Detection of Visual Impairment From Retinal Fundus Images with Deep Learning

Nowadays, there are challenges in terms of eye care, including the treatment of visual impairment, quality of prevention and vision rehabilitation services. Since the eye is an organ that gives information about other diseases due to its structure, examinations have an important role. In this study, a solution is sought with AlexNet, ResNet and Xception architectures based on deep learning to predict the presence or absence of visual impairment from retinal fundus images. Thus, the possibility of vision loss of patients can be reduced by detecting people with visual impairments and by early diagnosis, and thus, significant increases in the patient's quality of life can be observed.