基于彩色眼底照相检测多种眼底疾病的深度学习模型的开发与评估
该研究开发并评估了一个深度学习系统(DLS),用于通过彩色眼底照相检测正常眼底及12种主要眼底疾病。结果显示DLS在内部和外部测试集上均表现出较高的AUC、敏感性和特异性,诊断敏感性高于人类医生但特异性较低,结论认为该DLS在真实世界眼底疾病筛查中具有潜力。
要点
- DLS可检测正常眼底及12种主要眼底疾病,包括可转诊糖尿病视网膜病变、病理性近视视网膜变性等。
- 内部测试集AUC为0.950–0.996,两个外部测试集AUC分别为0.931–1.000和0.934–1.000。
- 与人类医生相比,DLS诊断敏感性更高但特异性更低。
核心结论
- 所提出的DLS能有效诊断正常眼底和12种主要眼底疾病,在真实世界眼底疾病筛查中具有较大潜力。
研究设计与样本
- 研究还进行了DLS与人类医生的诊断性能比较。
主要发现
- 内部测试集AUC为0.950(95%CI 0.942–0.957)至0.996(95%CI 0.994–0.998),敏感性为80.4%(95%CI 79.1%–81.6%)至97.3%(95%CI 96.7%–97.8%),特异性为89.7%(95%CI 88.8%–90.7%)至98.1%(95%CI 97.7%–98.6%)。
- 第一个外部测试集AUC为0.931(95%CI 0.923–0.939)至1.000(95%CI 0.999–1.000),敏感性为64.6%(95%CI 63.0%–66.1%)至100%(95%CI 100%–100%),特异性为78.7%(95%CI 77.4%–80.0%)至99.6%(95%CI 99.4%–99.8%)。
- 第二个外部测试集AUC为0.934(95%CI 0.929–0.938)至1.000(95%CI 0.999–1.000),敏感性为68.0%(95%CI 67.1%–68.9%)至100%(95%CI 100%–100%),特异性为88.1%(95%CI 87.4%–88.7%)至98.7%(95%CI 98.5%–99.0%)。
- 与人类医生相比,DLS诊断敏感性更高但特异性更低。
临床怎么用
- 该DLS可用于正常眼底和12种主要眼底疾病的检测,有望用于真实世界眼底疾病筛查。
- 需注意DLS敏感性高于人类医生但特异性较低,在临床应用中应结合具体场景权衡。
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
AIM: To explore and evaluate an appropriate deep learning system (DLS) for the detection of 12 major fundus diseases using colour fundus photography. METHODS: Diagnostic performance of a DLS was tested on the detection of normal fundus and 12 major fundus diseases including referable diabetic retinopathy, pathologic myopic retinal degeneration, retinal vein occlusion, retinitis pigmentosa, retinal detachment, wet and dry age-related macular degeneration, epiretinal membrane, macula hole, possible glaucomatous optic neuropathy, papilledema and optic nerve atrophy. The DLS was developed with 56 738 images and tested with 8176 images from one internal test set and two external test sets. The comparison with human doctors was also conducted. RESULTS: The area under the receiver operating characteristic curves of the DLS on the internal test set and the two external test sets were 0.950 (95% CI 0.942 to 0.957) to 0.996 (95% CI 0.994 to 0.998), 0.931 (95% CI 0.923 to 0.939) to 1.000 (95% CI 0.999 to 1.000) and 0.934 (95% CI 0.929 to 0.938) to 1.000 (95% CI 0.999 to 1.000), with sensitivities of 80.4% (95% CI 79.1% to 81.6%) to 97.3% (95% CI 96.7% to 97.8%), 64.6% (95% CI 63.0% to 66.1%) to 100% (95% CI 100% to 100%) and 68.0% (95% CI 67.1% to 68.9%) to 100% (95% CI 100% to 100%), respectively, and specificities of 89.7% (95% CI 88.8% to 90.7%) to 98.1% (95%CI 97.7% to 98.6%), 78.7% (95% CI 77.4% to 80.0%) to 99.6% (95% CI 99.4% to 99.8%) and 88.1% (95% CI 87.4% to 88.7%) to 98.7% (95% CI 98.5% to 99.0%), respectively. When compared with human doctors, the DLS obtained a higher diagnostic sensitivity but lower specificity. CONCLUSION: The proposed DLS is effective in diagnosing normal fundus and 12 major fundus diseases, and thus has much potential for fundus diseases screening in the real world.
引用
- Li B, Chen H, Zhang B, et al. Development and evaluation of a deep learning model for the detection of multiple fundus diseases based on colour fundus photography. Br J Ophthalmol. 2021. PMID: 33785508. doi:10.1136/bjophthalmol-2020-316290
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。