背景:近视影响全世界14亿人。值得注意的是,越来越多的证据表明脉络膜厚度在近视和近视相关疾病发展风险中起重要作用.随着人工智能(AI)的进步,脉络膜厚度分割现在可以自动化,提供固有的优势,如更好的可重复性,降低分级机的变异性,减少对人力的依赖。因此,我们的目的是使用两个扫频源光学相干断层扫描(OCT)系统评估AI自动和人工分割测量中心凹下脉络膜厚度(SFCT)之间的一致性.
方法:年龄≥16岁的受试者,双眼近视≥0.50屈光度,从新加坡前瞻性近视队列研究(PROMYSE)招募。使用TritonDRI-OCT和PLEXElite9000获得OCT扫描。使用已建立的SA-Net架构自动分割OCT图像,并使用标准技术手动分割,由两个独立的分级者进行裁决。随后基于分割确定SFCT。Bland-Altman图和组内相关系数(ICC)用于评估协议。
结果:共纳入229名受试者(456只眼),平均[±标准差(SD)]年龄为34.1(10.4)岁。使用TritonDRI-OCT,基于手动分割的总体SFCT(平均值±SD)为216.9±82.7µm,使用PLEXElite9000,为239.3±84.3µm。ICC值显示AI自动和手动分段SFCT测量之间具有极好的一致性(PLEXElite9000:ICC=0.937,95%CI:0.922至0.949,P<0.001;TritonDRI-OCT:ICC=0.887,95%CI:0.608至0.950,P<0.001)。对于PLEXElite9000,与AI自动分段测量相比,手动分段测量通常更厚。固定偏倚为6.3µm(95%CI:3.8至8.9,P<0.001),比例偏倚为0.120(P<0.001)。另一方面,TritonDRI-OCT的手动分段测量比AI自动分段测量相对更薄,固定偏倚为-26.7µm(95%CI:-29.7至-23.7,P<0.001),比例偏倚为-0.090(P<0.001)。
结论:我们观察到在脉络膜分割测量中,当比较手动和AI自动化技术时,使用来自两个SS-OCT系统的图像。鉴于其相对于手动分割的优势,自动分割可能会成为未来脉络膜厚度测量的主要方法。
BACKGROUND: Myopia affects 1.4 billion individuals worldwide. Notably, there is increasing evidence that choroidal thickness plays an important role in myopia and risk of developing myopia-related conditions. With the advancements in artificial intelligence (AI), choroidal thickness segmentation can now be automated, offering inherent advantages such as better repeatability, reduced grader variability, and less reliance for manpower. Hence, we aimed to evaluate the agreement between AI-automated and manual segmented measurements of subfoveal choroidal thickness (SFCT) using two swept-source optical coherence tomography (OCT) systems.
METHODS: Subjects aged ≥ 16 years, with myopia of ≥ 0.50 diopters in both eyes, were recruited from the Prospective Myopia Cohort Study in Singapore (PROMYSE). OCT scans were acquired using Triton DRI-OCT and PLEX Elite 9000. OCT images were segmented both automatically with an established SA-Net architecture and manually using a standard technique with adjudication by two independent graders. SFCT was subsequently determined based on the segmentation. The Bland-Altman plot and intraclass correlation coefficient (ICC) were used to evaluate the agreement.
RESULTS: A total of 229 subjects (456 eyes) with mean [± standard deviation (SD)] age of 34.1 (10.4) years were included. The overall SFCT (mean ± SD) based on manual segmentation was 216.9 ± 82.7 µm with Triton DRI-OCT and 239.3 ± 84.3 µm with PLEX Elite 9000. ICC values demonstrated excellent agreement between AI-automated and manual segmented SFCT measurements (PLEX Elite 9000: ICC = 0.937, 95% CI: 0.922 to 0.949, P < 0.001; Triton DRI-OCT: ICC = 0.887, 95% CI: 0.608 to 0.950, P < 0.001). For PLEX Elite 9000, manual segmented measurements were generally thicker when compared to AI-automated segmented measurements, with a fixed bias of 6.3 µm (95% CI: 3.8 to 8.9, P < 0.001) and proportional bias of 0.120 (P < 0.001). On the other hand, manual segmented measurements were comparatively thinner than AI-automated segmented measurements for Triton DRI-OCT, with a fixed bias of - 26.7 µm (95% CI: - 29.7 to - 23.7, P < 0.001) and proportional bias of - 0.090 (P < 0.001).
CONCLUSIONS: We observed an excellent agreement in choroidal segmentation measurements when comparing manual with AI-automated techniques, using images from two SS-OCT systems. Given its edge over manual segmentation, automated segmentation may potentially emerge as the primary method of choroidal thickness measurement in the future.