OptiCNN: Local thresholding segmentation and CNN with SVM Approach for Diabetic Retinopathy Detection and Classification of Fundus Images 

Abstract

Diabetic Retinopathy (DR) is a progressive eye disease that can lead to vision loss and blindness if left untreated. Ophthalmologists diagnose DR using medical imaging modalities such as fundus photography and optical coherence tomography (OCT); however, manual interpretation of these images is time-consuming and subject to inter-observer variability. While DR is irreversible, vision loss can be prevented through early detection and timely intervention. Regular eye examinations and systematic DR monitoring are essential for preventing blindness in diabetic patients. Therefore, there is an urgent need for computer-assisted diagnosis (CAD) systems to support ophthalmologists in detecting and grading DR accurately and efficiently. This paper proposes a novel CAD system for automated DR classification. The proposed methodology consists of three stages: (1) image preprocessing through grayscale conversion and resizing, (2) retinal vessel segmentation using a local thresholding approach, and (3) classification using a hybrid architecture that integrates a Convolutional Neural Network (CNN) with a Support Vector Machine (SVM) classifier. The proposed model, OptiCNN (Optimized CNN), aligns its predictions with the International Clinical Diabetic Retinopathy (ICDR) severity scale. Experimental results demonstrate that OptiCNN achieves an accuracy of 94%, precision of 96%, recall of 91%, F1-score of 93%, and area under the curve (AUC) of 92% on benchmark datasets. The proposed system provides reliable DR staging to assist ophthalmologists in treatment planning and clinical decision-making, potentially reducing diagnostic workload while maintaining high diagnostic accuracy.