Department of Ophthalmology, Eye Hospital and School of Ophthalmology and Optometry, Wenzhou Medical University, Wenzhou, Zhejiang, China.
National Clinical Research Center for Ocular Disease, Wenzhou, Zhejiang, China ; and.
Retina. 2022 Oct 1;42(10):1965-1974. doi: 10.1097/IAE.0000000000003547.
To investigate the impact of penetration and image analysis in different optical coherence tomography (OCT) instruments on the measurement of choroidal vascularity parameters.
Twenty-three healthy volunteers were imaged using two swept-source OCTs and one spectral-domain OCT. A fully automatic segmentation method based on ResNet-UNet and Niblack local threshold binarization was performed to quantify the relevant choroidal vascular parameters, including choroidal vascularity index, total choroidal volume, and luminal volume. The intraclass correlation coefficient (ICC) and coefficient of repeatability (COR) were used to analyze the repeatability and consistency of automatic and manual segmentation, respectively.
Both swept-source OCT devices showed good consistency of luminal volume and total choroidal volume measurements (all ICC value >0.98 with COR% < 8.53%) based on manual segmentation, whereas the consistency of the spectral-domain OCT was lower (ICC value <0.60 with COR% > 40%), which was greatly improved after using the automatic algorithm (ICC value >0.99 with COR% < 4%). The repeatability of choroidal vascularity index obtained from different OCT images using manual or automatic segmentation showed good agreement (all ICC values >0.85), whereas the choroidal vascularity index measurement from the spectral-domain OCT was larger than the other two swept-source OCT devices (ICC value <0.65).
For healthy youngsters, the penetration of OCT plays a role in the measurement precision for choroidal vascularity parameters, and automatic segmentation can improve the ability of choroidal boundary identification with deficient penetration, suggesting these factors need to be considered in clinical work.
研究不同光学相干断层扫描（OCT）仪器的穿透深度和图像分析对脉络膜血管参数测量的影响。
对 23 名健康志愿者使用两台扫频源 OCT 和一台谱域 OCT 进行成像。采用基于 ResNet-UNet 和 Niblack 局部阈值二值化的全自动分割方法，定量测量相关脉络膜血管参数，包括脉络膜血管指数、脉络膜总体积和管腔体积。采用组内相关系数（ICC）和可重复性系数（COR）分别分析自动和手动分割的可重复性和一致性。
手动分割时，两种扫频源 OCT 设备的管腔体积和脉络膜总体积测量均具有良好的一致性（所有 ICC 值>0.98，COR%<8.53%），而谱域 OCT 的一致性较低（ICC 值<0.60，COR%>40%），使用自动算法后大大提高（ICC 值>0.99，COR%<4%）。手动或自动分割获得的不同 OCT 图像的脉络膜血管指数的重复性具有良好的一致性（所有 ICC 值>0.85），而谱域 OCT 的脉络膜血管指数测量值大于其他两种扫频源 OCT 设备（ICC 值<0.65）。
对于健康年轻人，OCT 的穿透深度对脉络膜血管参数的测量精度有一定影响，自动分割可以提高穿透深度不足时脉络膜边界识别能力，提示在临床工作中需要考虑这些因素。
