Deep Learning Based Decision Support System for Retinal Disease Classification: Diabetic Retinopathy and Macular Hole

Year 2025, Volume: 5 Issue: 1, 51 - 62, 01.05.2025

Belinay Kabataş Emre Ölmez

Abstract

In this study, a deep learning-based decision support system was developed to classify diabetic retinopathy (DR), macular hole (MH) and healthy samples using fundus images. A total of 1,397 fundus images selected from the open source Retinal Disease Classification dataset were used in the training and testing phases. ResNet50, InceptionV3 and Xception models were trained with different hyperparameter configurations and their performances were comparatively evaluated. As a result of the analysis, the ResNet50 model showed the highest success on the test set with an accuracy of 93.79%. However, the Xception model stood out with its consistent performance against different hyperparameter combinations and provided the most balanced results in terms of average accuracy. The results show that deep learning-based methods can be effectively used as a clinical decision support system for retinal disease diagnosis.

Keywords

deep learning , fundus images , diabetic retinopathy , macular hole , convolutional neural networks , Resnet50 , Xception

References

• [1] B. Vatansever, H. Aydın, and A. Çetinkaya, “Genetik Algoritma Yaklaşımıyla Öznitelik Seçimi Kullanılarak Makine Öğrenmesi Algoritmaları ile Kalp Hastalığı Tahmini,” Journal of Scientific Technology and Engineering Research, Nov. 2021, doi: 10.53525/jster.1005934.
• [2] Ş. Aykat et al., “Derin Öğrenme Kullanılarak Fundus Görüntülerinden Katarakt ve Diyabetik Retinopati Tespiti Detection of Cataract and Diabetic Retinopathy from Fundus Images Using Deep Learning,” 2023.
• [3] Q. Wei et al., “Development and Validation of an Automatic Ultrawide-Field Fundus Imaging Enhancement System for Facilitating Clinical Diagnosis: A Cross-sectional Multicenter Study,” Engineering, Oct. 2024, doi: 10.1016/j.eng.2024.05.006.
• [4] K. Jin and J. Ye, “Artificial intelligence and deep learning in ophthalmology: Current status and future perspectives,” Nov. 01, 2022, Elsevier Inc. doi: 10.1016/j.aopr.2022.100078.
• [5] Y. B. Özçelik and A. Altan, “Diyabetik Retinopati Teşhisi için Fundus Görüntülerinin Derin Öğrenme Tabanlı Sınıflandırılması,” European Journal of Science and Technology, Dec. 2021, doi: 10.31590/ejosat.1011806.
• [6] E. Yaşar, N. Erol, M. D. Bilgeç, and A. İ. Çakmak, “Coexistence of peripheral retinal diseases with macular hole,” Turk J Ophthalmol, vol. 49, no. 4, pp. 209–212, Aug. 2019, doi: 10.4274/tjo.galenos.2019.06706.
• [7] S. Pachade et al., “Retinal fundus multi-disease image dataset (Rfmid): A dataset for multi-disease detection research,” Data (Basel), vol. 6, no. 2, pp. 1–14, Feb. 2021, doi: 10.3390/data6020014.
• [8] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” Dec. 2015, [Online]. Available: http://arxiv.org/abs/1512.03385
• [9] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Dec. 2016, pp. 2818–2826. doi: 10.1109/CVPR.2016.308.
• [10] F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Institute of Electrical and Electronics Engineers Inc., Nov. 2017, pp. 1800–1807. doi: 10.1109/CVPR.2017.195.
• [11] F. S. Sorrentino et al., “Novel Approaches for Early Detection of Retinal Diseases Using Artificial Intelligence,” Jul. 01, 2024, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/jpm14070690.
• [12] R. Lee, T. Y. Wong, and C. Sabanayagam, “Epidemiology of diabetic retinopathy, diabetic macular edema and related vision loss,” Dec. 01, 2015, BioMed Central Ltd. doi: 10.1186/s40662-015-0026-2.
• [13] D. Mikhail et al., “The role of artificial intelligence in macular hole management: A scoping review,” Jan. 01, 2024, Elsevier Inc. doi: 10.1016/j.survophthal.2024.09.003.
• [14] A. Kori, S. S. Chennamsetty, M. S. K. P., and V. Alex, “Ensemble of Convolutional Neural Networks for Automatic Grading of Diabetic Retinopathy and Macular Edema,” Sep. 2018, [Online]. Available: http://arxiv.org/abs/1809.04228
• [15] J. Sahlsten et al., “Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading,” Sci Rep, vol. 9, no. 1, Dec. 2019, doi: 10.1038/s41598-019-47181-w.
• [16] J. de la Torre, A. Valls, and D. Puig, “A deep learning interpretable classifier for diabetic retinopathy disease grading,” Neurocomputing, vol. 396, pp. 465–476, Jul. 2020, doi: 10.1016/j.neucom.2018.07.102.
• [17] S. N. Polater et al., “Diyabetik Retinopati Tespiti İçin Derin Öğrenmeye Dayalı Sınıflandırma Deep Learning-Based Classification for Diabetic Retinopathy Detection,” 2024.
• [18] Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning,” May 27, 2015, Nature Publishing Group. doi: 10.1038/nature14539.