Diagnosis Retinal Disease by using Deep Learning Models

Abstract

Deep learning approaches have shown to be useful in assisting physicians in making decisions about cancer, heart disease, degenerative brain disorders, and eye disease. In this work, a deep learning model was proposed for the diagnosis of retinal diseases utilizing optical coherence tomography X-ray pictures (OCT) to identify four states of retina disease. The proposed model consists of three different convolutional neural network (CNN) models to be used in this approach and compare the results of each one with others. The models were named respectively as 1FE1C, 2FE2C, and 3FE3C according to the design complexity. The concept uses deep CNN to learn a feature hierarchy from pixels to layers of classification retinal diseases. On the test set, the classifier accuracy is 65.60 % for a (1FE1C) Model, 86.81% for (2FE2C) Model, 96.00% for (3FE3C) Model, and 88.62% for (VGG16) Pre-Train Model. The third model (3FE3C) achieves the best accuracy, although the VGG16 model comes close. Also, this model improves the results of previous works and paves the way for the use of state-of-the-art technology of neural network in retinal disease diagnoses. The suggested strategy may have a bearing on the development of a tool for automatically identifying retinal disease.