Diabetic retinopathy (DR) is the leading cause of preventable blindness worldwide. The risk of DR progression is highly variable among different individuals, making it difficult to predict risk and personalize screening intervals. We developed and validated a deep learning system (DeepDR Plus) to predict time to DR progression within 5 years solely from fundus images. First, we used 717,308 fundus images from 179,327 participants with diabetes to pretrain the system. Subsequently, we trained and validated the system with a multiethnic dataset comprising 118,868 images from 29,868 participants with diabetes. For predicting time to DR progression, the system achieved concordance indexes of 0.754–0.846 and integrated Brier scores of 0.153–0.241 for all times up to 5 years. Furthermore, we validated the system in real-world cohorts of participants with diabetes. The integration with clinical workflow could potentially extend the mean screening interval from 12 months to 31.97 months, and the percentage of participants recommended to be screened at 1–5 years was 30.62%, 20.00%, 19.63%, 11.85% and 17.89%, respectively, while delayed detection of progression to vision-threatening DR was 0.18%. Altogether, the DeepDR Plus system could predict individualized risk and time to DR progression over 5 years, potentially allowing personalized screening intervals.

Deep learning has achieved remarkable success in the optical coherence tomography (OCT) image classification task with substantial labelled B-scan images available. However, obtaining such fine-grained expert annotations is usually quite difficult and expensive. How to leverage the volume-level labels to develop a robust classifier is very appealing. In this paper, we propose a weakly deep supervised learning framework with uncertainty estimation to address the macula-related disease classification problem from OCT images with only volume-level label being available. First, a convolutional neural network (CNN) based instance-level classifier is iteratively refined by using the proposed uncertainty-driven deep multiple instance learning scheme. To our best knowledge, we are the first to incorporate the uncertainty evaluation mechanism into multiple instance learning (MIL) for training a robust instance classifier. The classifier is able to detect suspicious abnormal instances and abstract the corresponding deep embedding with high representation capability simultaneously. Second, a recurrent neural network (RNN) takes instance features from the same bag as input and generates the final bag-level prediction by considering the individually local instance information and globally aggregated bag-level representation. For more comprehensive validation, we built two large diabetic macular edema (DME) OCT datasets from different devices and imaging protocols to evaluate the efficacy of our method}, which are composed of 30,151 B-scans in 1,396 volumes from 274 patients (Heidelberg-DME dataset) and 38,976 B-scans in 3,248 volumes from 490 patients (Triton-DME dataset), respectively. We compare the proposed method with the state-of-the-art approaches, and experimentally demonstrate that our method is superior to alternative methods, achieving volume-level accuracy, F1-score and area under receiver operating characteristic curve (AUC) of 95.1%, 93.9% and 99.0% on Heidelberg-DME and those of 95.1%, 93.5% and 98.6% on Triton-DME, respectively. Furthermore, the proposed method also yields competitive results on another public age-related macular degeneration OCT dataset, indicating the high potential as an effective screening tool in the clinical practice.

Optical coherence tomography angiography (OCT-A) provides depth-resolved visualization of the retinal microvasculature without intravenous dye injection. It facilitates investigations of various retinal vascular diseases and glaucoma by assessment of qualitative and quantitative microvascular changes in the different retinal layers and radial peripapillary layer non-invasively, individually, and efficiently. Deep learning (DL), a subset of artificial intelligence (AI) based on deep neural networks, has been applied in OCT-A image analysis in recent years and achieved good performance for different tasks, such as image quality control, segmentation, and classification. DL technologies have further facilitated the potential implementation of OCT-A in eye clinics in an automated and efficient manner and enhanced its clinical values for detecting and evaluating various vascular retinopathies. Nevertheless, the deployment of this combination in real-world clinics is still in the “proof-of-concept” stage due to several limitations, such as small training sample size, lack of standardized data preprocessing, insufficient testing in external datasets, and absence of standardized results interpretation. In this review, we introduce the existing applications of DL in OCT-A, summarize the potential challenges of the clinical deployment, and discuss future research directions.

Current brain imaging to detect silent brain infarctions (SBIs) is not feasible for the general population. Here, to overcome this challenge, we developed a retinal image-based deep learning system, DeepRETStroke, to detect SBI and refine stroke risk. We use 895,640 retinal photographs to pretrain the DeepRETStroke system, which encodes a domain-specific foundation model for representing eye–brain connections. Then, we validated the downstream clinical tasks of DeepRETStroke using 213,762 retinal photographs from diverse datasets across China, Singapore, Malaysia, the USA, the UK and Denmark to detect SBI and predict stroke events. DeepRETStroke performed well in internal validation datasets, with areas under the curve of 0.901 for predicting incident stroke and 0.769 for predicting recurrent stroke. External validations demonstrated consistent performances across diverse datasets. Finally, in a prospective study comprising 218 participants with stroke, we assessed the performance of DeepRETStroke compared with clinical traits in guiding strategies for stroke recurrence prevention. Altogether, the retinal image-based deep learning system, DeepRETStroke, is superior to clinical traits in predicting stroke events, especially by incorporating the detection of SBI, without the need for brain imaging.