Keratoconus Classification Using Machine Learning

The diagnosis of several ophthalmic diseases such as age-related macular degeneration, glaucoma, diabetic retinopathy and keratoconus involves the analysis of the eye topographic maps. The dependence between ophthalmology and images processing represents a point of attraction for researchers to benefit of capacity and performance of deep learning tools in image processing. These tools allow a better differentiation between a sick eye and a normal one based on the analysis of the eye topographic maps and can change potentially the practices of ophthalmologists in diagnosis and treatment of similar diseases. Among the diseases already mentioned, keratoconus, this non-inflammatory disease characterized by a progressive thinning of the cornea is often accompanied by aspens of vision. The increasing number of people diagnosed with keratoconus has made this disease the subject of several research studies.This paper represents an overview of artificial intelligence application in keratoconus classification and a proposal system of keratoconus classification based on neural networks.