Detection of Glaucoma and Diabetic Retinopathy Using Fundus Images and Deep Learning

Glaucoma and Diabetic Retinopathy are serious diseases that can lead to vision loss and blindness. With a growing number of patients affected by these diseases, it is crucial to find reliable and efficient methods for diagnosis and treatment. In this study, we aimed to compare the performance of five different models for diagnosing Glaucoma and Diabetic Retinopathy from images using AI. Specifically, we used the CNN-based models LeNet and AlexNet, as well as the inception and ResNet models. After training and testing each model, we compared their performance on accuracy and loss parameters. Our results showed that the AlexNet model outperformed the other models with an accuracy of 97.96% and Lenet performed the most consistent with all different parameters.