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.
Retinal image analysis is crucial for The classification of retinal diseases such as "Age Related Macular Degeneration (AMD)", "Diabetic Retinopathy (DR)", "Retinoblastoma", "Macular Bunker", "Retinitis Pigmentosa", and "Retinal Detachment". The early detection of such diseases is important insofar as it contributes in mitigating future implications. Many approaches have been developed in the literature for auto-detecting of retinal landmarks and pathologies. The current revolution in deep learning techniques has opened the horizon for researchers in the field of ophthalmology. This paper is a comprehensive review of the deep learning techniques applied for the classification of retinal images, pathology, retinal landmarks, and disease classification. This review is based on indicators such as sensitivity, Area under ROC curve, specificity, F score, and accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.