Computational methods for segmentation of the optic disc in retinal images: a review

The use of digital image processing techniques (DIP) is highlighted in the medical scenario for automatic diagnosis of pathologies. In the ophthalmologic area, glaucoma is the second leading cause of vision loss in the world and has no cure. Currently, treatments are used to prevent vision loss, but the disease must be discovered in the early stages. This paper aims to review the methodologies and techniques of optic disc and cup limits segmentation. These regions are used to calculate metrics for classiffication of glaucoma and assistance to professionals in the area. The most recent published studies were classified into five groups according to the central DIP technique applied: clustering, superpixel, active contour, mathematical morphology and Convolutional Neural Network. Also, a survey was conducted of the main images databases and evaluation metrics used.