Automatic detection of papilledema through fundus retinal images using deep learning

Papilledema is a syndrome of the retina in which retinal optic nerve inflated by elevation intracranial pressure. The papilledema abnormalities such as fiber layer (RNFL) opacification may lead to blindness. These could be seen through capturing images means fundus camera. This paper presents deep learning-based automated system that detects and grades U-Net Dense-Net architectures. proposed approach has two main stages. First, disc its surrounding area image are localized cropped for input classifies or normal. Second, consists preprocessing classified Gabor filter. preprocessed achieve segmented vascular network from vessel discontinuity index (VDI) proximity (VDIP) calculated grading papilledema. VDI VDIP standard parameter check severity evaluated on 60 40 normal taken STARE dataset. experimental results classification much better terms sensitivity 98.63%, specificity 97.83%, accuracy 99.17%. Similarly, mild severe also 99.82%, 98.65%, 99.89%. detection clinical purposes first effort state art.