Question How does the performance of an automated deep learning algorithm compare with manual grading by ophthalmologists for identifying diabetic retinopathy in retinal fundus photographs? Finding In 2 validation sets of 9963 images and 1748 images, at the operating point selected for high specificity, the algorithm had 90.3% and 87.0% sensitivity and 98.1% and 98.5% specificity for detecting referable diabetic retinopathy, defined as moderate or worse diabetic retinopathy or referable macular edema by the majority decision of a panel of at least 7 US board-certified ophthalmologists. At the operating point selected for high sensitivity, the algorithm had 97.5% and 96.1% sensitivity and 93.4% and 93.9% specificity in the 2 validation sets. Meaning Deep learning algorithms had high sensitivity and specificity for detecting diabetic retinopathy and macular edema in retinal fundus photographs. Importance Deep learning is a family of computational methods that allow an algorithm to program itself by learning from a large set of examples that demonstrate the desired behavior, removing the need to specify rules explicitly. Application of these methods to medical imaging requires further assessment and validation. Objective To apply deep learning to create an algorithm for automated detection of diabetic retinopathy and diabetic macular edema in retinal fundus photographs. Design and Setting A specific type of neural network optimized for image classification called a deep convolutional neural network was trained using a retrospective development data set of 128 175 retinal images, which were graded 3 to 7 times for diabetic retinopathy, diabetic macular edema, and image gradability by a panel of 54 US licensed ophthalmologists and ophthalmology senior residents between May and December 2015.
India's largest eye care provider, Aravind Eye Hospital, has been quietly working for over four years with Google on a project to use artificial intelligence (AI) in ophthalmology. Aravind Eye Hospital, which has branches across India, is headquartered in Madurai, Tamil Nadu. Lily Peng, product manager at Google, who released a paper on the research a year ago, said at the 2017 WIRED Business Conference that Google had just finished a clinical study in India, and that work was underway to get the technology into routine use with patients. India, considered the diabetes capital of the world, has over 70 million diabetes patients who are at risk of blindness due to the disease. India's largest eye care provider, Aravind Eye Hospital, has been quietly working for over three to four years with Google on a project to use artificial intelligence in ophthalmology At the TensorFlow Dev Summit earlier this year, Peng had said that that Google's machine learning algorithm was very close to an ophthalmologist in terms of performance.
In an evaluation of retinal photographs from adults with diabetes, an algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy, according to a study published online by JAMA. Among individuals with diabetes, the prevalence of diabetic retinopathy is approximately 29 percent in the United States. Most guidelines recommend annual screening for those with no retinopathy or mild diabetic retinopathy and repeat examination in 6 months for moderate diabetic retinopathy. Retinal photography with manual interpretation is a widely accepted screening tool for diabetic retinopathy. Automated grading of diabetic retinopathy has potential benefits such as increasing efficiency and coverage of screening programs; reducing barriers to access; and improving patient outcomes by providing early detection and treatment.
Diabetes is a globally prevalent disease that can cause visible microvascular complications such as diabetic retinopathy and macular edema in the human eye retina, the images of which are today used for manual disease screening. This labor-intensive task could greatly benefit from automatic detection using deep learning technique. Here we present a deep learning system that identifies referable diabetic retinopathy comparably or better than presented in the previous studies, although we use only a small fraction of images ( 1/4) in training but are aided with higher image resolutions. We also provide novel results for five different screening and clinical grading systems for diabetic retinopathy and macular edema classification, including results for accurately classifying images according to clinical five-grade diabetic retinopathy and four-grade diabetic macular edema scales. These results suggest, that a deep learning system could increase the cost-effectiveness of screening while attaining higher than recommended performance, and that the system could be applied in clinical examinations requiring finer grading.