Diagnosis Retinal Disease by using Deep Learning Models

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