SUPPORT VECTOR MACHINE MODELS FOR DIABETIC RETINOPATHY DIAGNOSIS AND GRADING
DOI:
https://doi.org/10.55766/sujst-2023-03-e02051Keywords:
Decision strategy, Diabetic retinopathy, Multiclass decision, Support vector machineAbstract
This work applies five variants of the support vector machine to the classification of the various stages of nonproliferative diabetic retinopathy. Four hundred eye fundus images from the Messidor repository are preprocessed and thirteen features extracted. The features best suited as inputs for support vector machine classification are identified. Initially, binary classification of severe nonproliferative diabetic retinopathy alone versus a normal eye is performed, achieving an accuracy of 97.44% using the standard support vector machine with Gaussian kernel and when optimized for accuracy. When optimized for sensitivity, the twin bounded support vector machine achieves the highest sensitivity of 99.06%. Then multiclass grading into all four stages of nonproliferative diabetic retinopathy is performed. Best performance with regards to four performance metrics, namely accuracy, sensitivity, specificity, and precision is achieved with the twin bounded support vector machine variant, when one-versus-one decision configuration is used in combination with a novel decision strategy that includes accumulated distances from the decision hyperplanes in the decision algorithm. The results compare favorably with data published in the literature.
References
Acharya, U.R., Chua, C.K., Ng, E.Y.K., Yu, W., and Chee, C. (2008). Application of higher order spectra for the identification of diabetes retinopathy stages. J. Med. Syst., 32(6):481-488. https://doi.org/10.1007/s10916-008-9154-8
Ali, J.,Aldhaifallah, M., Nisar, K.S., Aljabr, A.A. and Tanveer, M. (2021). Regularized least squares twin SVM for multiclass classification. Big Data Res., 27:100295. https://doi.org/10.1016/j.bdr.2021.100295
American Academy of Ophthalmology. (2019). Fundamentals and Principles of Ophthalmology. Basic and Clinical Science Course, 546p.
Bhardwaj, C., Jain, S. and Sood, M. (2020). Hierarchical severity grade classification of non-proliferative diabetic retinopathy. J. Ambient. Intell. Humaniz. Comput., 12:2,649-2,670. https://doi.org/10.1007/s12652-020-02426-9
Carrera, E.V., González, A. and Carrera, R. (2017). Automated detection of diabetic retinopathy using SVM, The 2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON), p. 1-4. https://doi.org/10.1109/INTERCON.2017.8079692
Chang, C.C., and Lin, C.J. (2011). LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol.,
(3):1-27. https://doi.org/10.1145/1961189.1961199
Chen, B., Wang, L., Wang, X., Sun, J., Huang, Y., Feng, D. and Xu, Z. (2020). Abnormality detection in retinal image by individualized background learning. Pattern Recognit., 102:107209. https://doi.org/10.1016/j.patcog.2020.107209
Dandapat, S., Ghosh, S., Si, S. and Datta, A. (2021). Analysis of diabetic retinopathy abnormalities detection techniques. Proceedings of International Conference on Frontiers in Computing and Systems. Advances in Intelligent Systems and Computing, vol 1255. Springer, Singapore, p. 235-247. https://doi.org/10.1007/978-981-15-7834-2_22
Decencière, E., Zhang, X., Gazuguel, G., Lay, B., Cochener, B., Trone, C., Gain, P., Ordonez, R., Massin, P., Erginay, A., Charton, B., and Klein, J.C. (2014). Feedback on a publicly distributed database: the Messidor database. Image Analysis & Stereology, 33(3):231-234. https://doi.org/10.5566/ias.1155
Ghosh, R., Ghosh, K., and Maitra, S. (2017). Automatic detection and classification of retinopathy stages using CNN, Proceedings of the 4th International Conference on Signal Processing and Integrated Networks (SPIN 2017), p. 550-554. https://doi.org/10.1109/SPIN.2017.8050011
Gonzalez, R.C., Woods, R.E., and Eddins, S.L. (2009). Digital Image Processing Using MATLAB. 2nd. ed. Gatesmark Publishing, United States, 827p.
Hemanth, J., Deperlioglu, O., and Kose, U. (2020). An enhanced diabetic retinopathy detection and classification approach using deep convolutional neural network. Neural Comput & Applic., 32:707-721. https://doi.org/10.1007/s00521-018-03974-0
Imani, E., Pourezza, H.R. and Banaee, T. (2015). Fully automated diabetic retinopathy screening using morphological component analysis. Computerized Medical Imaging and Graphics, 43:78-88. https://doi.org/10.1016/j.compmedimag.2015.03.004
James, J., Sharifahmadian, E., and Shih, L. (2018). Automatic severity level classification of diabetic retinopathy. International J. Comput. Appl., 180(12):30-35. https://doi.org/10.5120/ijca2018916244
Kandhasamy, J.P., Balamurali, S., Kadry, S., and Ramasamy, L.K. (2020). Diagnosis of diabetic retinopathy using multi level set segmentation algorithm with feature extraction using SVM with selective features. Multimed. Tools. Appl., 79:10,581-10,596.
Katada, Y., Ozawa, N., Masayoshi, K., Ofuji, Y., Tsubota, K., and Kurihara, T. (2020). Automatic screening for diabetic retinopathy in interracial fundus images using artificial intelligence. Intelligence-Based Medicine, 3-4:100024. https://doi.org/10.1016/j.ibmed.2020.100024
Li, Y.H., Yeh, N.N., Chen, S.J., and Chung, Y.C. (2019). Computer-assisted diagnosis for diabetic retinopathy based on fundus images using deep convolutional network. Mob. Inf. Syst., 2019:6143839. https://doi.org/10.1155/2019/6142839
Maher, R., Kayte, S., and Dhopeshwarkar, D.M. (2015). Review of automated detection for diabetes retinopathy using fundus images. Int. J. Adv. Res. Comput. Sci. Eng. Inf. Technol., 5(3):1,129-1,136.
Namgyal, J., and Schulz, E. (2022). A Novel Decision Method for Multiclass Twin Support Vector Machines by Average Distance. The First Annual meeting in Mathematics (AMM2022), p. 57-76.
Ramos-Soto, O., Rodríguez-Esparza, E., Balderas-Matta, S.E., Oliva, D., Hassanien, A.E., Meleppat, R.K., and Zawadzki R.J. (2021). An efficient retinal blood vessel segmentation in eye fundus images by using optimized top-hat and homomorphic filtering. Computer Methods and Programs in Biomedicine, 201:105949. https://doi.org/10.1016/j.cmpb.2021.105949
Sarki, R., Ahmed, K., Wang, H. and Zhang, Y. (2020). Automatic detection of diabetic eye disease through deep learning using fundus images: a survey. IEEE Access, 8: 151133-151148. https://doi.org/10.1109/ACCESS.2020.3015258
Welikala, R.A., Fraz, M.M., Dehmeshki, J., Hoppe, A., Tah, V., Mann, S., Williamson, T.H., and Barman, S.A. (2015). Genetic algorithm-based feature selection combined with dual classification for the automatic detection of proliferative diabetic retinopathy. Computerized Medical Imaging and Graphics, 43:64-77. https://doi.org/10.1016/j.compmedimag.2015.03.003
World Health Organization. (2015). TADDS: Tool for the Assessment of Diabetic Retinopathy and Diabetes Management Systems. Available from: https://apps.who.int/iris/rest/bitstreams/1242602/retrieve
