SWEPT-SOURCE OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY ASSESSMENT OF FELLOW EYES IN COATS DISEASE.

PURPOSE: To assess foveal and parafoveal vasculature at superficial capillary plexus (SCP), deep capillary plexus, and choriocapillaris using optical coherence tomography angiography in the fellow eyes of patients with Coats disease. METHODS: Observational and prospective case series. Thirteen patients with unilateral Coats and 14 healthy age- and sex-matched controls were consecutively recruited at Manchester Royal Eye Hospital and the Department of Ophthalmology of San Raffaele Hospital. Both groups underwent complete ophthalmologic examination, including optical coherence tomography angiography (Topcon Corp) 3 mm × 3 mm scans. Images were imported into ImageJ software and binarized; foveal avascular zone area was manually outlined and vessel density analyzed in inner (foveal) and outer (parafoveal) areas of SCP, deep capillary plexus, and choriocapillaris. RESULTS: Fellow eyes disclosed a significant increase in the foveal vessel density of SCP (P = 0.04); in particular, superior and temporal quadrants showed more marked alterations (P = 0.02 and 0.04, respectively). Analysis of foveal avascular zone area revealed a significant enlargement in the SCP (P = 0.04). No correlation was found between fellow eyes and the stage of affected eyes. CONCLUSION: Fellow eyes of Coats patients carry quantitative foveal vascular alterations at SCP. These may represent markers of altered inner blood-retinal barrier, due to a bilateral defect in midcapillary angiogenesis.

Differentiation of Diabetic Status Using Statistical and Machine Learning Techniques on Optical Coherence Tomography Angiography Images.

Purpose: To investigate the potential of statistical and machine learning approaches to determine the diabetic status of patients from optical coherence tomography angiography (OCT-A) images. Methods: This was a retrospective cross-sectional observational study based at Manchester Royal Eye Hospital, United Kingdom. OCT-A scans were sequentially selected from one eye of each of 182 patients who were either not diabetic, diabetic without retinopathy, or diabetic with retinopathy requiring hospital follow-up. Eligible images were analyzed by expert purpose-built automated algorithms to calculate clinically relevant outcome measures. These were used in turn as inputs to machine learning and statistical procedures to derive algorithms to perform clinically relevant classifications of patient images into the clinical groups. Receiver operating characteristic curves for the classifiers were evaluated and predictive accuracy assessed using area under curve (AUC). Results: For distinguishing diabetic patients from those without diabetes, the Random Forest classifier provided the highest AUC (0.8). For distinguishing diabetic patients with significant retinopathy from those with no retinopathy, the highest AUC was represented by logistic regression (0.91). Conclusions: The study demonstrates the potential of novel techniques using automated analysis of OCT-A scans to diagnose patients with diabetes, or when diabetic status is known, to automatically determine those that require hospital input. Translational Relevance: This work advances the concept of a rapid and noninvasive clinical screening tool using OCT-A to determine a patient's diabetic status.