Characterization of retinal arteries by adaptive optics ophthalmoscopy image analysis.

OBJECTIVE: This paper aims at quantifying biomarkers from the segmentation of retinal arteries in adaptive optics ophthalmoscopy images (AOO). METHODS: The segmentation is based on the combination of deep learning and knowledge-driven deformable models to achieve a precise segmentation of the vessel walls, with a specific attention to bifurcations. Biomarkers (junction coefficient, branching coefficient, wall to lumen ratio (wlr) are derived from the resulting segmentation. RESULTS: reliable and accurate segmentations (mse = 1.75 ± 1.24 pixel) and measurements are obtained, with high reproducibility with respect to images acquisition and users, and without bias. SIGNIFICANCE: In a preliminary clinical study of patients with a genetic small vessel disease, some of them with vascular risk factors, an increased wlr was found in comparison to a control population. CONCLUSION: The wlr estimated in AOO images with our method (AOV, Adaptive Optics Vessel analysis) seems to be a very robust biomarker as long as the wall is well contrasted.

[Imaging of retinal arteries with adaptative optics, feasibility and reproducibility]. / Imagerie des artérioles rétiniennes par optique adaptative, faisabilité et reproductibilité.

OBJECTIVE: Adaptative optic is a new non-invasive imaging technique that allows to measure arterioles wall thickness and diameter with a resolution near two microns. Our objectives were to evaluate the feasibility and the reproducibility of this technique in untreated hypertensive patients. DESIGN AND METHODS: In 23 naive hypertensive patients and in 14 normotensives, the internal diameter (ID) and the wall thickness of the superior temporal artery were automatically measured. Those measurements were made on a temporal artery segment and led to determine a whole vessel cross sectional area (WCSA) and a wall to lumen ratio (WLR). Intra-observer reproducibility was evaluated by realizing three consecutive measurements in 14 subjects. Inter-observer reproducibility was assessed by two independent readers in 17 patients. Variation coefficient was calculated as SD/mean values. A comparison of retinal parameters was made between normal and hypertensive subjects. RESULTS: Inter-observer reproducibility indicated a variation coefficient of 1.3% for ID, 3.7% for the WCSA and 3.2% for the WLR. Intra-observer reproducibility indicated a variation coefficient of 3.2% for the WLR. Arterial remodeling was present in hypertensive patients at baseline with a significantly increased WLR as compared to normal subjects (0.32 ± 0.04 vs. 0.26 ± 0.04; P<0.05), both population having the same ID. CONCLUSION: Adaptative optics is feasible and reproducible technique. The possibility of a direct and non-invasive assessment of retinal arterioles must assess the attractions in this technique in hypertensive patients' care.