Correlation of Vascular and Fluid-Related Parameters in Neovascular Age-Related Macular Degeneration Using Deep Learning

AI Generated Summary*

Fifty-four eyes of 54 treatment-naive patients with type 1 or 2 macular neovascularization from age-related macular degeneration were imaged at baseline and one month after a single aflibercept injection. A convolutional neural network quantified intraretinal and subretinal fluid on SD-OCT within the central 6 mm, while AngioTool analysis of swept-source OCTA images yielded nine vascular metrics, including lesion size, vessel density, endpoints and lacunarity. Median total fluid fell from 173.7 nl to 5.0 nl, while vascular metrics did not change significantly. Baseline fluid correlated weakly with endpoint count (R2 = 0.17) and subretinal fluid with several metrics (R2 0.08 to 0.20). No parameter correlated with relative fluid reduction, and investigators judged lesion morphology a minor contributor to exudation.

*This summary was generated by AI and is published unedited. Oku does not alter these summaries. It may contain errors or omissions and is provided for general informational purposes only. Oku does not guarantee its accuracy, completeness, or reliability. For authoritative information, please refer to the original, peer-reviewed article.