Xiong Honglian, You Qi Sheng, Guo Yukun, Wang Jie, Wang Bingjie, Gao Liqin, Flaxel Christina J, Bailey Steven T, Hwang Thomas S, Jia Yali
School of Physics and Optoelectronic Engineering, Foshan University, Foshan, Guangdong 528000, China.
Casey Eye Institute, Oregon Health & Science University, Portland, OR 97239, USA.
Br J Ophthalmol. 2023 Jan;107(1):84-89. doi: 10.1136/bjophthalmol-2020-318646. Epub 2021 Sep 13.
A deep-learning-based macular extrafoveal avascular area (EAA) on a 6×6 mm optical coherence tomography (OCT) angiogram is less dependent on the signal strength and shadow artefacts, providing better diagnostic accuracy for diabetic retinopathy (DR) severity than the commercial software measured extrafoveal vessel density (EVD).
To compare a deep-learning-based EAA to commercial output EVD in the diagnostic accuracy of determining DR severity levels from 6×6 mm OCT angiography (OCTA) scans.
The 6×6 mm macular OCTA scans were acquired on one eye of each participant with a spectral-domain OCTA system. After excluding the central 1 mm diameter circle, the EAA on superficial vascular complex was measured with a deep-learning-based algorithm, and the EVD was obtained with commercial software.
The study included 34 healthy controls and 118 diabetic patients. EAA and EVD were highly correlated with DR severity (ρ=0.812 and -0.577, respectively, both p<0.001) and visual acuity (r=-0.357 and 0.420, respectively, both p<0.001). EAA had a significantly (p<0.001) higher correlation with DR severity than EVD. With the specificity at 95%, the sensitivities of EAA for differentiating diabetes mellitus (DM), DR and severe DR from control were 80.5%, 92.0% and 100.0%, respectively, significantly higher than those of EVD 11.9% (p=0.001), 13.6% (p<0.001) and 15.8% (p<0.001), respectively. EVD was significantly correlated with signal strength index (SSI) (r=0.607, p<0.001) and shadow area (r=-0.530, p<0.001), but EAA was not (r=-0.044, p=0.805 and r=-0.046, p=0.796, respectively). Adjustment of EVD with SSI and shadow area lowered sensitivities for detection of DM, DR and severe DR.
Macular EAA on 6×6 mm OCTA measured with a deep learning-based algorithm is less dependent on the signal strength and shadow artefacts, and provides better diagnostic accuracy for DR severity than EVD measured with the instrument-embedded software.
基于深度学习的6×6毫米光学相干断层扫描血管造影（OCTA）黄斑中心凹外无血管区（EAA）对信号强度和阴影伪像的依赖性较小，在诊断糖尿病视网膜病变（DR）严重程度方面比商业软件测量的中心凹外血管密度（EVD）具有更高的诊断准确性。
比较基于深度学习的EAA与商业输出的EVD在通过6×6毫米OCT血管造影（OCTA）扫描确定DR严重程度水平的诊断准确性。
使用光谱域OCTA系统采集每位参与者一只眼睛的6×6毫米黄斑OCTA扫描图像。排除中心直径1毫米的圆后，使用基于深度学习的算法测量浅层血管复合体的EAA，并使用商业软件获得EVD。
该研究纳入了34名健康对照者和118名糖尿病患者。EAA和EVD与DR严重程度（分别为ρ=0.812和-0.577，均p<0.001）以及视力（分别为r=-0.357和0.420，均p<0.001）高度相关。EAA与DR严重程度的相关性显著高于EVD（p<0.001）。在特异性为95%时，EAA区分糖尿病（DM）、DR和重度DR与对照组的敏感性分别为80.5%、92.0%和100.0%，显著高于EVD的11.9%（p=0.001）、13.6%（p<0.001）和15.8%（p<0.001）。EVD与信号强度指数（SSI）（r=0.607，p<0.001）和阴影面积（r=-0.530，p<0.001）显著相关，但EAA与它们无关（分别为r=-0.044，p=0.805和r=-0.046，p=0.796）。用SSI和阴影面积对EVD进行校正会降低检测DM、DR和重度DR的敏感性。
基于深度学习算法测量的6×6毫米OCTA黄斑EAA对信号强度和阴影伪像的依赖性较小，在诊断DR严重程度方面比仪器嵌入式软件测量的EVD具有更高的诊断准确性。
