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

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