Optical Nerve Detection Using Fuzzy Convergence Algorithm

The extraction of blood vessels from retinal images is an important and challenging task in medical analysis and diagnosis. Retinal images of humans play an important role in the detection and diagnosis of many eye diseases for ophthalmologists. This paper presents an automated method to locate the optic nerve in images of the ocular fundus. The fuzzy convergence algorithm is used to find the vessel network convergence. The algorithm is a voting type method that works in the spatial domain of the image. The input to the algorithm is a binary segmentation of the blood vessels. Each vessel is modeled by a fuzzy segment, which contributes to a cumulative voting image. The output from the algorithm is a convergence image, which is thresholded to identify the strongest points of convergence. The method uses 30 images of healthy retinas and 51 images of diseased retinas, containing diverse symptoms as tortuous vessels, choroidal neovascularization, and hemorrhages that completely obscure the actual nerve. On this difficult data set, the proposed method achieved 89% correct detection.