Purpose: To develop a new intelligent system based on deep learning for automatically optical coherence tomography (OCT) images categorization. Methods: A total of 60,407 OCT images were labeled by 17 licensed retinal experts and 25,134 images were included. One hundred one-layer convolutional neural networks (ResNet) were trained for the categorization. We applied 10-fold cross-validation method to train and optimize our algorithms. The area under the receiver operating characteristic curve (AUC), accuracy and kappa value were calculated to evaluate the performance of the intelligent system in categorizing OCT images. We also compared the performance of the system with results obtained by two experts. Results: The intelligent system achieved an AUC of 0.984 with an accuracy of 0.959 in detecting macular hole, cystoid macular edema, epiretinal membrane, and serous macular detachment. Specifically, the accuracies in discriminating normal images, cystoid macular edema, serous macular detachment, epiretinal membrane, and macular hole were 0.973, 0.848, 0.947, 0.957, and 0.978, respectively. The system had a kappa value of 0.929, while the two physicians' kappa values were 0.882 and 0.889 independently. Conclusions: This deep learning-based system is able to automatically detect and differentiate various OCT images with excellent accuracy. Moreover, the performance of the system is at a level comparable to or better than that of human experts. This study is a promising step in revolutionizing current disease diagnostic pattern and has the potential to generate a significant clinical impact. Translational Relevance: This intelligent system has great value in increasing retinal diseases' diagnostic efficiency in clinical circumstances.

With the emergence of unmanned plane, autonomous vehicles, face recognition, and language processing, the artificial intelligence (AI) has remarkably revolutionized our lifestyle. Recent studies indicate that AI has astounding potential to perform much better than human beings in some tasks, especially in the image recognition field. As the amount of image data in imaging center of ophthalmology is increasing dramatically, analyzing and processing these data is in urgent need. AI has been tried to apply to decipher medical data and has made extraordinary progress in intelligent diagnosis. In this paper, we presented the basic workflow for building an AI model and systematically reviewed applications of AI in the diagnosis of eye diseases. Future work should focus on setting up systematic AI platforms to diagnose general eye diseases based on multimodal data in the real world.

The main function of ocular blood flow is to supply sufficient oxygen and nutrients to the eye. Local blood vessels resistance regulates overall blood distribution to the eye and can vary rapidly over time depending on ocular need. Under normal conditions, the relation between blood flow and perfusion pressure in the eye is autoregulated. Basically, autoregulation is a capacity to maintain a relatively constant level of blood flow in the presence of changes in ocular perfusion pressure and varied metabolic demand. In addition, ocular blood flow dysregulation has been demonstrated as an independent risk factor to many ocular diseases. For instance, ocular perfusion pressure plays key role in the progression of retinopathy such as glaucoma and diabetic retinopathy. In this review, different direct and indirect techniques to measure ocular blood flow and the effect of myogenic and neurogenic mechanisms on ocular blood flow are discussed. Moreover, ocular blood flow regulation in ocular disease will be described.

Background: Retinopathy of prematurity (ROP) is a leading cause of childhood blindness worldwide but can be a treatable retinal disease with appropriate and timely diagnosis. This study was performed to develop a robust intelligent system based on deep learning to automatically classify the severity of ROP from fundus images and detect the stage of ROP and presence of plus disease to enable automated diagnosis and further treatment. Methods: A total of 36,231 fundus images were labeled by 13 licensed retinal experts. A 101-layer convolutional neural network (ResNet) and a faster region-based convolutional neural network (Faster-RCNN) were trained for image classification and identification. We applied a 10-fold cross-validation method to train and optimize our algorithms. The accuracy, sensitivity, and specificity were assessed in a four-degree classification task to evaluate the performance of the intelligent system. The performance of the system was compared with results obtained by two retinal experts. Moreover, the system was designed to detect the stage of ROP and presence of plus disease as well as to highlight lesion regions based on an object detection network using Faster-RCNN. Results: The system achieved an accuracy of 0.903 for the ROP severity classification. Specifically, the accuracies in discriminating normal, mild, semi-urgent, and urgent were 0.883, 0.900, 0.957, and 0.870, respectively; the corresponding accuracies of the two experts were 0.902 and 0.898. Furthermore, our model achieved an accuracy of 0.957 for detecting the stage of ROP and 0.896 for detecting plus disease; the accuracies in discriminating stage I to stage V were 0.876, 0.942, 0.968, 0.998 and 0.999, respectively. Conclusions: Our system was able to detect ROP and differentiate four-level classification fundus images with high accuracy and specificity. The performance of the system was comparable to or better than that of human experts, demonstrating that this system could be used to support clinical decisions.

ON bipolar cells are critical for the function of the ON pathway in the visual system. They express a metabotropic glutamate receptor (mGluR6) that, when activated, couples to the G_oclass of G protein. The channel that is primarily responsible for the synaptic response has been recently identified as the transient receptor potential cation channel subfamily M member 1 (TRPM1); TRPM1 is negatively coupled to the mGluR6/Go cascade such that activation of the cascade results in closure of the channel. Light indirectly opens TRPM1 by reducing transmitter release from presynaptic photoreceptors, resulting in a decrease in mGluR6 activation. Conversely, in the dark, binding of synaptic glutamate to mGluR6 inhibits TRPM1 current. Closure of TRPM1 by G-protein activation in the dark is a critical step in the process of ON bipolar cell signal transduction, but the precise pathway linking these two events is not understood. To address this question, we measured TRPM1 activity in retinal bipolar cells, in human ependymal melanocytes (HEMs) that endogenously express TRPM1, and in HEK293 cells transfected with TRPM1. Dialysis of the Gβγ subunit dimer, but not Gα_o, closed TRPM1 channels in every cell type that we tested. In addition, activation of an endogenous G-protein–coupled receptor pathway in HEK293 cells that releases Gβγ without activating Go protein also closed TRPM1 channels. These results suggest a model in which the Gβγ dimer that is released as a result of the dissociation from Gα_oupon activation of mGluR6 closes the TRPM1 channel, perhaps via a direct interaction.