Diabetic retinopathy is the leading cause of blindness among diabetic patients. It occurs when the light-sensitive tissue in the retina is damaged. According to WHO statistics, the current global prevalence of diabetic retinopathy is approximately 103 million and is expected to be 161 million by 2045. The existing diagnosis methods are enriched with advanced retinal image processing and feature extraction techniques are frequently used to detect the presence of diabetic retinopathy in patients rather than focusing on early-stage detection. Therefore, detecting diabetic retinopathy at an early stage is crucial to prevent severe complications. The current study has explored the feasibility of identifying different stages of diabetic retinopathy using retinal images analyzed through deep learning algorithms. Labeled data corresponding to the five stages of diabetic retinopathy from the APTOS 2019 blindness detection dataset were preprocessed and a transfer learning approach was applied, utilizing pre-trained models from ImageNet for training. Among the transfer learning algorithms, the neural networks of ResNet_101, DenseNet_201 and EfficientNet_b0 were selected to train three DL models to select the optimal model based on test accuracy. The proposed method achieved a test accuracy of 91% using the fine-tuned EfficientNet_b0 model.

Keywords - Stages of Diabetic retinopathy, Deep learning, Training, Test accuracy, EfficientNet_b0

[1] S. A. Antar et al., “Diabetes mellitus: Classification, mediators, and complications; A gate to identify potential targets for the development of new effective treatments,” Biomed. Pharmacother., vol. 168, p. 115734, Dec. 2023, doi: 10.1016/j.biopha.2023.115734.

[2] T. Y. Wong and T.-E. Tan, “The diabetic retinopathy ‘pandemic’ and evolving global strategies: The 2023 Friedenwald Lecture,” Invest. Ophthalmol. Vis. Sci., vol. 64, no. 15, p. 47, Dec. 2023, doi: 10.1167/iovs.64.15.47.

[3] Karthik, Maggie, and S. Dane, “APTOS 2019 Blindness Detection,” Kaggle,2019.[Online].Available: https://www.kaggle.com/competitions/aptos2019-blindness-detection

[4] J. D. Bodapati et al., “Blended multi-modal deep ConvNet features for diabetic retinopathy severity prediction,” Electronics, vol. 9, no. 6, p. 914, May 2020, doi: 10.3390/electronics9060914.

[5] L. Qiao, Y. Zhu, and H. Zhou, “Diabetic retinopathy detection using prognosis of microaneurysm and early diagnosis system for non-proliferative diabetic retinopathy based on deep learning algorithms,” IEEE Access, vol. 8, pp. 104292–104302, 2020, doi: 10.1109/ACCESS.2020.2993937.

[6] R. Sarki, K. Ahmed, H. Wang, Y. Zhang, J. Ma, and K. Wang, “Image preprocessing in classification and identification of diabetic eye diseases,” Data Sci. Eng., vol. 6, no. 4, pp. 455–471, Dec. 2021, doi: 10.1007/s41019-021-00167-z.

[7] N. Tsiknakis et al., “Deep learning for diabetic retinopathy detection and classification based on fundus images: A review,” Comput. Biol. Med., vol. 135, p. 104599, Aug. 2021, doi: 10.1016/j.compbiomed.2021.104599.

[8] D. Mandl et al., “Learning lightprobes for mixed reality illumination,” in Proc. IEEE Int. Symp. Mixed Augment. Reality (ISMAR), Oct. 2017, pp. 82–89, doi: 10.1109/ISMAR.2017.25.

[9] “Models and pre-trained weights — Torchvision 0.17 documentation,” PyTorch,[Online].Available:https://pytorch.org/vision/stable/models.html#classification

[10] G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 2261–2269, doi: 10.1109/CVPR.2017.243.

[11] L. Wang, “EfficientNet — An elegant, powerful CNN,” Medium, Oct. 1, 2022. [Online]. Available: https://pub.towardsai.net/efficientnet-an-elegant-powerful-cnn-6e2a8d528ae3

[12] “What is epoch in machine learning?— UNext,” UNext, Nov. 24, 2022. [Online]. Available: https://u-next.com/blogs/machine-learning/epoch-in-machine-learning/

[13] “What is learning rate in machine learning? The full guide,” Deepchecks, May 27, 2024. [Online]. Available: https://www.deepchecks.com/glossary/learning-rate-in-machine-learning/

[14] A. Kumar, “Weight decay in machine learning: Concepts – Data Analytics,” Data Analytics, Jun. 7, 2022. [Online]. Available: https://vitalflux.com/weight-decay-in-machine-learning-concepts/

[15] D. Mandy, “Batch size in a neural network explained,” deeplizard.com. [Online].Available: https://deeplizard.com/learn/video/U4WB9p6ODjM