Publication Details

Abstract

Glaucoma is a leading cause of irreversible blindness globally. Timely and accurate detection is crucial for early intervention and vision preservation. This paper proposes a deep learning-based automated pipeline integrating segmentation (e.g., U-Net or conditional Generative Adversarial Networks) with convolutional neural network (CNN) classifiers to detect glaucoma from retinal fundus images. The proposed method enhances the Region of Interest (ROI) extraction, primarily focusing on the optic disc and cup, thereby improving classification accuracy. Experimental results demonstrate the effectiveness of the integrated pipeline, offering promising potential for large-scale screening and computer-aided diagnosis.