A Hybrid Imaging and Machine Learning Framework for Early Detection of Higher-Order Glaucoma

The article presented a multimodal ophthalmic imaging and data-driven analysis as a hybrid imaging machine learning platform to the early detection of a progressive type of glaucoma. The proposed technique implies the combination of fundus images and OCT images, thus the proposed technique would capture complementary information on the structural and textual parameters that would be crucial to identify the occurrence of glaucomatous alterations (particularly at early stages). Incorporation of manual components with deep learning representations can enable an effective and discriminatory feature set to overcome the drawbacks of the classical image analysis and single deep learning of features. Experimental performance demonstrates that the hybrid structure suggested will be more effective in terms of accuracy, sensitivity, and specificity than the existing machine learning and deep learning algorithms. It is notable that the sensitivity it attains in the diagnosis of the disease at the early stages of glaucoma highlights the capability of the framework to identify the higher-order manifestation of disease at an early age and hence provide clinical interventions to the patients on how to ensure that irreversible vision loss does not occur. The method of classification is also more reliable with the feature selection strategy and the complexity of the computational procedure is reduced which makes the method usable in the practice. The next steps will incorporate the extension of the framework to bigger and more varied datasets, longitudinal analysis to trace the progress of the disease, and model interpretability to raise the level of clinical trust and adoption.  

[1]                 N. Flores, J. La Rosa, S. Tuesta, L. Izquierdo, M. Henriquez, and D. Mauricio, “Hybrid deep learning model for improved glaucoma diagnostic accuracy,” Information, vol. 16, no. 7, p. 593, 2025, doi: 10.3390/info16070593. [2]                 A. Aljohani and R. Y. Aburasain, “A hybrid framework for glaucoma detection through federated machine learning and deep learning models,” BMC Medical Informatics and Decision Making, vol. 24, no. 1, p. 115, 2024, doi: 10.1186/s12911-024-02518-y. [3]                 L. J. Coan et al., “Automatic detection of glaucoma via fundus imaging and artificial intelligence: A review,” Survey of Ophthalmology, vol. 68, no. 1, pp. 17–41, 2023, doi: 10.1016/j.survophthal.2022.08.005. [4]                 D. M. S. Barros, J. C. C. Moura, C. R. Freire, et al., “Machine learning applied to retinal image processing for glaucoma detection: Review and perspective,” BioMedical Engineering OnLine, vol. 19, p. 20, 2020, doi: 10.1186/s12938-020-00767-2. [5]                 M. M. Hasan, J. Phu, A. Sowmya, E. Meijering, and M. Kalloniatis, “Artificial intelligence in the diagnosis of glaucoma and neurodegenerative diseases,” Clinical and Experimental Optometry, vol. 107, no. 2, pp. 130–146, 2024, doi: 10.1080/08164622.2023.2235346. [6]                 M. H. Shahriari, F. Asadi, H. Moghaddasi, A. Roshanpour, F. Sharifipour, and Z. Khorrami, “Applications of machine learning in glaucoma diagnosis based on tabular data: A systematic review,” BMC Biomedical Engineering, vol. 7, no. 1, p. 9, 2025, doi: 10.1186/s42490-025-00095-3. [7]                 B. Ubochi, A. E. Olawumi, J. Macaulay, O. I. Ayomide, K. F. Akingbade, and R. Al-Nima, “Comparative analysis of vanilla CNN and transfer learning models for glaucoma detection,” Journal of Electrical and Computer Engineering, vol. 2024, p. 8053117, 2024. [8]                 S. Pathan, P. Kumar, R. M. Pai, and S. V. Bhandary, “An automated classification framework for glaucoma detection in fundus images using ensemble of dynamic selection methods,” Progress in Artificial Intelligence, vol. 12, no. 3, pp. 287–301, Sep. 2023, doi: 10.1007/s13748-023-00304-x. [9]                 W. L. Alyoubi, W. M. Shalash, and M. F. Abulkhair, “Diabetic retinopathy detection through deep learning techniques: A review,” Informatics in Medicine Unlocked, vol. 20, p. 100377, 2020. [10]              M. Govindan, V. K. Dhakshnamurthy, K. Sreerangan, M. D. Nagarajan, and S. K. Rajamanickam, “A framework for early detection of glaucoma in retinal fundus images using deep learning,” Engineering Proceedings, vol. 62, no. 1, p. 3, 2024, doi: 10.3390/engproc2024062003.