A Comparative Analysis of Convolutional Neural Networks for Automated Myopia Classification via Fundus Imaging

Manuel J. Ibarra-Carrera; Danny Noe Cuaquira-Huachaca

Authors

Manuel J. Ibarra-Carrera Universidad Nacional Micaela Bastidas de Apurimac Author https://orcid.org/0000-0001-6711-4916
Danny Noe Cuaquira Huachaca Universidad Nacional Micaela Bastidas de Apurimac Author https://orcid.org/0009-0009-0717-6766

Keywords:

Myopia, Convolutional Neural Network, Fundus Imagery, Deep Learning

Abstract

According to recent reports from the World Health Organization (WHO), myopia now affects 30% of the global population and continues to rise steadily. Given that early detection is critical for timely and effective treatment. This study evaluates and compares the performance of two prominent convolutional neural network (CNN) architectures—ResNet50 and InceptionV3—for the automated classification of myopia using blue-light fundus imagery. Employing a cross-sectional, non-experimental design, the research utilized a large-scale dataset of 124,794 images (63,294 Myopia; 61,500 Normal). The data were partitioned into training (70%), validation (20%), and testing (10%) sets. Models were implemented in Python using TensorFlow and Keras, leveraging the Google Colab Pro environment with A100 GPU acceleration. To mitigate overfitting and enhance generalization, rigorous preprocessing and data augmentation techniques were applied. Experimental results indicate that both architectures achieved exceptional performance; notably, InceptionV3 outperformed ResNet50, achieving a validation accuracy of 99.97% and a significantly lower loss of 0.0075. These results confirm the robustness of deep learning models for clinical myopia screening in response to the growing global prevalence.

References

Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D. G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., … Xiao, Y. (2016, November 2–4). TensorFlow: A system for large-scale machine learning [Paper presentation]. 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), Savannah, GA, United States, 265–283. https://www.usenix.org/conference/osdi16/technical-sessions/presentation/abadi

Bisong, E. (2019). Building machine learning and deep learning models on Google Cloud Platform: A comprehensive guide for beginners. Apress. https://doi.org/10.1007/978-1-4842-4470-8

Cahya, F. N., Hardi, N., Riana, D. & Hadianti, S. (2021). Klasifikasi penyakit mata menggunakan convolutional neural network (CNN). SISTEMASI, 10(3), 618–626. https://doi.org/10.32520/stmsi.v10i3.1248

Celano, G. G. A. (2021). A ResNet-50-Based Convolutional Neural Network Model for Language ID Identification from Speech Recordings [Paper presentation]. Proceedings of the Third Workshop on Computational Typology and Multilingual NLP, Online, 107–111. https://aclanthology.org/2021.sigtyp-1.13

Fricke, T. R., Jong, M., Naidoo, K. S., Sankaridurg, P., Naduvilath, T. J., Ho, S. M., Wong, T. Y., & Resnikoff, S. (2018). Global prevalence of visual impairment associated with myopic macular degeneration and temporal trends from 2000 through 2050: Systematic review, meta-analysis and modelling. British Journal of Ophthalmology, 102(7), 855–862. https://doi.org/10.1136/bjophthalmol-2017-311266

Hartati, E. (2024). Klasifikasi penyakit mata menggunakan convolutional neural network model Resnet-50. Jurnal Rekayasa Sistem Informasi dan Teknologi, 1(3), 199–206. https://doi.org/10.59407/jrsit.v1i3.529

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. [Paper presentation]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–778. https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_ Residual_Learning_CVPR_2016_paper.html

Holden, B. A., Fricke, T. R., Wilson, D. A., Jong, M., Naidoo, K. S., Sankaridurg, P., Wong, T. Y., Naduvilath, T. J., & Resnikoff, S. (2016). Global prevalence of myopia and high myopia and temporal trends from 2000 through 2050. Ophthalmology, 123(5), 1036–1042. https://doi.org/10.1016/j.ophtha.2016.01.006

Jatmoko, D., & Lestiawan, H. (2024). Prediksi penyakit mata menggunakan convolutional neural network. [Paper presentation]. Proceedings Semnas Ristek (Seminar Nasional Riset dan Teknologi), 8(1), 851–857. https://doi.org/10.30998/semnasristek.v8i01.7129

Jonas, J. B., Bikbov, M. M., Wang, Y.-X., Jonas, R. A., & Panda-Jonas, S. (2023). Anatomic peculiarities associated with axial elongation of the myopic eye. Journal of Clinical Medicine, 12(4), 1317. https://doi.org/10.3390/jcm12041317

Kaya, M. (2025). Efficient diagnosis of retinal diseases using convolutional neural networks. Gazi University Journal of Science Part A: Engineering and Innovation, 12(1), 15–35. https://doi.org/10.54287/gujsa.1592915

Laksono, G. I., & Winarno, S. (2025). Myopia identification by fundus photo image classification using convolutional neural network. Journal of Applied Informatics and Computing, 9(5), 2801–2806. https://doi.org/10.30871/jaic.v9i5.10624

Primadiani, I. S., & Rahmi, F. L. (2017). Faktor-faktor yang mempengaruhi progresivitas miopia pada mahasiswa kedokteran. Jurnal Kedokteran Diponegoro, 6(4), 1505-1517. https://ejournal3.undip.ac.id/index.php/medico/article/viewFile/18381/17461

Puspitasari, N., Utami, D., Sulistyawati, A., & Simanjutak, H. (2024). Gambaran kelainan refraksi pada siswa/i di SDN Padaulun Kecamatan Majalaya tahun 2024. Nama Orang.

Sait, W., & Rahaman, A. (2023). Artificial intelligence-driven eye disease classification model. Applied Sciences, 13(20), 11437. https://doi.org/10.3390/app132011437

Sambulele, A. P., Najoan, I. H. M., & Supit, W. P. (2025). Gambaran kejadian miopia pada mahasiswa Fakultas Kedokteran Universitas Sam Ratulangi. Medical Scope Journal, 7(1), 85–90. https://doi.org/10.35790/msj.v7i1.55450

Sanderson, K. (n.d.). Myopia image dataset. Kaggle. Retrieved December 23, 2025, from https://www.kaggle.com/datasets/kellysanderson/myopia-image-dataset

Shyamalee, T., & Meedeniya, D. (2022). CNN based fundus images classification for glaucoma identification. [Paper presentation]. 2022 2nd International Conference on Advanced Research in Computing (ICARC), 200–205. https://doi.org/10.1109/ICARC54489.2022.9754171

Simarmata, M. M., Doringin, F., Khofifah, N. A., & Aulia, Z. R. (2024). Upaya pencegahan miopia pada anak-anak sekolah dalam rangka Hari Kesehatan Nasional di Jakarta Convention Center. Jurnal Peduli Kesehatan Mata, 2(4), 48-57. https://doi.org/10.54363/pkm.v2i4.249

Singh, H., Singh, H., Latief, U., Tung, G. K., Shahtaghi, N. R., Sahajpal, N. S., Kaur, I., & Jain, S. K. (2022). Myopia, its prevalence, current therapeutic strategy and recent developments: A review. Indian Journal of Ophthalmology, 70(8), 2788. https://doi.org/10.4103/ijo.IJO_2415_21

Steinmetz, J. D., Bourne, R. R. A., Briant, P. S., Flaxman, S. R., Taylor, H. R. B., Jonas, J. B., Abdoli, A. A., Abrha, W. A., Abualhasan, A., Abu-Gharbieh, E. G., Adal, T. G., Afshin, A., Ahmadieh, H., Alemayehu, W., Alemzadeh, S. A. S., Alfaar, A. S., Alipour, V., Androudi, S., Arabloo, J., … Vos, T. (2021). Causes of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to VISION 2020: The Right to Sight: An analysis for the Global Burden of Disease Study. The Lancet Global Health, 9(2), e144–e160. https://doi.org/10.1016/S2214-109X(20)30489-7

Swain, S., & R, S. (2023). Prediction of myopia progression based on artificial intelligence model. In Applied Mathematics, Modeling and Computer Simulation (pp. 940–950). IOS Press. https://doi.org/10.3233/ATDE231034

Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. [Paper presentation]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2818–2826. http://doi.org/10.1109/CVPR.2016.308

United Nations. (n.d.). Sustainable Development Goals. https://www.un.org/sustainabledevelopment/

Van Rossum, G., & Drake, F. L. (2009). Python 3 Reference Manual. CreateSpace.

Wardhani, A. S., Anggraeny, F. T., & Rizki, A. M. (2024). Penerapan model hibrida CNN-KNN untuk klasifikasi penyakit mata. Jurnal Mahasiswa Teknik Informatika - JATI, 8(3), 3662–3667. https://doi.org/10.36040/jati.v8i3.9774

Zahra, R. P., Zaldi, Z., Laszuarni, L., & Sarirah, M. (2024). Risiko miopia terhadap jarak pandang dekat pada mahasiswa Fakultas Kedokteran Universitas Muhammadiyah Sumatera Utara. Jurnal Pandu Husada, 5(4), 8–21. https://doi.org/10.30596/jph.v5i4.21031.g12591

Zhang, H.-Q., Arif, M., Thafar, M. A., Albaradei, S., Cai, P., Zhang, Y., Tang, H., & Lin, H. (2025). PMPred-AE: A computational model for the detection and interpretation of pathological myopia based on artificial intelligence. Frontiers in Medicine, 12, 1529335. https://doi.org/10.3389/fmed.2025.1529335