Detection of primary glaucoma using a hybrid combination of fuzzy c-means clustering algorithm and level-1 support vector machine algorithm

Abstract

Glaucoma, a leading cause of irreversible blindness, necessitates early and accurate detection for effective management. This research paper presents a novel approach for the early detection of primary glaucoma through the integration of the fuzzy c-means clustering algorithm and the level-1 support vector machine (SVM) algorithm. The proposed hybrid system leverages the strengths of both algorithms, exploiting fuzzy clustering to enhance feature extraction and the level-1 SVM for robust classification. The methodology involves preprocessing of retinal images, followed by the application of the fuzzy c-means algorithm for clustering and feature extraction. The extracted features are then fed into the level-1 SVM classifier for accurate discrimination between healthy and glaucomatous eyes. The hybrid model is trained and evaluated using a comprehensive dataset of ophthalmic images, considering a diverse range of glaucoma severity levels. Results indicate that the proposed hybrid approach outperforms traditional methods in terms of sensitivity, specificity, and overall accuracy. The integration of fuzzy clustering allows for improved representation of subtle variations in retinal characteristics associated with glaucoma, while the level-1 SVM ensures efficient classification with reduced computational complexity. The promising outcomes suggest the potential of the hybrid model as an effective tool for early-stage primary glaucoma detection, paving the way for enhanced clinical interventions and preventative measures. Further validation and integration into existing diagnostic frameworks are warranted to validate the clinical utility of this innovative approach in real-world settings.