Abstract: Science Set Journal of Ophthalmology and Eye Care

Abstract:
Segmenting retinal vessels is vital for automating the analysis of fundus images to screen and diagnose various retinal vascular diseases, such as diabetic retinopathy, a common complication of diabetes that can lead to sudden vision loss. Automated vessel segmentation offers more efficient and accurate detection of changes compared to manual assessment by an ophthalmologist. The proposed method aims to precisely identify blood vessels in retinal images, simplifying the segmentation process and reducing computational complexity. This approach can improve the accuracy and reliability of retinal image analysis, assisting in diagnosing various eye diseases. The NAU-Net architecture plays a crucial role in segmenting retinal images for conditions like diabetic retinopathy, showing promising results in enhancing segmentation accuracy. Extensive experiments on a retinal segmentation dataset demonstrated that the proposed approach surpassed existing methods in terms of performance and computational efficiency.