Diabetic retinopathy (DR) is a common eye disease and a significant cause of blindness in diabetic patients. Regular screening with fundus photography and timely intervention is the most effective way to manage the disease. The large population of diabetic patients and their massive screening requirements have generated interest in a computer-aided and fully automatic diagnosis of DR. Deep neural networks, on the other hand, have brought many breakthroughs in various tasks in the recent years. To automate the diagnosis of DR and provide appropriate suggestions to DR patients, we have built a dataset of DR fundus images that have been labeled by the proper treatment method that is required. Using this dataset, we trained deep convolutional neural network models to grade the severities of DR fundus images. We were able to achieve an accuracy of 88.72% for a four-degree classification task in the experiments. We deployed our models on a cloud computing platform and provided pilot DR diagnostic services for several hospitals; in the clinical evaluation, the system achieved a consistency rate of 91.8% with ophthalmologists, demonstrating the effectiveness of our work. INDEX TERMS Diabetic retinopathy, automatic diagnosis, deep neural networks.
Background
Retinopathy of prematurity (ROP) is the leading cause of childhood blindness worldwide. Automated ROP detection system is urgent and it appears to be a safe, reliable, and cost-effective complement to human experts.
Methods
An automated ROP detection system called DeepROP was developed by using Deep Neural Networks (DNNs). ROP detection was divided into ROP identification and grading tasks. Two specific DNN models, i.e., Id-Net and Gr-Net, were designed for identification and grading tasks, respectively. To develop the DNNs, large-scale datasets of retinal fundus images were constructed by labeling the images of ROP screenings by clinical ophthalmologists.
Findings
On the test dataset, the Id-Net achieved a sensitivity of 96.62%(95%CI, 92.29%–98.89%) and a specificity of 99.32% (95%CI, 96.29%–9.98%) for ROP identification while the Gr-Net attained sensitivity and specificity values of 88.46% (95%CI, 96.29%–99.98%) and 92.31% (95%CI, 81.46%–97.86%), respectively, on the ROP grading task. On another 552 cases, the developed DNNs outperformed some human experts. In a clinical setting, the sensitivity and specificity values of DeepROP for ROP identification were 84.91% (95%CI, 76.65%–91.12%) and 96.90% (95%CI, 95.49%–97.96%), respectively, whereas the corresponding measures for ROP grading were 93.33%(95%CI, 68.05%–99.83%) and 73.63%(95%CI, 68.05%–99.83%), respectively.
Interpretation
We constructed large-scale ROP datasets with adequate clinical labels and proposed novel DNN models. The DNN models can directly learn ROP features from big data. The developed DeepROP is potential to be an efficient and effective system for automated ROP screening.
Fund
National Natural Science Foundation of China under Grant 61432012 and U1435213.
Retinopathy of Prematurity (ROP) is a retinal vasproliferative disorder disease principally observed in infants born prematurely with low birth weight. ROP is an important cause of childhood blindness. Although automatic or semiautomatic diagnosis of ROP has been conducted, most previous studies have focused on "plus" disease, which is indicated by abnormalities of retinal vasculature. Few studies have reported methods for identifying the "stage" of ROP disease. Deep neural networks have achieved impressive results in many computer vision and medical image analysis problems, raising expectations that it might be a promising tool in automatic diagnosis of ROP. In this paper, convolutional neural networks (CNNs) with novel architecture is proposed to recognize the existence and severity of ROP disease per-examination. The severity of ROP is divided into mild and severe cases according to the disease progression. The proposed architecture consists of two sub-networks connected by a feature aggregate operator. The first sub-network is designed to extract high-level features from images of the fundus. These features from different images in an examination are fused by the aggregate operator, then used as the input for the second subnetwork to predict its class. A large dataset imaged by RetCam 3 is used to train and evaluate the model. The high classification accuracy in the experiment demonstrates the effectiveness of proposed architecture for recognizing ROP disease.
The current results suggest that 27G PPV system is a safe and effective treatment for various vitreoretinal diseases. When learning to perform 27G PPV, surgeons may encounter a learning curve and should gradually expand surgical indications from easy to pathologically complicated cases.
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.