Quantification of retinal artery-vein ratio for vascular disease diagnosis using spatial U-Net

The retinal <span>vascular morphological caliber changes reveal the signs of systemic health disorder and life threat diseases such as cardio cerebral diseases. quantitative vascular parameters like narrowed arteries, widened venules, reduced artery-vein ratio (AVR) have been associated with aforesaid disorders Hence biomarker AVR is important parameter in diagnosing variety accurate quantification be possible if only classification arteries vein done. In this paper, we proposed a deep learning based robust vessel segmentation algorithm on spatial <br /> U-Net accuracy 97.8%. process, applied region interest (RoI) fundus image measured values using central artery equivalent (CRAE) (CRVE). experimentation carried digital images for extraction (DRIVE) dataset. outcome work observed to >0.4 normal case value <0.4 unhealthy case.</span>