Computer Aided Diagnosis for Early Detection of Glaucoma Using Convolutional Neural Network (CNN)

Glaucoma is an eye disease caused by an increase in eye pressure resulting in damage to the optic nerve and can cause blindness. An ophthalmologist makes the diagnosis of glaucoma by analyzing the fundus images that show the retinal structure. This manual diagnosis requires years of expertise and prone to error. Previous studies have designed a glaucoma CAD system based on Convolutional Neural Network (CNN) and showed promising results. This study proposes the CNN method consisting of three hidden layers that use 3 × 3 of the filter size with 16, 32, 64 output channels, fully connected layers, and sigmoid activation. The experiment is conducted using the RIMONE R2 fundus images dataset to classify normal and glaucoma conditions. From 455 fundus images, 75% are used as the training data, while the rest is used as the validation data. From the experiment, this study outperforms other previous studies by achieving 91.22% of accuracy. The glaucoma system detection that has been developed in this research, can be helpful for ophthalmologists to establish an initial diagnosis of glaucoma that can reduce the harmful effects of glaucoma.