Many conditions affecting the heart, brain, and even the eyes have their origins in blood vessel pathology, underscoring the role of vascular regulation. In age-related macular degeneration (AMD), there is excessive growth of abnormal blood vessels in the eye (choroidal neovascularization), eventually leading to vision loss due to detachment of retinal pigmented epithelium. As the advanced stage of this disease involves loss of retinal pigmented epithelium, much less attention has been given to early vascular events such as endothelial dysfunction. Although current gold standard therapy using inhibitors of vascular endothelial growth factor (VEGF) have achieved initial successes, some drawbacks include the lack of long-term restoration of visual acuity, as well as a subset of the patients being refractory to existing treatment, alluding us and others to hypothesize upon VEGF-independent mechanisms. Against this backdrop, we present here a nonexhaustive review on the vascular underpinnings of AMD, implications with genetic and systemic factors, experimental models for studying choroidal neovascularization, and interestingly, on both endothelial-centric pathways and noncell autonomous mechanisms. We hope to shed light on future research directions in improving vascular function in ocular disorders.

Deep learning (DL)-based retinal image quality assessment (RIQA) algorithms have been gaining popularity, as a solution to reduce the frequency of diagnostically unusable images. Most existing RIQA tools target retinal conditions, with a dearth of studies looking into RIQA models for optic nerve head (ONH) disorders. The recent success of DL systems in detecting ONH abnormalities on color fundus images prompts the development of tailored RIQA algorithms for these specific conditions. In this review, we discuss recent progress in DL-based RIQA models in general and the need for RIQA models tailored for ONH disorders. Finally, we propose suggestions for such models in the future.

The quality of ocular fundus photographs can affect the accuracy of the morphologic assessment of the optic nerve head (ONH), either by humans or by deep learning systems (DLS). In order to automatically identify ONH photographs of optimal quality, we have developed, trained, and tested a DLS, using an international, multicentre, multi-ethnic dataset of 5015 ocular fundus photographs from 31 centres in 20 countries participating to the Brain and Optic Nerve Study with Artificial Intelligence (BONSAI). The reference standard in image quality was established by three experts who independently classified photographs as of “good”, “borderline”, or “poor” quality. The DLS was trained on 4208 fundus photographs and tested on an independent external dataset of 807 photographs, using a multi-class model, evaluated with a one-vs-rest classification strategy. In the external-testing dataset, the DLS could identify with excellent performance “good” quality photographs (AUC = 0.93 (95% CI, 0.91–0.95), accuracy = 91.4% (95% CI, 90.0–92.9%), sensitivity = 93.8% (95% CI, 92.5–95.2%), specificity = 75.9% (95% CI, 69.7–82.1%) and “poor” quality photographs (AUC = 1.00 (95% CI, 0.99–1.00), accuracy = 99.1% (95% CI, 98.6–99.6%), sensitivity = 81.5% (95% CI, 70.6–93.8%), specificity = 99.7% (95% CI, 99.6–100.0%). “Borderline” quality images were also accurately classified (AUC = 0.90 (95% CI, 0.88–0.93), accuracy = 90.6% (95% CI, 89.1–92.2%), sensitivity = 65.4% (95% CI, 56.6–72.9%), specificity = 93.4% (95% CI, 92.1–94.8%). The overall accuracy to distinguish among the three classes was 90.6% (95% CI, 89.1–92.1%), suggesting that this DLS could select optimal quality fundus photographs in patients with neuro-ophthalmic and neurological disorders affecting the ONH.