Detection of Retinal Disease Using Convolutional Neural Networks

The paper “Detection of Retinal Disease Using Convolutional Neural Networks” focuses on leveraging deep learning techniques for the early detection of retinal degeneration. Retinal diseases such as age-related macular degeneration (AMD), retinal detachment, diabetic retinopathy (DR), retinitis pigmentosa, and retinoblastoma can result in severe vision loss. Automated recognition of these pathologies is of outmost importance for early diagnosis and cure. There are various methods developed in history for automatic segmentation and detection of retinal landmarks and diseases. But, modern deep learning technology and advanced imaging tools in the field of ophthalmology have given new areas for investigation. This inquiry introduces two deep neural networks (DNN) as the primary research- the Multilayer Convolutional Neural Network (CNN) and AlexNet for the detection of retinal degeneration. The scientists play with the sensitivity of the neural networks by applying the three different optimizers—ADAM, RMSProp, and SGDM—to the fundus images and the results are analyzed at three different training rates for these neural networks. The write-up aims at insignificantly different things from CNNs which are image-based pattern recognition, and their layered structure which consists of an input layer, an output, and a hidden layer. Each layer accomplishes the operations of linear and non-linear, getting the details correct from the images. On the contrary, the combination of fully connected layers with convolutional layers was used in AlexNet, a very comprehensive approach. The research makes it absolutely clear that optimization procedures play a key role in this kind of network because the use of RMSProp usually provides the best performance.