Deep Learning of Diabetic Retinopathy Classification in Fundus Images
Main Article Content
Abstract
Diabetic retinopathy is an eye disease in diabetic patients due to damage to the small blood vessels in the retina due to high and low blood sugar levels. Accurate detection and classification of Diabetic Retinopathy is an important task in computer-aided diagnosis, especially when planning for diabetic retinopathy surgery. Therefore, this study aims to design an automated model based on deep learning, which helps ophthalmologists detect and classify diabetic retinopathy severity through fundus images. In this work, a deep convolutional neural network (CNN) with transfer learning and fine tunes has been proposed by using pre-trained networks known as Residual Network-50 (ResNet-50). The overall framework of the proposed classification model is divided into three major phases, including pre-processing, training the Resnet-50 network, and classification with evaluation. In the first phase, pre-processing techniques are applied to the APTOS2019 fundus images dataset to find the best features and highlight some fine details of these images. The resnet-50 network was trained in the second phase using the training set and saved the best model obtained that gives high accuracy during the training process. Finally, this saved model has been implemented on the testing dataset for classification DR grades. The proposed model shows good and best classification performance, which was obtained with an accuracy of 98.3%, a precision of 98.4%, an F1-Score of 98.5 % and the recall of 98.4%.
Article received: 12/03/2023
Article accepted: 13/04/2023
Article published: 01/12/2023
Article Details
How to Cite
Publication Dates
References
Albayati, A.Q., Al-Araj I, A.S., and Ameen , S.H., 2020. Arabic Sentiment Analysis (ASA) Using Deep Learning Approach. Journal of Engineering, 26(6), pp. 85-93. Doi:10.31026/j.eng.2020.06.07
Ahmed, H. A., and Mohammed, E. A., 2022. Detection and Classification of the Osteoarthritis in Knee Joint Using Transfer Learning with Convolutional Neural Networks (CNNs). Iraqi Journal of Science, 63(11), pp. 5058–5071. Doi:10.24996/ijs.2022.63.11.40
Ali, A. A., Abd, F., and Dawood, A., 2022. Diabetic retinopathy detection and classification based on deep learning: A review. Int. J. Nonlinear Anal. Appl, 13, pp. 2008–6822. Doi:10.22075/ijnaa.2022.28174.3823
Ali, N.H., Abdulmunem, M.E., and Ali, A.E., 2021. Learning Evolution: A Survey. Iraqi Journal of Science, 62(12), pp. 4978–4987. Doi:10.24996/ijs.2021.62.12.34
Asiri, N., Hussain, M., Al Adel, F., and Alzaidi, N., 2019. Deep learning based computer-aided diagnosis systems for diabetic retinopathy: A survey. Artificial Intelligence in Medicine, 99. Doi:10.1016/j.artmed.2019.07.009
Abuqadumah, M.M., Ali, M.A., and Al-Nima, R.R., 2020, February. Personal authentication application using deep learning neural network. In 2020 16th IEEE International Colloquium on Signal Processing & Its Applications (CSPA) (pp. 186-190). Doi:10.1109/CSPA48992.2020.9068706.
Al-Bayati, A.Q., Al-Araji, A.S., and Ameen, S.H., 2020. Arabic sentiment analysis (ASA) using deep learning approach. Journal of Engineering, 26(6), pp. 85-93. Doi: 10.31026/j.eng.2020.06.07.
Alfarhany, A.A.R., and Abdullah, N.A., 2023. Iraqi Sentiment and Emotion Analysis Using Deep Learning. Journal of Engineering, 29(09), pp. 150-165. Doi: 10.31026/j.eng.2023.09.11.
Altaf, F., Islam, S.M., Akhtar, N., and Janjua, N.K., 2019. Going deep in medical image analysis: concepts, methods, challenges, and future directions. IEEE Access, 7, pp. 99540-99572. Doi:10.1109/ACCESS.2019.2929365
Balafar, M., 2012. Review of noise reducing algorithms for brain MRI images. Methods, 10, p.11.
Balafar, M. A., 2012. Review of noise reducing algorithms for brain MRI images. International Journal on Technical and Physical Problems of Engineering (IJTPE), 13, pp. 54–59.
Chaturvedi, S.S., Gupta, K., Ninawe, V., and Prasad, P.S., 2020. Automated diabetic retinopathy grading using deep convolutional neural network. arXiv preprint arXiv:2004.06334. Doi:10.48550/arXiv.2004.06334
Doshi, D., Shenoy, A., and Sidhpura, D., 2016. Diabetic retinopathy detection using deep convolutional neural network. International Conference on Computing, Analytics and Security Trends (CAST), 19-21 Dec., Pune, India. Doi:10.1109/CAST.2016.7914977
Elswah, D.K., Elnakib, A.A., and Moustafa, H.E., 2020. Automated diabetic retinopathy grading using resnet. 2020 37th National Radio Science Conference (NRSC), pp. 248–254. Doi:10.1109/NRSC49500.2020.9235098
Ghadi, N.M., and Salman, N.H., 2022. Deep learning-based segmentation and classification techniques for brain tumor mri: a review. Journal of Engineering, 28(12), pp. 93–112. Doi:10.31026/j.eng.2022.12.07
Ghosh, R., Ghosh, K., and Maitra, S., 2017. Automatic Detection and Classification of Diabetic Retinopathy stages using CNN. 2017 4th International Conference on Signal Processing and Integrated Networks (SPIN), pp. 550–554. https://www.kaggle.com/c/diabetic-retinopathy-detection/data
Hssayni, E.H., and Ettaouil, M., 2021. Generalization ability augmentation and regularization of deep convolutional neural networks using l 1/2 pooling. International Journal on Technical and Physical Problems of Engineering, 13(48), pp. 1–6. www.iotpe.com
He, K., Zhang, X., Ren, S., and Sun, J., 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
Hameed, R.A., 2021. The intelligent auto-tuning controller design based on dolphin echo location for blood glucose monitoring system. Journal of Engineering, 27(8), pp. 1–18. Doi:10.31026/j.eng.2021.08.01.
Islam, Md. R., Hasn, Md. A.M., and Sayeed, A., 2020. Transfer learning based diabetic retinopathy detection with a novel preprocessed layer. 2020 IEEE Region 10 Symposium (TENSYMP), pp. 888–891.
Jenkins, A.J., Joglekar, M.V., Hardikar, A.A., Keech, A.C., O’Neal, D.N., and Januszewski, A.S., 2015. Biomarkers in diabetic retinopathy. Review of Diabetic Studies, 12(1–2), pp. 159–195. Doi:10.1900/RDS.2015.12.159
Jabbar, M.A., and Radhi, A.M., 2022. Diagnosis of malaria infected blood cell digital images using deep convolutional neural networks. Iraqi Journal of Science, pp. 380-396. LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." nature 521.7553 (2015), pp. 436-444.
Kwasigroch, A., Jarzembinski, B., and Grochowski, M., 2018, May. Deep CNN based decision support system for detection and assessing the stage of diabetic retinopathy. In 2018 International Interdisciplinary PhD Workshop (IIPhDW), pp. 111-116.
Mateen, M., Wen, J., Nasrullah, N., Sun, S., and Hayat, S., 2020. Exudate detection for diabetic retinopathy using pretrained convolutional neural networks. Complexity, 2020, pp.1-11.
Nasser, E.S., and Dawood, F.A.A., 2021. Diagnosis and classification of type II diabetes based on multilayer neural network. Iraqi Journal of Science, 62(10), pp. 3744–3758. Doi:10.24996/ijs.2021.62.10.33
Pradhan, A., Sarma, B., Nath, R.K., Das, A., and Chakraborty, A., 2020. Diabetic Retinopathy Detection on Retinal Fundus Images Using Convolutional Neural Network. Communications in Computer and Information Science, 1240 CCIS, pp. 254–266. Doi:10.1007/978-981-15-6315-7_21
Reza, A.M., 2004. Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement. Journal of VLSI signal processing systems for signal, image and video technology, 38, pp. 35-44.
Rawat, V., and Suryakant., 2019. A classification system for diabetic patients with machine learning techniques. International Journal of Mathematical, Engineering and Management Sciences, 4(3), pp. 729–744. Doi:10.33889/IJMEMS.2019.4.3-057
Salvi, R.S., Labhsetwar, S.R., Kolte, P.A., Venkatesh, V. S., and Baretto, A. M., 2021. Predictive analysis of diabetic retinopathy with transfer learning. 2021 International Conference on Nascent Technologies in Engineering, ICNET 2021 - Proceedings. Doi:10.1109/ICNTE51185.2021.9487789
Swathi, C., Anoop, B. K., Dhas, D., A.S., and Sanker, S.P., 2017. Comparison of different image preprocessing methods used for retinal fundus images. 2017 Conference on Emerging Devices and Smart Systems (ICEDSS), pp. 175–179.
Thenmozhi, K., and Reddy, U.S., 2019. Crop pest classification based on deep convolutional neural network and transfer learning. Computers and Electronics in Agriculture, 164, P. 104906., Doi:10.1016/j.compag.2019.104906.
Wan, S., Liang, Y., and Zhang, Y., 2018. Deep convolutional neural networks for diabetic retinopathy detection by image classification. Computers and Electrical Engineering, 72, 274–282. Doi:10.1016/j.compeleceng.2018.07.042
Wilkinson, C. P., Ferris, F. L., Klein, R. E., Lee, P. P., Agardh, C. D., Davis, M., Dills, D., Kampik, A., Pararajasegaram, R., Verdaguer, J. T., and Lum, F., 2003. Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales. Ophthalmology, 110(9), pp. 1677–1682. Doi:10.1016/S0161-6420(03)00475-5
Wu, B., Zhu, W., Shi, F., Zhu, S., and Chen, X., 2017. Automatic detection of microaneurysms in retinal fundus images. Computerized Medical Imaging and Graphics, 55, pp. 106–112. Doi:10.1016/j.compmedimag.2016.08.001
Zareena Hassanbee, M.S.A., 2021. Effective Contrast Enhancement techniques for Fundus images. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(11), pp.6937-6943.