognition: Part 1. k-Nearest neighbour classification by using alternative voting rules. Anal Chim Acta. 1982;136:15–27. https://doi.org/10.1016/S0003-2670(01)95359-0.
Decencière E, Zhang X, Cazuguel G, Lay B, Cochener B, Trone C, Gain P, et al. Feedback on a publicly distributed image database: the Messidor database. Image Anal Stereol. 2014;33(3):231–4. https://doi.org/10.5566/ias.1155.
Franklin SW, Rajan SE. Computerized screening of diabetic retinopathy employing blood vessel segmentation in retinal images. Biocybern and Biomed Eng. 2014;34:117–24. https://doi.org/10.1016/j.bbe.2014.01.004.
Gayathri S, Gopi V, Palanisamy P. Automated classification of diabetic retinopathy through reliable feature selection. Phys Eng Sci Med. 2020a:43. https://doi.org/10.1007/s13246-020-00890-3.
Gayathri S, Krishna AK, Gopi VP, PalanisamyP. Automated binary and multiclass classification of diabetic retinopathy using Haralick and multiresolution features. IEEE Access. 2020b;8:57497–504. https://doi.org/10.1109/ACCESS.2020.2979753.
Hajabdollahi M, Esfandiarpoor R, Najarian K, Karimi N, Samavi S, Reza Soroushmehr SM. Hierarchical pruning for simplification of convolutional neural networks in diabetic retinopathy classification. 41st Ann. Int Conf IEEE Eng Med Biol Soc. 2019:970–3. https://doi.org/10.1109/EMBC.2019.8857769.
Hemanth DJ, Deperlioglu O, Kose U. An enhanced diabetic retinopathy detection and classification approach using deep convolutional neural network. Neural Comput Appl. 2020;32(3):707–21. https://doi.org/10.1007/s00521-018-03974-0.
International Diabetes Federation. IDF DIABETES ATLAS. Eighth (8th) edition 2017, International Diabetes Federation, 2017. https://www.diabetesatlas.org.
Jiang Y, Zhang H, Ning T, Li C. Automatic retinal blood vessel segmentation based on fully convolutional neural networks. Symmetry. 2019;11(9):1112. https://doi.org/10.3390/sym11091112.
Jiang Y, Falin W, Jing G, Liu W. Efficient BFCN for automatic retinal vessel segmentation. J Ophthalmol. 2020;2020:6439407. https://doi.org/10.1155/2020/6439407.
Jin Q, Meng Z, Pham TD, Chen Q, Wei L, Su R. DUNet: A deformable network for retinal vessel segmentation. Knowl Based Syst. 2019;178:149–62. https://doi.org/10.1016/j.knosys.2019.04.025.
Kobrin K, Barbara E. Overview of epidemiologic studies of diabetic retinopathy. Ophthalmic Epidemiol. 2007;14(4):179–83. https://doi.org/10.1080/09286580701396720.
Kumar S, Adarsh A, Kumar B, Singh AK. An automated early diabetic retinopathy detection through improved blood vessel and optic disc segmentation. Opt Laser Technol. 2020;121:105815. https://doi.org/10.1016/j.optlastec.2019.105815.
Leontidis G, Al-Diri B, Hunter A. A new unified framework for the early detection of the progression to diabetic retinopathy from fundus images. Comput Biol and Med. 2017;90:98–115. https://doi.org/10.1016/j.compbiomed.2017.09.008.
Li D, Rahardja S. BSEResU-Net: An attention-based before-activation residual U-Net for retinal vessel segmentation. Comput Methods Programs Biomed. 2021;205:106070. https://doi.org/10.1016/j.cmpb.2021.106070.
Liu J, Chen S, Tan X, Zhang D. Efficient pseudoinverse linear discriminant analysis and its nonlinear form for face recognition. Int J Pattern Recognit Artif Intell. 2007;21(8):1265–78. https://doi.org/10.1142/S0218001407005946.
Lv Y, Ma H, Li J, Liu S. Attention guided U-net with atrous convolution for accurate retinal vessels segmentation. IEEE Access. 2020;8:32826–39. https://doi.org/10.1109/ACCESS.2020.2974027.
Ma Y, Li X, Duan X, Peng Y, Zhang Y. Retinal vessel segmentation by deep residual learning with wide activation. Comput Intell and Neurosci. 2020:8822407. https://doi.org/10.1155/2020/8822407.
Marcano-Cedeño A, Alvarez-Vellisco A, Andina D. Artificial metaplasticity MLP applied to image classification. In: IEEE International Conference on Industrial Informatics (INDIN); 2009. p. 650–3. https://doi.org/10.1109/INDIN.2009.5195879.
Nair AT, Muthuvel K. Blood vessel segmentation and diabetic retinopathy recognition: an intelligent approach. Comput Methods Biomech Biomed Eng: Imaging Vis. 2020;8(2):169–81. https://doi.org/10.1080/21681163.2019.1647459.
Ogurtsova K, da Rocha Fernandes JD, Huang Y, Linnenkamp U, Guariguata L, Cho NH, Cavan D, Shaw JE, Makaroff LE. IDF Diabetes Atlas: global estimates for the prevalence of diabetes for 2015 and 2040. Diabetes Res Clin Pract. 2017;128:40–50. https://doi.org/10.1016/j.diabres.2017.03.024.
Ozgunalp U, Fan R, Serener A. Semantic segmentation of retinal vessels using SegNet. In: 2020 28th Signal Processing and Communications Applications Conference (SIU); 2020. p. 1–4. https://doi.org/10.1109/SIU49456.2020.9302055.
Qomariah DUN, Tjandrasa H, Fatichah C. Classification of diabetic retinopathy and normal retinal images using CNN and SVM. In: 2019 12th International Conference on Information Communication Technology and System (ICTS); 2019. p. 152–7. https://doi.org/10.1109/ICTS.2019.8850940.
Samuel PM, Veeramalai T. Multilevel and multiscale deep neural network for retinal blood vessel segmentation. Symmetry. 2019;11(7) https://doi.org/10.3390/sym11070946.
Sathananthavathi V, Indumathi G. Encoder Enhanced Atrous (EEA) Unet architecture for retinal blood vessel segmentation. Cognit Syst Res. 2021;67:84–95. https://doi.org/10.1016/j.cogsys.2021.01.003.
Staal J, Abràmoff M, Niemeijer M, ViergeverM GB. Ridge-based vessel segmentation in color images of the retina. IEEE Transact Med Imaging. 2004;23:501–9. https://doi.org/10.1109/TMI.2004.825627.
Sultana R, Rajasekhar KS. Diabetic retinopathy classification using HARALICK features. Int J Recent Technol Eng. 2019;7(6):5.
Wang S, WangX HY, Shen Y, Yang Z, Gan M, Lei B. Diabetic retinopathy diagnosis using multichannel generative adversarial network with semisupervision. IEEE Transact Autom Sci Eng. 2021;18(2):574–85. https://doi.org/10.1109/TASE.2020.2981637.
Yau JWY, Rogers SL, Kawasaki R, Lamoureux EL, Kowalski JW, Bek T, Chen SJ, et al. global prevalence and major risk factors of diabetic retinopathy. Diabetes Care. 2012;35(3):556–64. https://doi.org/10.2337/dc11-1909.
Acknowledgements
The authors thank the Directorate-General of Scientific Research and Technological Development (DGRSDT) for financial assistance towards this research, URL:www.dgrsdt.dz, Algeria.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics approval
This article does not contain any studies with human participants performed by any of the authors.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Elaouaber, Z.A., Lazouni, M.E.A. & Messadi, M. Retinal vasculature extraction and analysis for diabetic retinopathy recognition. Res. Biomed. Eng. 39, 479–491 (2023). https://doi.org/10.1007/s42600-023-00279-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42600-023-00279-7