Abstract
Diabetic retinopathy (DR) is a chronic disease that may cause vision loss in diabetic patients. Microaneurysms which are characterized by small red spots on the retina due to fluid or blood leakage from the weak capillary wall often occur during the early stage of DR, making screening at this stage is essential. In this paper, an automatic screening system for early detection of DR in retinal images is developed using a combined shape and texture features. Due to minimum number of hand-crafted features, the computational burden is much reduced. The proposed hybrid multi-kernel support vector machine classifier is constructed by learning a kernel model formed as a combination of the base kernels. This approach outperforms the recent deep learning techniques in terms of the evaluation metrics. The efficiency of the proposed scheme is experimentally validated on three public datasets — Retinopathy Online Challenge, DIARETdB1, MESSIDOR, and AGAR300 (developed for this study). Studies reveal that the proposed model produced the best results of 0.503 in ROC dataset, 0.481 in DIARETdB1, and 0.464 in the MESSIDOR dataset in terms of FROC score. The AGAR300 database outperforms the existing MA detection algorithm in terms of FROC, AUC, F1 score, precision, sensitivity, and specificity which guarantees the robustness of this system.
Graphical abstract
Similar content being viewed by others
References
International diabetes federation Diabetes atlas (2013) Brussels, Belgium, 6th edn. Available: https://www.idf.org/e-library/epidemiology-research/diabetes-atlas/19-atlas-6th-edition.html
Lian S, Li L, Lian G, Xiao X, Luo Z, Li S (2021) A global and local enhanced residual U-net for accurate retinal vessel segmentation. In IEEE/ACM Transactions on Computational Biology and Bioinformatics 3(01):852–862
Taylor HR, Keeffe JE (2001) World blindness: a 21st century perspective. British Jour Ophthalmology 85(3):261–266
Zou B, Dai Y, He Q, Zhu C, Liu G, Su Y, Tang R (2021) Multi-label classification scheme based on local regression for retinal vessel segmentation. In IEEE/ACM Transactions on Computational Biology and Bioinformatics 3(01):2586–2597
Wang S, Tang HL, Al Turk LI, Hu Y, Sanei S, Saleh GM, Peto T (2017) Localizing microaneurysm in fundus image through singular spectrum analysis. IEEE Trans Biomed Eng 64(5):46–53
Zhou W, Wu C, Chen D, Yi Y, Du W (2017) Automatic microaneurysm detection using the sparse principal component analysis-based unsupervised classification method. IEEE Access 5:2563–2572
Veiga D, Martins N, Ferreira M, Monteiro J (2017) Automatic microaneurysm detection using laws texture masks and support vector machines. Comput Methods Biomech Biomed Eng: Imaging Vis 6(4):405–416
Habib MM, Welikala RA, Hoppe A, Owen CG, Rudnicka AR, Barman SA (2017) Detection of microaneurysms in retinal images using an ensemble classifier. Inform Med 9:44–57
Orlando JI, Prokofyeva E, Fresno M, Blaschko MB (2018) An ensemble deep learning based approach for red lesion detection in fundus images. Comp Methods and Prog in Biomed 153:115–127
Chudzik P, Majumdar S, Caliva F, Al-Din B, Hunter A (2018) Microaneurysm detection using fully convolutional neural networks. Comput Methods Programs Biomed 158:185–192
Ling Dai, Liang Wi, and Huating Li, “A deep learning system for detecting diabetic retinopathy across the disease spectrum,” Nature Communications, 10–1038/s41467021–23458–5
Zhao G, Fu D, Yang T (2021) A deep learning method for microaneurysms segmentation in fundus images. In: Jia Y., Zhang W., Fu Y., Yu Z., Zheng S. (eds) Proceedings of 2021 Chinese Intelligent Systems Conference. Lecture Notes in Electrical Engineering, vol 805. Springer, Singapore. https://doi.org/10.1007/978-981-16-6320-8_79.
Eftekhari N, Pourreza H, Masoudi M, Ghiasi-Shirazi K, Saeedi E (2019) “Microaneurysm detection in fundus images using a two-step convolutional neural network”, Bio Medical Engineering Online, vol. 18,no. 67.
Dashtbozorg B, Zhang J, Huang F, HaarRomeny BM (2018) Retinal microaneurysms detection using local convergence index features. IEEE Trans Image Process 27(7):3300–3315
Derwin DJ, Selvi ST, Singh OJ (2019) Discrimination of microaneurysm in color retinal images using texture descriptors. SIViP 7(5):1–8
Kauppi T, Kalesnykiene V, Kamarainen JK, Lensu L, Sorri I, Raninen A, Voutilainen R, Uusitalo H, Kalviainen H, Pietila J (2007) “The DIARETDB1 diabetic retinopathy database and evaluation protocol,” Proceedings of the British Machine Conference, BMVA Press, pp. 15.1–15.10.
Decencière E, Zhang X, Cazuguel G, Laÿ B, Cochener B (2014) “Feedback on a publicly distributed image database: the messidor database”, Image Analysis and Stereology, International Society for Stereology, pp.231–234. ff10.5566/ias.1155ff. ffhal-01082570f.
http://webeye.ophth.ulowa.edu/roc/var/www/university of Iowa, Retinopathy Online Challenge: 2007. Accessed 2007
Derwin DJ, Selvi ST, Singh OJ (2019) Secondary observer system for detection of microaneurysms in fundus images using texture descriptors. Journal of Dig Imag 32(1):1–9
Imran U, Alnejalli KA (2020) Intelligent automated detection of microaneurysms in fundus images using feature-set tuning. IEEE Access 8:65187–65196
Joshi S, Karule PT (2020) Mathematical morphology for microaneurysm detection in fundus images. Eur J Ophthalmol 30(5):1135–1142
Manjaramkar A, Kokare M (2017) Statistical geometrical features for microaneurysm detection. J Digit Imag 31(2):224–234
Romero RR, Carballido JM, Capistran JH, Uribe-valencia LJ (2015) ‘A method to assist in the diagnosis of early diabetic retinopathy: image processing applied to detection of microaneurysms in fundus images.’ Computerized Med Imag Graph 44:41–53
Seoud L, Hurtut T, Chelbi J (2016) Red lesion detection using dynamic shape features for diabetic retinopathy screening. IEEE Trans Med Imag 35(4):1116–1126
Mizutani A, Muramatsu C, Hatanaka Y, Suemori S, Hara T, Fujita H (2009) Automated microaneurysm detection method based on double ring filter in retinal fundus images. Proc. SPIE 7260, Medical Imaging 2009: Computer-Aided Diagnosis, 72601N. https://doi.org/10.1117/12.813468
Aravind C, Ponnibala M, Vijayachitra S (2013) Automatic detection of microaneurysms and classification of diabetic retinopathy images using SVM technique. Int J Comput Appl 11:18–22
Sehirli E, Turan MK, Dietzel A (2015) Automatic detection of microaneurysms in RGB retinal fundus images. Int J Sci Technol Res 1(8):1–7
Haloi M (2016) “Improved microaneurysm detection using deep neural networks”, Available: arXiv:1505.04424.
Cao W, Czarnek N, Shan J, Li L (2018) Microaneurysm detection using principal component analysis and machine learning methods. IEEE Trans Nanobiosci 17(3):191–198
Ren F, Cao P, Li W, Zhao D, Zaiane O (2017) Ensemble based adaptive over-sampling method for imbalanced data learning in computer aided detection of microaneurysm. Computerized Med Imag Graph 55:54–67
Jeba Derwin, Priestly Shan, “Diabetic retinopathy- fundus image dataset (AGAR300)”, IEEE Dataport, Nov 2020. https://doi.org/10.21227/Fsnq-Tn19
Adal KM, Sidibe D, Ali S, Chaum E, Karnowski TP, Meriaudeau F (2014) Automated detection of microaneurysms using scale-adapted blob analysis and semi-supervised learning. Comp Methods and Programs in Biomed 114(1):1–10
Derwin J, Selvi T, Singh J, Shan P (2020) A novel automated system of discriminating microaneurysms in fundus images. Biomed Signal Process Control 58:1–9
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
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
About this article
Cite this article
Derwin, D.J., Shan, B.P. & Singh, O.J. Hybrid multi-kernel SVM algorithm for detection of microaneurysm in color fundus images. Med Biol Eng Comput 60, 1377–1390 (2022). https://doi.org/10.1007/s11517-022-02534-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-022-02534-y