文献速递眼底病与葡萄膜炎

人工智能算法与人工分级在糖尿病视网膜病变诊断中的准确性比较:广域真彩共焦扫描与标准数字视网膜图像

Diagnostic accuracy of diabetic retinopathy grading by an artificial intelligence-enabled algorithm compared with a human standard for wide-field true-colour confocal scanning and standard digital retinal images.
PubMed 文献 · Br J Ophthalmol · 2020-05-06

本研究为横断面研究,连续纳入1257例年度糖尿病眼筛查患者,比较EyeArt V.2.1.0自动视网膜图像分析软件在EIDON广域真彩共焦扫描图像与标准NDESP图像上的分级性能,以人工分级标准NDESP图像为参考标准。结果显示,EIDON图像上任何视网膜病变的敏感度为92.27%(95%CI:88.43%~94.69%),威胁视力视网膜病变为99%(95%CI:95.35%~100%),增殖性视网膜病变为100%(95%CI:61%~100%);标准图像上相应敏感度分别为92.26%(95%CI:88.37%~94.69%)、100%(95%CI:99.53%~100%)和100%(95%CI:61%~100%)。结论认为EyeArt在EIDON图像上的敏感度与标准图像相似,超过筛查试验推荐的敏感度阈值。

要点

  • EyeArt在EIDON与标准NDESP图像上检测任何视网膜病变的敏感度均约为92%。
  • 威胁视力视网膜病变敏感度:EIDON图像99%,标准图像100%。
  • EIDON图像分析中漏诊1例威胁视力视网膜病变(R1M1),标准图像未漏诊。

核心结论

  • EyeArt在EIDON图像上检测糖尿病视网膜病变的敏感度与标准NDESP图像相似,超过筛查试验推荐的敏感度阈值。

研究设计与样本

  • 横断面研究,连续纳入1257例参加年度糖尿病眼筛查的患者,采用散瞳双视野协议,分别用EIDON平台和标准NDESP相机成像,以人工分级标准NDESP图像为参考标准。

主要发现

  • EIDON图像上任何视网膜病变敏感度为92.27%(95%CI:88.43%~94.69%),威胁视力视网膜病变为99%(95%CI:95.35%~100%),增殖性视网膜病变为100%(95%CI:61%~100%)。
  • 标准NDESP图像上任何视网膜病变敏感度为92.26%(95%CI:88.37%~94.69%),威胁视力视网膜病变为100%(95%CI:99.53%~100%),增殖性视网膜病变为100%(95%CI:61%~100%)。
  • EyeArt分析EIDON图像时漏诊1例威胁视力视网膜病变(R1M1),但该例被人工分级识别;标准图像中EyeArt识别了所有威胁视力视网膜病变。

关键数值与推荐

  • EIDON图像:任何视网膜病变敏感度92.27%(95%CI:88.43%~94.69%),威胁视力视网膜病变99%(95%CI:95.35%~100%),增殖性视网膜病变100%(95%CI:61%~100%)。
  • 标准NDESP图像:任何视网膜病变敏感度92.26%(95%CI:88.37%~94.69%),威胁视力视网膜病变100%(95%CI:99.53%~100%),增殖性视网膜病变100%(95%CI:61%~100%)。

临床怎么用

  • 在糖尿病视网膜病变筛查中,EyeArt可用于EIDON广域真彩共焦扫描图像和标准NDESP图像的自动分级,其敏感度与人工分级参考标准相近。
  • 需注意EIDON图像分析中可能漏诊个别威胁视力视网膜病变,需进一步优化无视网膜病变的识别及理解两种成像系统的病变检测差异。

局限性

  • 原文未报告局限性内容。

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: Photographic diabetic retinopathy screening requires labour-intensive grading of retinal images by humans. Automated retinal image analysis software (ARIAS) could provide an alternative to human grading. We compare the performance of an ARIAS using true-colour, wide-field confocal scanning images and standard fundus images in the English National Diabetic Eye Screening Programme (NDESP) against human grading. METHODS: Cross-sectional study with consecutive recruitment of patients attending annual diabetic eye screening. Imaging with mydriasis was performed (two-field protocol) with the EIDON platform (CenterVue, Padua, Italy) and standard NDESP cameras. Human grading was carried out according to NDESP protocol. Images were processed by EyeArt V.2.1.0 (Eyenuk Inc, Woodland Hills, California). The reference standard for analysis was the human grade of standard NDESP images. RESULTS: We included 1257 patients. Sensitivity estimates for retinopathy grades were: EIDON images; 92.27% (95% CI: 88.43% to 94.69%) for any retinopathy, 99% (95% CI: 95.35% to 100%) for vision-threatening retinopathy and 100% (95% CI: 61% to 100%) for proliferative retinopathy. For NDESP images: 92.26% (95% CI: 88.37% to 94.69%) for any retinopathy, 100% (95% CI: 99.53% to 100%) for vision-threatening retinopathy and 100% (95% CI: 61% to 100%) for proliferative retinopathy. One case of vision-threatening retinopathy (R1M1) was missed by the EyeArt when analysing the EIDON images, but identified by the human graders. The EyeArt identified all cases of vision-threatening retinopathy in the standard images. CONCLUSION: EyeArt identified diabetic retinopathy in EIDON images with similar sensitivity to standard images in a large-scale screening programme, exceeding the sensitivity threshold recommended for a screening test. Further work to optimise the identification of 'no retinopathy' and to understand the differential lesion detection in the two imaging systems would enhance the use of these two innovative technologies in a diabetic retinopathy screening setting.

来源:Br J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Olvera-Barrios A, Heeren TF, Balaskas K, et al. Diagnostic accuracy of diabetic retinopathy grading by an artificial intelligence-enabled algorithm compared with a human standard for wide-field true-colour confocal scanning and standard digital retinal images. Br J Ophthalmol. 2020. PMID: 32376611. doi:10.1136/bjophthalmol-2019-315394

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。