Cognitive Diagnosis Of Chronic Glaucoma And Its Differentiation From Diabetic Retinopathy Using Machine Learning And Deep Learning
Keywords:
Chronic Glaucoma, Diabetic Retinopathy, Machine Learning, Deep Learning, Fundus Imaging, Convolutional Neural Networks, Multi-label Classification, Model Interpretability, SHAP, Grad-CAM, Medical DiagnosticsAbstract
Timely and accurate diagnosis of ocular diseases such as Chronic Glaucoma and Diabetic Retinopathy is essential to prevent irreversible vision impairment and blindness. Traditional diagnostic methods often rely on manual examination and expert interpretation, which can be both time-intensive and prone to variability. This study presents a comprehensive machine learning and deep learning-based framework for the automated prediction of Chronic Glaucoma and Retinopathy using both clinical data and retinal fundus images. The proposed methodology integrates structured data analysis using machine learning algorithms for image-based diagnosis. Fundus photographs are preprocessed using standard enhancement techniques, including histogram equalization, denoising, and vessel segmentation, to improve feature visibility and model accuracy. Clinical features such as intraocular pressure, optic cup-to-disc ratio, blood glucose levels, and patient history are employed alongside imaging data to enrich the prediction pipeline. A multi-label classification approach is adopted to enable the simultaneous detection of both diseases, accommodating cases where patients present with overlapping symptoms or comorbid conditions. Model performance is rigorously evaluated using metrics such as accuracy, precision, recall, F1-score, and the area under the ROC curve (AUC-ROC). Interpretability and model transparency are addressed through the application of Gradient-weighted Class Activation Mapping (Grad-CAM) for CNN models and SHapley Additive exPlanations (SHAP) for tree-based ML models, offering insight into critical decision-driving features. The results demonstrate that the integration of clinical and imaging data substantially improves predictive performance and reliability. The proposed system holds promise for deployment in clinical environments, especially in areas with limited access to ophthalmology specialists, by providing a scalable and accurate diagnostic tool for early-stage detection and management of Chronic Glaucoma and Retinopathy.
Downloads
References
D.M.S. Barros, J.C.C. Moura, C.R. Freire, A.C. Taleb, R.A.M. Valentim and P.S.G. Morais, "Machine learning applied to retinal image processing for glaucoma detection: Review and perspective", BioMed. Eng., vol. 19, pp. 20, 2019.
2. A. Diaz-Pinto, S. Morales, V. Naranjo, T. Köhler,
M. Jose and A. Navea, "CNNs for automatic glaucoma assessment using fundus images: An extensive validation", BioMed. Eng., vol. 18, pp. 29, 2019.
3. Dong-yan FAN, "Multi-focus Image Fusion Algorithm 4. "International Journal of Science and Research (IJSR)", International Journal of Science and Research, vol. 5, no. 5, pp. 1331-33, May 2016, [online] Available:
https://doi.org/10.21275/v5i5.6051605.
5. M. Juneja, S. Singh, N. Agarwal, S. Bali, S. Gupta, N. Thakur, et al., "Automated detection of
Glaucoma using deep learning convolution network (G-net)", Multimed. Tools Appl., vol. 79, pp. 15531-15553, 2020.
6. B.N. Kumar, R.P. Chauhan and N. Dahiya, "Detection of glaucoma using image processing techniques: 7. L. Li, M. Xu, H. Liu, Y. Li, X. Wang, L.
Jiang, et al., "A large-scale database and a CNN model for attention-based glaucoma detection", IEEE Trans. Med. Imaging, vol. 39,
pp. 413-424, 2020.
8. I.J.C. MacCormick, B.M. Williams, Y. Zheng, K. Li, B. Al-Bander, S. Czanner, R. Cheeseman, C.E. Willoughby, E.N. Brown,
G.L. Spaeth et al., "Accurate fast data efficient and interpretable glaucoma diagnosis with automated spatial analysis of the whole cup to disc profile",PLoSONE, vol. 14, pp. e0209409, 2019.
9. M.C.V.S. Mary, E.B. Rajsingh and G.R. Naik, "Retinal fundus image analysis for diagnosis of glaucoma: A comprehensive survey", IEEE Access, vol. 4, pp. 4327-4354, 2016.
10. P.H. Prastyo, A.S. Sumi and A. Nuraini, "Optic cup segmentation using U-Net architecture on retinal fundus image", J. Inf. Technol. Comput. Eng., vol. 4, pp. 105-109, 2020.A. Sarhan, J. Rokne and R. Alhajj, "Glaucoma detection using image processing techniques: A literature review", Comput. Med. Imaging Graph. Off. J. Comput. Med. Imaging Soc., vol. 78, pp. 101657, 2019.
11. S. Senjam, "Glaucoma blindness–A rapidly emerging non-communicable ocular disease in India: Addressing the issue with advocacy", J. Fam. Med. Prim. Care, vol. 9, pp. 2200, 2020.
12. N.M. SynaSreng, K. Hamamoto and K.Y. Win, "Deep learning for optic disc segmentation and glaucoma diagnosis on retinal images", Appl. Sci., vol. 10, pp. 4916, 2020.
13. Y. Wang, S. Panda-Jonas and J. Jonas, "Optic nerve head anatomy in myopia and glaucoma including parapapillary zones alpha beta gamma and delta: Histology and clinical features", Prog. Retin. Eye Res., vol. 83, pp. 100933, 2021.
14. Yu Zhang et al., "Boundary Finding Based Multi-focus Image Fusion Through Multi-scale Morphological Focus-measure", Information Fusion, vol. 35, pp. 81-101, May 2017, [online] Available: https://doi.org/10.1016/j.inffus.2016.09.006.
15. M. R. Islam, L. F. Abdulrazak, M. Nahiduzzaman, M. O. F. Goni, M. S. Anower, M. Ahsan, et al., "Applying supervised contrastive learning for the detection of diabetic retinopathy and its severity levels from fundus images", Computers in Biology and Medicine, pp. 105602, 2022.
16. K. Shankar, Y. Zhang, Y. Liu, L. Wu and C.-H. Chen, "Hyperparameter tuning deep learning for diabetic retinopathy fundus image
classification", IEEE Access, vol. 8, pp. 118164-118173, 2020.
17. R. Sarki, K. Ahmed, H. Wang and Y. Zhang, "Automatic detection of diabetic eye disease through deep learning using fundus images: a survey", IEEE Access, vol. 8, pp. 151133-151149, 2020.
18. H. Kaushik, D. Singh, M. Kaur, H. Alshazly, A. Zaguia and H. Hamam, "Diabetic retinopathy diagnosis from fundus images using stacked generalization of deep models", IEEE Access, vol. 9, pp. 108276- 108292, 2021.
19. J. P. Allam, S. Samantray and S. Ari, "Spec: A system for patient specific ecg beat classification using deep residual network", Biocybernetics and Biomedical Engineering, vol. 40, no. 4, pp. 1446-1457,
2020.
