Enhancing Eye Disease Classification Accuracy Using Convolutional Neural Networks with Transfer Learning


Nazlina Izmi Addyna(1*); Rahmat Widia Sembiring(2); Agus Perdana Windarto(3);

(1) STIKOM Tunas Bangsa
(2) Politeknik Negeri Medan
(3) STIKOM Tunas Bangsa
(*) Corresponding Author

  

Abstract


Eye diseases serve as a primary contributor to global blindness, making early detection a critical determinant in effective treatment outcomes. While retinal fundus image analysis is the diagnostic standard, conventional manual methods are often hindered by observer subjectivity and time inefficiencies. This study aims to optimize eye disease classification using a Convolutional Neural Network (CNN) approach empowered by transfer learning techniques. Utilizing a dataset of 1,200 retinal fundus images sourced from Kaggle, this research classifies four categories: normal, glaucoma, cataract, and diabetic retinopathy. To mitigate the challenge of limited labeled medical datasets, specific data augmentation strategies—including random flip, zoom, and contrast adjustments—were applied. The study conducts a comparative evaluation of three architectures: standard VGG16, baseline MobileNet, and a proposed optimized MobileNet. The proposed method utilizes Random Search to systematically optimize hyperparameters such as learning rates, dense layer units, and dropout rates. Experimental results demonstrate that the optimized MobileNet achieved superior performance with 89.17% accuracy, significantly outperforming the VGG16 baseline 82,00% and baseline MobileNet 85,00%. Notably, the model achieved perfect recall for diabetic retinopathy, although glaucoma remained the most challenging class due to subtle morphological similarities with normal eyes. These findings confirm that integrating lightweight CNNs with appropriate transfer learning yields a diagnostic system that is not only accurate but also efficient for deployment in resource-constrained environments

Keywords


CNN; Eye Disease Classification; MobileNet; VGG16; Transfer Learning

  
  

Full Text:

PDF
  

Article Metrics

Abstract view: 92 times
PDF view: 19 times 		     

Digital Object Identifier

doi  https://doi.org/10.33096/ilkom.v18i1.2886.195-206 		  

Cite

How to cite item

References


T. Bonsaksen, A. Brunes, and T. Heir, “Quality of life in people with visual impairment compared with the general population,” J. Public Heal., vol. 33, no. 1, pp. 23–31, 2025, doi: 10.1007/s10389-023-01995-1.

X. Han, W. Cheng, and L. Liang, “· Editorial Global eye health : challenges , innovations , and future prospects,” pp. 97–98, 2025, doi: 10.12419/es2025010101.

A. Almazroa et al., “The Patients’ Perspective for the Impact of Late Detection of Ocular Diseases on Quality of Life: A Cross-Sectional Study,” Clin. Optom., vol. 15, pp. 191–204, 2023, doi: 10.2147/OPTO.S422451.

S. F. Ahmed et al., Deep learning modelling techniques: current progress, applications, advantages, and challenges, vol. 56, no. 11. Springer Netherlands, 2023. doi: 10.1007/s10462-023-10466-8.

O. Goktas, “Factors associated with eye disorders and diseases : A retrospective study,” Pakistan J. Med. Sci., vol. 41, no. 1, pp. 176–181, 2025.

T. Y. Wong, S. C. Loon, and S. M. Saw, “The epidemiology of age related eye diseases in Asia,” Br. J. Ophthalmol., vol. 90, no. 4, pp. 506–511, 2006, doi: 10.1136/bjo.2005.083733.

R. Kesuma and A. Prasetyo, Literature Review on the Prevalence of Vision Impairment and Age-Related Eye Diseases, no. Bishss 2023. Atlantis Press SARL, 2024. doi: 10.2991/978-2-38476-273-6_111.

I. Kulkov et al., “Technology entrepreneurship in healthcare: Challenges and opportunities for value creation,” J. Innov. Knowl., vol. 8, no. 2, p. 100365, 2023, doi: 10.1016/j.jik.2023.100365.

G. Więckiewicz, S. Weber, I. Florczyk, and P. Gorczyca, “Socioeconomic Burden of Psychiatric Cancer Patients: A Narrative Review,” Cancers (Basel)., vol. 16, no. 6, 2024, doi: 10.3390/cancers16061108.

J. Sheppard, B. S. Lee, L. M. Periman, J. Sheppard, B. S. Lee, and L. M. Periman, “Dry eye disease : identification and therapeutic strategies for primary care clinicians and clinical specialists,” Ann. Med., vol. 55, no. 1, pp. 241–252, 2023, doi: 10.1080/07853890.2022.2157477.

S. Iqbal, A. N. Qureshi, J. Li, and T. Mahmood, “On the analyses of medical images using traditional machine learning techniques and convolutional neural networks,” 2023, Springer. doi: 10.1007/s11831-023-09899-9.

E. Hassan, S. Elmougy, M. R. Ibraheem, M. S. Hossain, and ..., “Enhanced deep learning model for classification of retinal optical coherence tomography images,” 2023, mdpi.com.

U. P. S. Parmar et al., “Artificial Intelligence (AI) for Early Diagnosis of Retinal Diseases,” Med., vol. 60, no. 4, pp. 1–15, 2024, doi: 10.3390/medicina60040527.

T. Ahad, Y. Li, B. Song, and T. Bhuiyan, “Arti fi cial Intelligence in Agriculture Comparison of CNN-based deep learning architectures for rice diseases classi fi cation,” Artif. Intell. Agric., vol. 9, pp. 22–35, 2023, doi: 10.1016/j.aiia.2023.07.001.

L. Alzubaidi et al., Review of deep learning: concepts, CNN architectures, challenges, applications, future directions, vol. 8, no. 1. Springer International Publishing, 2021. doi: 10.1186/s40537-021-00444-8.

G. S. Nugraha, M. I. Darmawan, and ..., “Comparison of CNN’s architecture GoogleNet, AlexNet, VGG-16, Lenet-5, Resnet-50 in Arabic handwriting pattern recognition,” … Electron. Control, 2023.

S. Jamshidiha, A. Rezaee, F. Hajati, M. Golzan, and R. Chiong, “An Explainable Transformer Model for Alzheimer’s Disease Detection Using Retinal Imaging,” no. Ml, pp. 1–20, 2025.

M. A. K. Raiaan et al., “A systematic review of hyperparameter optimization techniques in Convolutional Neural Networks,” Decis. Anal. J., vol. 11, no. September 2023, p. 100470, 2024, doi: 10.1016/j.dajour.2024.100470.

B. Tymchenko, P. Marchenko, and D. Spodarets, “Deep Learning Approach to Diabetic Retinopathy Detection,” Int. Conf. Pattern Recognit. Appl. Methods, vol. 1, pp. 501–509, 2020, doi: 10.5220/0008970805010509.

J. Debnath et al., “Informatics in Medicine Unlocked LMVT : A hybrid vision transformer with attention mechanisms for efficient and explainable lung cancer diagnosis,” Informatics Med. Unlocked, vol. 57, no. June, p. 101669, 2025, doi: 10.1016/j.imu.2025.101669.

D. B. Olawade, S. Chinaza, S. Marinze, E. Egbon, A. Osunmakinde, and A. Osborne, “International Journal of Medical Informatics Artificial intelligence in clinical trials : A comprehensive review of opportunities , challenges , and future directions,” Int. J. Med. Inform., vol. 206, no. October 2025, p. 106141, 2026, doi: 10.1016/j.ijmedinf.2025.106141.

A. Choi et al., “OPEN A novel deep learning algorithm for real-time prediction of clinical deterioration in the emergency department for a multimodal clinical decision support system,” pp. 1–15, 2024.

S. Morelli and D. Giansanti, “Recent Advances in AI-Driven Mobile Health Enhancing Healthcare — Narrative Insights into Latest Progress,” pp. 1–80, 2026.

M. P. Singh et al., “OPEN ACCESS A Healthcare System Employing Lightweight CNN for Disease Prediction with Artificial Intelligence,” pp. 1–13, 2024, doi: 10.2174/0118749445302023240520111802.

A. A. Abdulamiery, L. M. Shaker, and A. Alamiery, “Synergizing technology and optics : Exploring the wonders of bioelectronics contact lenses,” Next Mater., vol. 10, no. December 2024, p. 101399, 2026, doi: 10.1016/j.nxmate.2025.101399.

C. A. Putri and S. Rakasiwi, “Edumatic : Jurnal Pendidikan Informatika Diagnosis Dini Penyakit Mata : Klasifikasi Citra Fundus Retina dengan Convolutional Neural Network VGG-16,” J. Pendidik. Inform., vol. 9, no. 1, pp. 208–216, 2025, doi: 10.29408/edumatic.v9i1.29571.

G. An, M. Akiba, K. Omodaka, T. Nakazawa, and H. Yokota, “Hierarchical deep learning models using transfer learning for disease detection and classification based on small number of medical images,” Sci. Rep., vol. 11, no. 1, pp. 1–9, 2021, doi: 10.1038/s41598-021-83503-7.

R. Sarki, K. Ahmed, H. Wang, Y. Zhang, and K. Wang, “Convolutional Neural Network for Multi-class Classification of Diabetic Eye Disease,” EAI Endorsed Trans. Scalable Inf. Syst., vol. 9, no. 4, 2022, doi: 10.4108/eai.16-12-2021.172436.

T. Kee and W. K. O. Ho, “Optimizing Machine Learning Models for Urban Sciences : A Comparative Analysis of Hyperparameter Tuning Methods,” 2025.

M. Sholeh, U. Lestari, and D. Andayati, “Hyperparameter Optimization Using Grid Search and Random Search to Improve the Performance of Prediction Models with Decision Trees,” vol. 3, no. 03, pp. 453–464, 2025.

S. K. Parinduri, P. Alkhairi, and H. Qurniawan, “Classification Model Optimization using Grid Search and Random Search in Machine Learning Algorithms,” vol. 4, no. 2, pp. 71–78, 2025, doi: 10.61944/bids.v4i2.136.

R. Pannu et al., “Computerized Medical Imaging and Graphics Enhanced glaucoma classification through advanced segmentation by integrating cup-to-disc ratio and neuro-retinal rim features,” Comput. Med. Imaging Graph., vol. 123, no. January, p. 102559, 2025, doi: 10.1016/j.compmedimag.2025.102559.


Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Nazlina Izmi Addyna, Rahmat Widia Sembiring, Agus Perdana Windarto

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.