Deep Learning Based Model for Fundus Retinal Image Classification

Several types of eye diseases can lead to blindness, including glaucoma. For better diagnosis, retinal images should be assessed using advanced artificial intelligence techniques, which are used to identify a wide range of eye diseases. In this paper, support vector machine (SVM), random forest (RF), decision tree (DT), and convolutional neural network (CNN) methods are used to classify fundus retinal images of healthy and glaucomatous patients. This study tests various models on a small dataset of 30 high-resolution fundus retinal images. To classify these retinal images, the proposed CNN-based classifier achieved a classification accuracy of 80%. Furthermore, according to the confusion matrix, the proposed CNN model was 80% accurate for the healthy and glaucoma classes. In the glaucoma case, the CNN-based classifier proved superior to other classifiers based on the comparative analysis.