Design and Evaluation of a Convolutional Neural Network Model for Automated Detection of Diabetic Retinopathy Using Retinal Fundus Photographs
Keywords:
Diabetic retinopathy, convolutional neural network, fundus image, image classificationAbstract
Diabetic retinopathy (DR) is a leading cause of preventable blindness globally, necessitating timely and accurate screening methods. This study presents the design and evaluation of a custom convolutional neural network (CNN) model, LightDR, for automated classification of DR using retinal fundus photographs. The Augmented_resized_V2 dataset, derived from the Eyepacs, Aptos, and Messidor collections from Kaggle, was used to train over 143,000 labeled images. The LightDR architecture was built using TensorFlow and optimized through data augmentation, class balancing, and performance-driven callbacks. Evaluation of the model yielded an accuracy of 84%, with precision and recall metrics indicating strong sensitivity to disease presence and reliable classification of healthy cases. The model demonstrated generalization and interpretability, supported by Grad-CAM visualizations and confusion matrix analysis. These findings suggest that LightDR offers a scalable and effective solution for DR screening, with potential for integration into clinical workflows pending further validation.
References
[1] Z. L. Teo et al., "Global Prevalence of Diabetic Retinopathy and Projection of Burden through 2045: Systematic Review and Meta-analysis," Ophthalmology, vol. 128, no. 11, pp. 1580-1591, 2021/11/01/ 2021, doi: https://doi.org/10.1016/j.ophtha.2021.04.027.
[2] E. A. Lundeen et al., "Prevalence of Diabetic Retinopathy in the US in 2021," JAMA Ophthalmology, vol. 141, no. 8, pp. 747-754, 2023, doi: 10.1001/jamaophthalmol.2023.2289.
[3] K. Cai, Y.-P. Liu, and D. Wang, "Prevalence of diabetic retinopathy in patients with newly diagnosed type 2 diabetes: A systematic review and meta-analysis," Diabetes/Metabolism Research and Reviews, vol. 39, no. 1, p. e3586, 2023, doi: https://doi.org/10.1002/dmrr.3586.
[4] A. A. Yameny, "Diabetes Mellitus Overview 2024," Journal of Bioscience and Applied Research, vol. 10, no. 3, pp. 641-645, 2024, doi: 10.21608/jbaar.2024.382794.
[5] IDF. "Facts & figures." International Diabetes Federation. https://idf.org/about-diabetes/diabetes-facts-figures/ (accessed 10th October 2025, 2025).
[6] S. Albahli and G. N. Ahmad Hassan Yar, "Automated detection of diabetic retinopathy using custom convolutional neural network," Journal of X-Ray Science and Technology, vol. 30, no. 2, pp. 275-291, 2022, doi: 10.3233/xst-211073.
[7] P. O. Adigun, A. A. Adeniyi, and T. T. Oyekanmi, "Detection and Interpretation of X-Ray Scans for the Presence of Pneumonia Using Convolutional Neural Network," American Academic Scientific Research Journal for Engineering, Technology, and Sciences, Original vol. 101, no. 1, pp. 97-108, 2025. [Online]. Available: https://core.ac.uk/download/pdf/640473726.pdf. Yes.
[8] T. Oyekanmi, P. Adigun, A. Adeniyi, and N. A. Azeez, "Deep Learning-Based Diagnosis of Brain Cancer Using Convolutional Neural Networks On MRI Scans: A Comparative Study of Model Architectures and Tumor Classification Accuracy," American Scientific Research Journal for Engineering, Technology, and Sciences, vol. 103, pp. 147-163, 04/10 2025.
[9] K. Xu, D. Feng, and H. Mi, "Deep Convolutional Neural Network-Based Early Automated Detection of Diabetic Retinopathy Using Fundus Image," Molecules, vol. 22, no. 12, p. 2054, 2017. [Online]. Available: https://www.mdpi.com/1420-3049/22/12/2054.
[10] R. Gargeya and T. Leng, "Automated Identification of Diabetic Retinopathy Using Deep Learning," Ophthalmology, vol. 124, no. 7, pp. 962-969, 2017/07/01/ 2017, doi: https://doi.org/10.1016/j.ophtha.2017.02.008.
[11] M. M. Islam, H.-C. Yang, T. N. Poly, W.-S. Jian, and Y.-C. Li, "Deep learning algorithms for detection of diabetic retinopathy in retinal fundus photographs: A systematic review and meta-analysis," Computer Methods and Programs in Biomedicine, vol. 191, p. 105320, 2020/07/01/ 2020, doi: https://doi.org/10.1016/j.cmpb.2020.105320.
[12] Y.-H. Li, N.-N. Yeh, S.-J. Chen, and Y.-C. Chung, "Computer-Assisted Diagnosis for Diabetic Retinopathy Based on Fundus Images Using Deep Convolutional Neural Network," Mobile Information Systems, vol. 2019, no. 1, p. 6142839, 2019, doi: https://doi.org/10.1155/2019/6142839.
[13] K. Rama et al., "Convolutional Neural Networks for Automated Diagnosis of Diabetic Retinopathy in Fundus Images," Journal of Artificial Intelligence and Technology, vol. 3, no. 4, pp. 205-214, 08/24 2023, doi: 10.37965/jait.2023.0264.
[14] W. Zhang et al., "Automated identification and grading system of diabetic retinopathy using deep neural networks," Knowledge-Based Systems, vol. 175, pp. 12-25, 2019/07/01/ 2019, doi: https://doi.org/10.1016/j.knosys.2019.03.016.
[15] A. S. Canipek, M. Çakan, and A. Aktuğ. Eyepacs, Aptos, Messidor Diabetic Retinopathy [Online] Available: https://www.kaggle.com/datasets/ascanipek/eyepacs-aptos-messidor-diabetic-retinopathy
Downloads
Published
Issue
Section
License
Copyright (c) 2025 American Scientific Research Journal for Engineering, Technology, and Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who submit papers with this journal agree to the following terms.
