Retinal Disease Classification Using Deep CNN on Fundus Images
DOI:
https://doi.org/10.56313/jictas.v4i2.451Keywords:
Diabetic Retinopathy, Fundus Image, Deep Convolutional Neural Network, Grad-CAM, Medical Image ClassificationAbstract
Diabetic retinopathy (DR) is one of the primary causes of preventable blindness, highlighting the necessity for accurate and automated retinal screening systems. Manual diagnosis through fundus image inspection is time-consuming and prone to subjective interpretation, particularly in regions with limited access to ophthalmic specialists. This study presents a deep convolutional neural network (CNN) approach based on ResNet50 architecture with fine-tuning for multi-class classification of retinal diseases. The proposed model was developed using the APTOS 2019 Blindness Detection dataset, consisting of 3,662 fundus images categorized into five levels of DR severity. A robust preprocessing pipeline, including illumination correction, contrast enhancement, normalization, and extensive data augmentation, was implemented to improve image quality and balance the dataset. The network was trained using the Adam optimizer with a learning rate of 1×10?? and categorical cross-entropy loss for 30 epochs under an 80:20 train–validation split. Experimental evaluation demonstrated high performance with 92.4% accuracy, 0.91 precision, 0.92 recall, 0.91 F1-score, and an AUC of 0.95, outperforming baseline CNN and VGG16 models. Furthermore, Grad-CAM visualization confirmed that the model accurately localized critical retinal regions associated with microaneurysms, hemorrhages, and exudates, enhancing interpretability and clinical trust. The proposed ResNet50-based framework provides an explainable, efficient, and reliable solution for automated diabetic retinopathy detection, supporting large-scale tele-ophthalmology and early diagnosis applications in medical imaging
References
H. Jiang et al., “Roles of serum uric acid on the association between arsenic exposure and incident metabolic syndrome in an older Chinese population,” J. Environ. Sci. (China), vol. 147, 2025, doi: 10.1016/j.jes.2023.12.005.
H. OLLEIK and B. BLANCHI, “254-LB: EndoC-ßH5 Human Beta Cells—A Unique ‘Thaw and Go’ Model for Accelerating Diabetes Research with Highly Functional and Ready-to-Use Human Beta Cells,” Diabetes, vol. 71, no. Supplement_1, 2022, doi: 10.2337/db22-254-lb.
V. Nagar, A. Kumar Sahu, A. Upadhyay, and D. Patidar, “Madhumehw.s.r. to Type 2 Diabetes Mellitus-A Review,” Int. Res. J. Ayurveda Yoga, vol. 06, no. 05, 2023, doi: 10.47223/irjay.2023.6519.
J. Kesavadev, A. Basanth, and S. Kalra, “Unproven Therapies for Diabetes,” in The Diabetes Textbook: Clinical Principles, Patient Management and Public Health Issues, Second Edition, 2023. doi: 10.1007/978-3-031-25519-9_68.
P. H. Prastyo, A. S. Sumi, and A. Nuraini, “Optic Cup Segmentation using U-Net Architecture on Retinal Fundus Image,” JITCE (Journal Inf. Technol. Comput. Eng., vol. 4, no. 02, 2020, doi: 10.25077/jitce.4.02.105-109.2020.
S. Wang et al., “Performance of deep neural network-based artificial intelligence method in diabetic retinopathy screening: A systematic review and meta-analysis of diagnostic test accuracy,” 2020. doi: 10.1530/EJE-19-0968.
J. E. Widyaya and S. Budi, “Pengaruh Preprocessing Terhadap Klasifikasi Diabetic Retinopathy dengan Pendekatan Transfer Learning Convolutional Neural Network,” J. Tek. Inform. dan Sist. Inf., vol. 7, no. 1, 2021, doi: 10.28932/jutisi.v7i1.3327.
M. J. M. Zedan, M. A. Zulkifley, A. A. Ibrahim, A. M. Moubark, N. A. M. Kamari, and S. R. Abdani, “Automated Glaucoma Screening and Diagnosis Based on Retinal Fundus Images Using Deep Learning Approaches: A Comprehensive Review,” 2023. doi: 10.3390/diagnostics13132180.
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, 2020, doi: 10.1109/ACCESS.2020.2993937.
A. Dian Deva, F. Firdaus, S. Hasyim, B. Yanto, and R. Mai Candra, “Klasifikasi Prediksi Penyakit Paru-Paru Normal dengan Pneumonia berdasarkan Citra Image X-ray dengan Optimasi Adam Convolutional Neural Network (CNN),” Riau J. Comput. Sci., vol. 10, no. 2, pp. 146–155, 2024.
B. Yanto, B. -, J. -, and B. H. Hayadi, “Indentifikasi Pola Aksara Arab Melayu Dengan Jaringan Syaraf Tiruan Convolutional Neural Network (Cnn),” JSAI (Journal Sci. Appl. Informatics), vol. 3, no. 3, pp. 106–114, 2020, doi: 10.36085/jsai.v3i3.1151.
C. Ciller et al., “Automatic Segmentation of Retinoblastoma in Fundus Image Photography using Convolutional Neural Networks,” Invest. Ophthalmol. Vis. Sci., vol. 58, no. 8, 2017.
X. Wang et al., “Joint Learning of Multi-Level Tasks for Diabetic Retinopathy Grading on Low-Resolution Fundus Images,” IEEE J. Biomed. Heal. Informatics, vol. 26, no. 5, 2022, doi: 10.1109/JBHI.2021.3119519.
D. Raval and J. N. Undavia, “A Comprehensive assessment of Convolutional Neural Networks for skin and oral cancer detection using medical images,” Healthc. Anal., vol. 3, 2023, doi: 10.1016/j.health.2023.100199.
E. Prasiwiningrum and Adyanata Lubis, “Classification Of Palm Oil Maturity Using CNN (Convolution Neural Network) Modelling RestNet 50,” Decod. J. Pendidik. Teknol. Inf., vol. 4, no. 3, pp. 983–999, 2024, doi: 10.51454/decode.v4i3.822.
M. A. Mukti, A. T. Kurniawan, S. Bahri, N. Husin, B. Yanto, and F. Asmen, “Akurasi 12 Layer Convolutional Neural Network (CNN) Untuk Jenis Tumor Otak Dari Hasil Citra MRI Dengan Google Colab Dan Dataset Kaggle,” Riau J. Comput. Sci., vol. 10, no. 2, pp. 135–145, 2024.
B. Yanto, E. Rouza, L. Fimawahib, B. H. Hayadi, and R. R. Pratama, “Penerapan Algoritma Deep Learning Convolutional Neural Network Dalam Menentukan Kematangan Buah Jeruk Manis Berdasarkan Citra Red Green Blue (RGB),” J. Teknol. Inf. dan Ilmu Komput., vol. 10, no. 1, 2023, doi: 10.25126/jtiik.20231015695.
B. Yanto, L. Fimawahib, A. Supriyanto, B. H. Hayadi, and R. R. Pratama, “Klasifikasi Tekstur Kematangan Buah Jeruk Manis Berdasarkan Tingkat Kecerahan Warna dengan Metode Deep Learning Convolutional Neural Network,” INOVTEK Polbeng - Seri Inform., vol. 6, no. 2, 2021, doi: 10.35314/isi.v6i2.2104.
B. Citra, R. E. D. Green, and B. Rgb, “PENERAPAN ALGORITMA DEEP LEARNING CONVOLUTIONAL NEURAL NETWORK DALAM MENENTUKAN KEMATANGAN BUAH JERUK MANIS APPLICATION OF THE DEEP LEARNING CONVOLUTIONAL NEURAL NETWORK ALGORITHM IN DETERMINING THE MURABILITY OF SWEET ORANGE FRUIT BASED ON IMAGES RED GRE,” vol. 10, no. 1, pp. 59–66, 2023, doi: 10.25126/jtiik.2023105695.
B. Yanto, J. Jufri, A. Lubis, B. H. Hayadi, and E. Armita, NST, “Klarifikasi Kematangan Buah Nanas Dengan Ruang Warna Hue Saturation Intensity (Hsi),” INOVTEK Polbeng - Seri Inform., vol. 6, no. 1, p. 135, 2021, doi: 10.35314/isi.v6i1.1882.
H. Z. Yuan, K. H. Ghazali, A. Lubis, S. Sunardi, and B. Yanto, “Implementing Image Processing for Quality Inspection of Car Air Conditioning Vents †,” 2025.
E. Oktafanda, A. Lubis, and E. Prasiwiningrum, “Detection of Oil Palm Seedling Disease Based on Leaf Images Using the MobileNetV2-CNN Architecture,” Int. J. Informatics Comput., vol. 7, no. 1, p. 2025, 2025, doi: 10.35842/ijicom.
. A. Pratt, B. Coenen, D. M. Broadbent, S. P. Harding, and Y. Zheng, “Convolutional neural networks for diabetic retinopathy classification,” Procedia Computer Science, vol. 90, pp. 200–205, 2016, doi: 10.1016/j.procs.2016.07.014.
. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 770–778, 2016, doi: 10.1109/CVPR.2016.90.
. R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-CAM: Visual explanations from deep networks via gradient-based localization,” Proc. IEEE Int. Conf. Comput. Vis. (ICCV), pp. 618–626, 2017, doi: 10.1109/ICCV.2017.74.
. A.-O. Asia, C.-Z. Zhu, S. A. Althubiti, et al., “Detection of diabetic retinopathy in retinal fundus images using CNN classification models,” Electronics, vol. 11, no. 17, p. 2740, 2022, doi: 10.3390/electronics11172740.
. N. Rahim, A. Hanif, and S. Akram, “Transfer learning for diabetic retinopathy classification using VGG16 architecture,” Computers in Biology and Medicine, vol. 137, p. 104112, 2021, doi: 10.1016/j.compbiomed.2021.104112.
. Z. Liang, T. Chen, and M. Lin, “Fundus image classification using CNN and Vision Transformer hybrid model,” IEEE Transactions on Medical Imaging, vol. 43, no. 5, pp. 2011–2024, 2024, doi: 10.1109/TMI.2024.3340951.
. Y. Wang, Z. Zhou, and X. Chen, “Ensemble deep learning for diabetic retinopathy detection,” IEEE Access, vol. 11, pp. 21144–21157, 2023, doi: 10.1109/ACCESS.2023.3249142.
. M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” Proc. Int. Conf. Mach. Learn. (ICML), pp. 6105–6114, 2019, doi: 10.48550/arXiv.1905.11946.
. Kaggle, “APTOS 2019 Blindness Detection Dataset,” 2019. [Online]. Available: https://www.kaggle.com/competitions/aptos2019-blindness-detection.
. X. Zhou, J. Tang, and Y. Zhang, “Attention U-Net for automatic diabetic retinopathy classification,” Sensors, vol. 23, no. 1, p. 45, 2023, doi: 10.3390/s23010045.
. Y. Wang, M. Liu, and H. Zhang, “Explainable deep learning for ophthalmic disease classification,” Frontiers in Radiology, vol. 2, pp. 1–12, 2022, doi: 10.3389/fradi.2022.1003458.
. N. Rahim, M. R. Khan, and S. Akram, “Hybrid deep convolutional model for diabetic retinopathy grading using fundus images,” Biocybernetics and Biomedical Engineering, vol. 42, no. 3, pp. 881–894, 2022, doi: 10.1016/j.bbe.2022.04.006.
. R. R. K. Sharma, D. R. Joshi, and S. Y. Lee, “Explainable transfer learning approach for diabetic retinopathy classification using pre-trained CNNs,” IEEE Access, vol. 10, pp. 91104–91118, 2022, doi: 10.1109/ACCESS.2022.3204792.
. F. Chen, A. Zhang, and J. Liu, “Retinal disease identification using deep residual networks and data augmentation,” Computers and Electrical Engineering, vol. 110, p. 108831, 2023, doi: 10.1016/j.compeleceng.2023.10883.
. P. Xu, L. Wu, and T. Jiang, “Improving robustness of CNN-based diabetic retinopathy detection via noise-based data augmentation,” Applied Sciences, vol. 13, no. 6, p. 3589, 2023, doi: 10.3390/app13063589.
Published
How to Cite
Issue
Section
Copyright (c) 2025 Journal of ICT Aplications and System
This work is licensed under a Creative Commons Attribution 4.0 International License.
