Abstract
Diabetic retinopathy (DR) is a serious retinal disease and is considered as a leading cause of blindness in the world. Ophthalmologists use optical coherence tomography (OCT) and fundus photography for the purpose of assessing the retinal thickness, and structure, in addition to detecting edema, hemorrhage, and scars. Deep learning models are mainly used to analyze OCT or fundus images, extract unique features for each stage of DR and therefore classify images and stage the disease. Throughout this paper, a deep Convolutional Neural Network (CNN) with 18 convolutional layers and 3 fully connected layers is proposed to analyze fundus images and automatically distinguish between controls (i.e. no DR), moderate DR (i.e. a combination of mild and moderate Non Proliferative DR (NPDR)) and severe DR (i.e. a group of severe NPDR, and Proliferative DR (PDR)) with a validation accuracy of 88%-89%, a sensitivity of 87%-89%, a specificity of 94%-95%, and a Quadratic Weighted Kappa Score of 0.91–0.92 when both 5-fold, and 10-fold cross validation methods were used respectively. A prior pre-processing stage was deployed where image resizing and a class-specific data augmentation were used. The proposed approach is considerably accurate in objectively diagnosing and grading diabetic retinopathy, which obviates the need for a retina specialist and expands access to retinal care. This technology enables both early diagnosis and objective tracking of disease progression which may help optimize medical therapy to minimize vision loss.
Highlights
Convolutional neural networks (CNNs) have been recently utilized for diagnosing diabetic retinopathy (DR) through analyzing fundus images and have proven their superiority in detection and classification tasks [1] [2]
We propose a novel deep CNN architecture that can classify subjects with high accuracy into controls, moderate DR that includes patients with mild or moderate non-proliferative DR (NPDR), and severe DR, which represents patients in the late stages with either severe NPDR or proliferative DR (PDR)
Each fold was further split into batches of 57 fundus images in order to reduce the computational complexity of the training process by deploying the Stochastic Gradient Descent (SGD) rather than a gradient descent over the entire training set
Summary
Convolutional neural networks (CNNs) have been recently utilized for diagnosing diabetic retinopathy (DR) through analyzing fundus images and have proven their superiority in detection and classification tasks [1] [2]. DR is a major complication that may eventually result in vision loss as well as blindness. It is caused by the damage occurring to the retina blood vessels as increased levels of blood sugar block minute blood vessels that supply blood to the retina. A CNN for the screening and staging of DR dataset folder can be downloaded by clicking on "Download All" button inside the "Data" webpage
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
