Classifying glaucoma and normal large optic cups using deep learning methods

Abstract

Abstract Glaucoma is a group of serious eye diseases that can cause incurable blindness. Glaucoma diagnosis is a costly task and some models have been proposed to automate diagnosis based on images of the retina, specifically the area known as the optic cup and the associated disc where retinal blood vessels and nerves enter and leave the eye. However, the diagnosis of glaucoma is complicated because both normal and glaucoma eyes vary greatly in appearance, and some normal cases appear very similar to glaucoma. For example, like glaucoma, some normal cases have a larger cup-to-disc ratio, one of the main criteria in glaucoma diagnosis, making it more difficult to distinguish them. Thus, we propose a deep learning model with domain features (DLMDF) to combine unstructured and structured features to distinguish between glaucoma and physiologic large cups. The structured features were based upon the known cup-to-disc ratios of the four quadrants of the optic discs in normal, normal large, and glaucomatous optic cups. We segmented each cup and disc using a fully convolutional neural network and then calculated the cup size, disc size, and cup-to-disc ratio of each quadrant. The unstructured features were learned from a deep convolutional neural network. In this way, both unstructured image information and structured features were utilized for diagnosis. Experiments conducted on a real dataset demonstrated the superiority of the proposed model over traditional ones.