RAVIR: A Dataset and Methodology for the Semantic Segmentation and Quantitative Analysis of Retinal Arteries and Veins in Infrared Reflectance Imaging.

The retinal vasculature provides important clues in the diagnosis and monitoring of systemic diseases including hypertension and diabetes. The microvascular system is of primary involvement in such conditions, and the retina is the only anatomical site where the microvasculature can be directly observed. The objective assessment of retinal vessels has long been considered a surrogate biomarker for systemic vascular diseases, and with recent advancements in retinal imaging and computer vision technologies, this topic has become the subject of renewed attention. In this paper, we present a novel dataset, dubbed RAVIR, for the semantic segmentation of Retinal Arteries and Veins in Infrared Reflectance (IR) imaging. It enables the creation of deep learning-based models that distinguish extracted vessel type without extensive post-processing. We propose a novel deep learning-based methodology, denoted as SegRAVIR, for the semantic segmentation of retinal arteries and veins and the quantitative measurement of the widths of segmented vessels. Our extensive experiments validate the effectiveness of SegRAVIR and demonstrate its superior performance in comparison to state-of-the-art models. Additionally, we propose a knowledge distillation framework for the domain adaptation of RAVIR pretrained networks on color images. We demonstrate that our pretraining procedure yields new state-of-the-art benchmarks on the DRIVE, STARE, and CHASE_DB1 datasets. Dataset link: https://ravirdataset.github.io/data.

Review of Clinical and Operative Recommendations for Ophthalmology Practices During the COVID-19 Pandemic.

In response to climbing global case and fatality rates of the novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and its associated disease, COVID-19, ophthalmology practices have modified their clinical and operative approach to patient care in an attempt to reduce spread of the virus. The presence of SARS-CoV-2 viral RNA in the preocular tear film raises speculation that the ocular surface can act as an initial site of infection as well as a potential source of person-to-person viral transmission. More recently, conjunctival specimens and immunohistochemical analyses have identified the presence of cellular surface factors necessary for SARS-CoV-2 infection on the ocular surface. Together, these results highlight the importance of safety measures in ophthalmology practices to prevent transmission of SARS-CoV-2. As ophthalmic exams typically require close proximity between a patient's respiratory tract and the provider, clinical and surgical recommendations are aimed at reducing unnecessary patient-provider interactions. Subspecialty professional guidelines can be used to instruct ophthalmologists on the necessity of various procedures and best practice measures. Ophthalmology practice during the COVID-19 pandemic has been dramatically curtailed in an effort to reduce the risk of transmission and converse valuable personal protective equipment (PPE), and the impacts of the ongoing pandemic on ophthalmology practices will be felt for the foreseeable future.

Pericentral hydroxychloroquine retinopathy in a Caucasian female.

PURPOSE: To report a rare presentation of the pericentral pattern of hydroxychloroquine (HCQ) retinal toxicity in a Caucasian female. OBSERVATIONS: The patient presented with 20 years of exposure to HCQ, at a daily dose of 5.2mg/kg of actual body weight, and manifested a pericentral-only phenotype of HCQ toxicity, as demonstrated with detailed structural and functional testing. CONCLUSIONS AND IMPORTANCE: Although rare, the pericentral pattern of HCQ toxicity may occur in Caucasian patients in the absence of paracentral changes.