Optical coherence tomography angiography (OCTA) is a noninvasive method of 3D imaging of the retinal and choroidal circulations. However, vascular depth discrimination is limited by superficial vessels projecting flow signal artifact onto deeper layers. The projection-resolved (PR) OCTA algorithm improves depth resolution by removing projection artifact while retaining in-situ flow signal from real blood vessels in deeper layers. This novel technology allowed us to study the normal retinal vasculature in vivo with better depth resolution than previously possible. Our investigation in normal human volunteers revealed the presence of 2 to 4 distinct vascular plexuses in the retina, depending on location relative to the optic disc and fovea. The vascular pattern in these retinal plexuses and interconnecting layers are consistent with previous histologic studies. Based on these data, we propose an improved system of nomenclature and segmentation boundaries for detailed 3-dimensional retinal vascular anatomy by OCTA. This could serve as a basis for future investigation of both normal retinal anatomy, as well as vascular malformations, nonperfusion, and neovascularization.

Artificial intelligence (AI) based on deep learning (DL) has sparked tremendous global interest in recent years. DL has been widely adopted in image recognition, speech recognition and natural language processing, but is only beginning to impact on healthcare. In ophthalmology, DL has been applied to fundus photographs, optical coherence tomography and visual fields, achieving robust classification performance in the detection of diabetic retinopathy and retinopathy of prematurity, the glaucoma-like disc, macular oedema and age-related macular degeneration. DL in ocular imaging may be used in conjunction with telemedicine as a possible solution to screen, diagnose and monitor major eye diseases for patients in primary care and community settings. Nonetheless, there are also potential challenges with DL application in ophthalmology, including clinical and technical challenges, explainability of the algorithm results, medicolegal issues, and physician and patient acceptance of the AI ‘black-box’ algorithms. DL could potentially revolutionise how ophthalmology is practised in the future. This review provides a summary of the state-of-the-art DL systems described for ophthalmic applications, potential challenges in clinical deployment and the path forward.

Retinopathy of prematurity (ROP) is a retinal vasoproliferative disease that affects premature infants. Despite improvements in neonatal care and management guidelines, ROP remains a leading cause of childhood blindness worldwide. Current screening guidelines are primarily based on two risk factors: birth weight and gestational age; however, many investigators have suggested other risk factors, including maternal factors, prenatal and perinatal factors, demographics, medical interventions, comorbidities of prematurity, nutrition, and genetic factors. We review the existing literature addressing various possible ROP risk factors. Although there have been contradictory reports, and the risk may vary between different populations, understanding ROP risk factors is essential to develop predictive models, to gain insights into pathophysiology of retinal vascular diseases and diseases of prematurity, and to determine future directions in management of and research in ROP.

; for the Imaging and Informatics in Retinopathy of Prematurity (i-ROP) Research Consortium IMPORTANCE Retinopathy of prematurity (ROP) is a leading cause of childhood blindness worldwide. The decision to treat is primarily based on the presence of plus disease, defined as dilation and tortuosity of retinal vessels. However, clinical diagnosis of plus disease is highly subjective and variable. OBJECTIVE To implement and validate an algorithm based on deep learning to automatically diagnose plus disease from retinal photographs. DESIGN, SETTING, AND PARTICIPANTS A deep convolutional neural network was trained using a data set of 5511 retinal photographs. Each image was previously assigned a reference standard diagnosis (RSD) based on consensus of image grading by 3 experts and clinical diagnosis by 1 expert (ie, normal, pre-plus disease, or plus disease). The algorithm was evaluated by 5-fold cross-validation and tested on an independent set of 100 images. Images were collected from 8 academic institutions participating in the Imaging and Informatics in ROP (i-ROP) cohort study. The deep learning algorithm was tested against 8 ROP experts, each of whom had more than 10 years of clinical experience and more than 5 peer-reviewed publications about ROP.

Shadowgraphic projection artifacts from superficial vasculature interfere with the visualization of deeper vascular networks in optical coherence tomography angiography (OCT-A). We developed a novel algorithm to remove this artifact by resolving the ambiguity between in situ and projected flow signals. The algorithm identifies voxels with in situ flow as those where intensity-normalized decorrelation values are higher than all shallower voxels in the same axial scan line. This "projection-resolved" (PR) algorithm effectively suppressed the projection artifact on both en face and cross-sectional angiograms and enhanced depth resolution of vascular networks. In the human macula, the enhanced angiograms show three distinct vascular plexuses in the inner retina and no vessels in the outer retina. We demonstrate that PR OCT-A cleanly removes flow projection from the normally avascular outer retinal slab while preserving the density and continuity of the intermediate and deep retinal capillary plexuses.