Department of Ophthalmology and Visual Sciences, School of Medicine, University of Louisville, Louisville, Kentucky, USA.
Faculty of Computers and Information, Mansoura University, Mansoura, Egypt.
Br J Ophthalmol. 2018 Nov;102(11):1564-1569. doi: 10.1136/bjophthalmol-2017-311489. Epub 2018 Jan 23.
Optical coherence tomography angiography (OCTA) is increasingly being used to evaluate diabetic retinopathy, but the interpretation of OCTA remains largely subjective. The purpose of this study was to design a computer-aided diagnostic (CAD) system to diagnose non-proliferative diabetic retinopathy (NPDR) in an automated fashion using OCTA images.
This was a two-centre, cross-sectional study. Adults with type II diabetes mellitus (DMII) were eligible for inclusion. OCTA scans of the macula were taken, and the five vascular maps generated per eye were analysed by a novel CAD system. For the purpose of classification/diagnosis, three different local features-blood vessel density, blood vessel calibre and the size of the foveal avascular zone (FAZ)-were segmented from these images and used to train a new, automated classifier.
One hundred and six patients with DMII were included in the study, 23 with no DR and 83 with mild NPDR. When using features of the superficial retinal map alone, the system demonstrated an accuracy of 80.0% and area under the curve (AUC) of 76.2%. Using the features of the deep retinal map alone, accuracy was 91.4% and AUC 89.2%. When data from both maps were combined, the presented CAD system demonstrated overall accuracy of 94.3%, sensitivity of 97.9%, specificity of 87.0%, area under curve (AUC) of 92.4% and dice similarity coefficient of 95.8%.
Automated diagnosis of NPDR using OCTA images is feasible and accurate. Combining this system with OCT data is a plausible next step that would likely improve its robustness.
光学相干断层扫描血管造影术（OCTA）越来越多地用于评估糖尿病视网膜病变，但 OCTA 的解读在很大程度上仍然是主观的。本研究的目的是设计一种计算机辅助诊断（CAD）系统，以便使用 OCTA 图像自动诊断非增生性糖尿病性视网膜病变（NPDR）。
这是一项在两个中心进行的横断面研究。符合条件的患者为患有 2 型糖尿病（DMII）的成年人。对黄斑 OCTA 扫描进行拍摄，并对每只眼睛生成的 5 个血管图进行分析。一种新的 CAD 系统用于分析。为了进行分类/诊断，从这些图像中分割出三个不同的局部特征-血管密度、血管口径和中心凹无血管区（FAZ）的大小，并使用这些特征来训练一个新的自动分类器。
研究共纳入 106 例 2 型糖尿病患者，其中 23 例无糖尿病视网膜病变，83 例为轻度 NPDR。仅使用浅层视网膜图的特征，系统的准确率为 80.0%，曲线下面积（AUC）为 76.2%。仅使用深层视网膜图的特征，准确率为 91.4%，AUC 为 89.2%。当结合两张图的数据时，所提出的 CAD 系统的总体准确率为 94.3%，灵敏度为 97.9%，特异性为 87.0%，AUC 为 92.4%，Dice 相似系数为 95.8%。
使用 OCTA 图像自动诊断 NPDR 是可行且准确的。将该系统与 OCT 数据相结合是下一步可行的方案，这可能会提高其稳健性。
