Detection Of Cataract, Diabetic Retinopathy and Glaucoma Eye Diseases with Deep Learning Approach

Abstract

Eye diseases are one of the serious health problems affecting human life. Cataract, diabetic retinopathy and glaucoma eye diseases cause visual impairment and cause irreversible eye defects. Throughout human life; genetic, age and environmental factors affect people's eye health. Detection of the disease plays a critical role in order to apply the right diagnosis and therefore increase the quality of life of the patient. With the developing technology, artificial intelligence can detect eye defects and therefore whether there is a disease or not. This study aims to develop solutions for detecting an important health problem such as eye health by using deep learning models. In the related study, Convolutional Neural Networks models, one of the deep learning types are used. The data set used for disease detection includes a total of 2748 Retinal Fundus images taken from 1374 normal individuals and 1374 different disease groups. In order to compare the classification performances and to achieve better performance, a solution to the disease detection problem was sought by using a total of 5 different Convolutional Neural Networks architectures. These are DenseNet, EfficientNet, Xception, VGG, Resnet. For the validity of the approach, it was tested using the 10-fold cross-validation technique. Accuracy, Recall, Precision, F1-Score, and Matthews’s coefficient correlation metrics were used as performance evaluation criteria. When the classification performances were examined, the results obtained with the EfficientNet architecture were measured as 94.88%, 94.88%, 95.02%, 94.88%, 89.89% for Accuracy, Recall, Precision, F1-Score, and Matthews’s coefficient correlation metrics. In this context, the best classification performance was obtained with the EfficientNet architecture.