文献速递眼底病与葡萄膜炎

使用光学相干断层扫描血管成像自动检测糖尿病视网膜病变:一项先导研究

Automated diabetic retinopathy detection using optical coherence tomography angiography: a pilot study.
PubMed 文献 · Br J Ophthalmol · 2018-01-23

这项两中心横断面研究纳入106例II型糖尿病患者(23例无糖尿病视网膜病变,83例轻度非增殖性糖尿病视网膜病变),利用光学相干断层扫描血管成像(OCTA)黄斑扫描生成的五幅血管图,提取血管密度、血管管径和中心凹无血管区(FAZ)大小三类局部特征训练自动化分类器。联合浅层和深层视网膜图特征时,系统总体准确率94.3%、敏感度97.9%、特异度87.0%、AUC 92.4%。作者认为基于OCTA图像的NPDR自动诊断可行且准确。

要点

  • 联合浅层和深层视网膜图特征时,CAD系统诊断轻度NPDR的总体准确率为94.3%、敏感度为97.9%、特异度为87.0%。
  • 仅用浅层视网膜图特征时准确率80.0%、AUC 76.2%;仅用深层视网膜图特征时准确率91.4%、AUC 89.2%。
  • 作者认为基于OCTA图像的NPDR自动诊断可行且准确,将本系统与OCT数据结合是合理的下一步。

核心结论

  • 使用OCTA图像自动诊断NPDR是可行且准确的。
  • 作者认为将本系统与OCT数据结合是合理的下一步,可能提高其稳健性。

研究设计与样本

  • 这是一项两中心横断面研究,纳入II型糖尿病成人患者。
  • 对黄斑进行OCTA扫描,每只眼生成五幅血管图,由新型计算机辅助诊断(CAD)系统分析。
  • 从图像中分割出血管密度、血管管径和中心凹无血管区(FAZ)大小三类局部特征,用于训练新的自动化分类器。
  • 共纳入106例II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。

主要发现

  • 仅使用浅层视网膜图特征时,系统准确率为80.0%,AUC为76.2%。
  • 仅使用深层视网膜图特征时,准确率为91.4%,AUC为89.2%。
  • 联合两幅图的数据时,CAD系统总体准确率为94.3%,敏感度为97.9%,特异度为87.0%,AUC为92.4%,Dice相似系数为95.8%。

关键数值与推荐

  • 联合浅层和深层视网膜图特征时,CAD系统诊断轻度NPDR的总体准确率为94.3%、敏感度为97.9%、特异度为87.0%、AUC为92.4%。
  • 仅用浅层视网膜图特征时准确率为80.0%、AUC为76.2%;仅用深层视网膜图特征时准确率为91.4%、AUC为89.2%。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: 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. METHODS: 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. RESULTS: 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%. CONCLUSION: 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.

来源:Br J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Sandhu HS, Eladawi N, Elmogy M, et al. Automated diabetic retinopathy detection using optical coherence tomography angiography: a pilot study. Br J Ophthalmol. 2018. PMID: 29363532. doi:10.1136/bjophthalmol-2017-311489

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。