Detecting Chronic Vascular Damage with Attention-Guided Neural System

The retinal vasculature has a vital role in predicting chronic diabetic and hypertensive retinopathy. Recently, the advent of deep learning algorithms has brought a revolution in ocular disease prediction. The researchers frequently design complex and intricate techniques to efficiently segment vessels, micro-vessels and achieve better response on publicly available benchmark datasets. This article has designed an attention-guided neural system to extract vascular tree and distinguish it in arteries and veins. The proposed learning protocol with a minimalist approach can compete with state-of-the-art work without a performance compromise. Our method has achieved a promising response on numerous retinal image datasets. The pitfall of previously proposed work is also addressed through the self-defined assessment criteria. The in-depth analysis highlights that the underlying problem is unsolved for unseen data with different distribution than training. Our method is cross-validated to report the performance loss by keeping diversity in data selection. The technique is further applied for the arteries and veins extraction. Our effort can be adapted as an efficient vision-critical platform to scan and localize retinal damage and diagnose the disease symptoms early to prevent vision impairment.