Enhancing Eye Diseases Classification Using Imbalance Training & Machine Learning
DOI:
https://doi.org/10.30871/jaic.v9i4.10207Keywords:
Eye Disease Classification, XGBoost, LightGBM, SMOTEAbstract
This research aims to evaluate the effectiveness of various machine learning algorithms in classifying eye diseases based on retinal images. The dataset comprises four categories of eye diseases: Cataract, Diabetic Retinopathy, Glaucoma, and Normal. The feature extraction method employed a transfer learning approach using ResNet50, followed by SMOTE for data balancing, PCA for dimensionality reduction, and normalization for scaling data consistently. Eleven machine learning models were evaluated, including basic algorithms, ensemble methods, and neural networks. The evaluation utilized metrics such as accuracy, precision, recall, and F1-score. K-Fold Cross Validation is also employed to observe all models' generalisation. The results revealed that the XGBoost algorithm achieved the highest performance with an accuracy of 92.03%, followed by LightGBM 91.88% and MLP 91.50%. K-Fold Validation also improved the MLP performance, which achieved an average accuracy of 91.94% with a standard deviation of 0.0178. This study successfully enhanced classification accuracy compared to previous studies and shows significant potential for clinical applications in resource-limited environments.
Downloads
References
[1] M. J. Burton et al., “The Lancet Global Health Commission on Global Eye Health: vision beyond 2020,” Lancet Glob. Heal., vol. 9, no. 4, pp. e489–e551, 2021, doi: 10.1016/S2214-109X(20)30488-5.
[2] Y. Jeong, Y. J. Hong, and J. H. Han, “Review of Machine Learning Applications Using Retinal Fundus Images,” Diagnostics, vol. 12, no. 1, pp. 1–27, 2022, doi: 10.3390/diagnostics12010134.
[3] M. Moannaei et al., “Performance and limitation of machine learning algorithms for diabetic retinopathy screening and its application in health management: a meta-analysis,” Biomed. Eng. Online, vol. 24, no. 1, pp. 1–15, 2025, doi: 10.1186/s12938-025-01336-1.
[4] J. H. Wu, T. Y. A. Liu, W. T. Hsu, J. H. C. Ho, and C. C. Lee, “Performance and limitation of machine learning algorithms for diabetic retinopathy screening: Meta-analysis,” J. Med. Internet Res., vol. 23, no. 7, pp. 1–15, 2021, doi: 10.2196/23863.
[5] S. Muchuchuti and S. Viriri, “Retinal Disease Detection Using Deep Learning Techniques: A Comprehensive Review,” J. Imaging, vol. 9, no. 4, 2023, doi: 10.3390/jimaging9040084.
[6] Z. Li, M. Xu, X. Yang, and Y. Han, “Multi-Label Fundus Image Classification Using Attention Mechanisms and Feature Fusion,” Micromachines, vol. 13, no. 6, 2022, doi: 10.3390/mi13060947.
[7] C. Patrício, J. C. Neves, and L. F. Teixeira, “Explainable Deep Learning Methods in Medical Image Classification: A Survey,” ACM Comput. Surv., vol. 56, no. 4, pp. 1–39, 2023, doi: 10.1145/3625287.
[8] Z. Salahuddin, H. C. Woodruff, A. Chatterjee, and P. Lambin, “Transparency of deep neural networks for medical image analysis: A review of interpretability methods,” Comput. Biol. Med., vol. 140, pp. 1–24, 2022, doi: 10.1016/j.compbiomed.2021.105111.
[9] M. Avanzo, J. Stancanello, G. Pirrone, A. Drigo, and A. Retico, “The Evolution of Artificial Intelligence in Medical Imaging : From Computer Science to Machine and Deep Learning,” Cancers (Basel)., vol. 16, no. 21, pp. 1–23, 2024.
[10] T. Sundeep, U. Divyasree, K. Tejaswi, U. R. Vinithanjali, and A. K. Kumar, “Feature Extraction of Ophthalmic Images Using Deep Learning and Machine Learning Algorithms †,” Eng. Proc., vol. 56, no. 1, 2023, doi: 10.3390/ASEC2023-15231.
[11] F. T. A. Sayyidul Laily, “Feature Extraction and Classification of Retinal Images Using Sobel Segmentation and Linear SVC,” Int. J. Artif. Intell. Med. Issues, vol. 2, no. 2, pp. 136–149, 2024, doi: 10.56705/ijaimi.v2i2.153.
[12] K. He, “Deep Residual Learning for Image Recognition,” IEEE Conf. Comput. Vis. pattern Recognit., pp. 770–778, 2016.
[13] M. A. Fikri, “Improving Osteosarcoma Detection through SMOTE-Driven Machine Learning Approaches,” IJID (International J. Informatics Dev., vol. 13, no. 2, pp. 517–529, 2025, doi: 10.14421/ijid.2024.4890.
[14] I. T. Jolliffe, J. Cadima, and J. Cadima, “Principal component analysis : a review and recent developments Subject Areas : Author for correspondence :,” 2016.
[15] S. G. K. Patro and K. K. sahu, “Normalization: A Preprocessing Stage,” Iarjset, pp. 20–22, 2015, doi: 10.17148/iarjset.2015.2305.
[16] G. Ramanathan, D. Chakrabarti, A. Patil, S. Rishipathak, and S. Kharche, “Eye Disease Detection Using Machine Learning,” 2021 2nd Glob. Conf. Adv. Technol. GCAT 2021, pp. 1–5, 2021, doi: 10.1109/GCAT52182.2021.9587740.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Muhammad Azrul Ihwan, Ajie Kusuma Wardhana
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
