COMPARATIVE STUDY OF CNN-BASED ARCHITECTURES ON EYE DISEASES CLASSIFICATION USING FUNDUS IMAGES TO AID OPHTHALMOLOGIST
Abstract
Eye health has a significant impact on quality of life, with more than 2.2 billion people experiencing vision problems. Many of these cases can be prevented or treated. The use of AI for eye disease classification helps healthcare professionals provide optimal care. However, the complexity of fundus images challenges classification performance. This study examines various Convolutional Neural Network (CNN) architectures using Transfer Learning and Adam optimization. Fundus images are processed using CLAHE (clip limit and grid size) and the Wiener filter (size) to enhance contrast and reduce noise. Afterward, ResNet-152, EfficientNet, MobileNetV1, and DenseNet-121 are tested to identify the most effective model. The study aims to determine the optimal CNN architecture for eye disease classification, assisting ophthalmologists in diagnosing eye diseases through fundus images. The best CNN model, ResNet-152, achieved an accuracy of 94.82%, outperforming other models by 3.95 - 8.29%.
Downloads
References
WHO, "Blindness and vision impairment," 2023. https://www.who.int/news-room/fact-sheets/detail/blindness-and-visual-impairment (accessed June. 15, 2024).
M. J. Burton, J. Ramke, A. P. Marques, R. R. A. Bourne, N. Congdon, I. Jones, B. A. M. Ah Tong, S. Arunga, D. Bachani, C. Bascaran, A. Bastawrous, K. Blanchet, T. Braithwaite, J. C. Buchan, J. Cairns, A. Cama, M. Chagunda, C. Chuluunkhuu, A. Cooper, ... H. B. Faal, "The Lancet Global Health Commission on Global Eye Health: vision beyond 2020," The Lancet Global Health, vol. 9, no. 4, 2021. https://doi.org/10.1016/S2214-109X(20)30488-5.
A. R. W. Sait, "Artificial Intelligence-Driven Eye Diseases Classification Model," Multidisciplinary Digital Publishing Institute (MDPI), vol. 13, no. 20, 2023. https://doi.org/10.3390/app132011437.
D. Nagpal, N. Alsubaie, B. O. Soufiene, M. S. Alqahtani, M. Abbas, and H. M. Almohiy, "Automatic Detection of Diabetic Hypertensive Retinopathy in Fundus Images Using Transfer Learning," Applied Sciences (Switzerland), vol. 13, no. 8, 2023. https://doi.org/10.3390/app13084695.
C. Guo, M. Yu, and J. Li, "Prediction of different eye diseases based on fundus photography via deep transfer learning," J. Clin. Med., vol. 10, no. 23, 2021. https://doi.org/10.3390/jcm10235481.
M. Juneja, S. Singh, N. Agarwal, S. Bali, S. Gupta, N. Thakur, and P. Jindal, "Automated detection of Glaucoma using deep learning convolution network (G-net)," Multimedia Tools and Applications, vol. 79, no. 21-22, 2020. https://doi.org/10.1007/s11042-019-7460-4.
Y. N. Fuadah, I. D. Ubaidullah, N. Ibrahim, F. F. Taliningsing, N. K. Sy, and M. A. Pramuditho, "Optimasi Convolutional Neural Network dan K-Fold Cross Validation pada Sistem Klasifikasi Glaukoma," ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika, vol. 10, no. 3, 2022. https://doi.org/10.26760/elkomika.v10i3.728
Z. Arif, R. Y. Nur Fu’adah, S. Rizal, and D. Ilhamdi, "Classification of eye diseases in fundus images using Convolutional Neural Network (CNN) method with EfficientNet architecture," JRTI (Jurnal Riset Tindakan Indonesia), vol. 8, no. 1, 2023. https://doi.org/10.29210/30032835000.
K. Saputra, et al., "Penerapan Algoritma Convolution Neural Network untuk Menentukan Retinopati Hipertensi Melalui Citra Retina Fundus," Jurnal Penelitian Teknik Informatika Universitas Prima Indonesia (UNPRI) Medan, vol. 6, no. 2, pp. 143-149, Oct. 2023. https://doi.org/10.34012/jutikomp.v6i2.4307
J. Wang, L. Yang, Z. Huo, W. He, and J. Luo, "Multi-Label Classification of Fundus Images with EfficientNet," IEEE Access, vol. 8, pp. 212499-212508, 2020. doi: 10.1109/ACCESS.2020.3040275
H. Li, Z. Yue, J. Liu, Y. Wang, H. Cai, K. Cui, and X. Chen, "Sccdnet: A pixel-level crack segmentation network," Appl. Sci., vol. 11, no. 11, 2021. doi: 10.3390/app11115074.
B. Jiang, N. Li, X. Cui, et al., "Research on facial expression recognition algorithm based on improved MobileNetV3," J. Image Video Process., vol. 2024, no. 22, 2024. doi: 10.1186/s13640-024-00638-z.
A. Wanto, Y. Yuhandri, and O. Okfalisa, "Optimization Accuracy of CNN Model by Utilizing CLAHE Parameters in Image Classification Problems," in Proceedings - 2023 International Conference on Networking, Electrical Engineering, Computer Science, and Technology, IConNECT 2023, 2023. https://doi.org/10.1109/IConNECT56593.2023.10327100.
K. Aurangzeb, S. Aslam, M. Alhussein, R. A. Naqvi, M. Arsalan, and S. I. Haider, "Contrast Enhancement of Fundus Images by Employing Modified PSO for Improving the Performance of Deep Learning Models," IEEE Access, vol. 9, pp. 55253-55264, 2021. doi: 10.1109/ACCESS.2021.3068477.
A. Hosna, E. Merry, J. Gyalmo, Z. Alom, Z. Aung, and M. A. Azim, "Transfer Learning: A Friendly Introduction," Journal of Big Data, vol. 9, no. 102, 2022. doi: 10.1186/s40537-022-00652-w.
M. D. A. Putra, T. S. Winanto, R. Hendrowati, A. Primajaya, and F. D. Adhinata, "A Comparative Analysis of Transfer Learning Architecture Performance on Convolutional Neural Network Models with Diverse Datasets," Komputika: Jurnal Sistem Komputer, vol. 12, no. 1, 2023. doi: 10.34010/komputika.v12i1.8626.
T. Babaqi, M. Jaradat, A. E. Yildirim, S. Al-Nimer, and D. Won, "Eye Disease Classification Using Deep Learning Techniques," in IISE Annual Conference and Expo 2023, 2023. doi: 10.21872/2023IISE_1944.
U. Bhimavarapu and G. Battineni, "Deep Learning for the Detection and Classification of Diabetic Retinopathy with an Improved Activation Function," Healthcare (Switzerland), vol. 11, no. 1, 2023. doi: 10.3390/healthcare11010097.
G. V. Doddi, "Eye Diseases Classification Dataset," 2022. https://www.kaggle.com/datasets/gunavenkatdoddi/eye-diseases-classification (accessed June. 10, 2024).
Copyright (c) 2025 Evelyn Callista Yaurentius, Theresia Ratih Dewi Saputri, Evan Tanuwijaya, Richard Evan Sutanto
This work is licensed under a Creative Commons Attribution 4.0 International License.
