Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes
Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes
复制标题
DOI：
10.1001/jama.2017.18152
复制
发表时间：
2017-12-12
影响因子：
120.7
通讯作者：
Wong, Tien Yin
中科院分区：
文献类型：
--
作者：
Ting, Daniel Shu Wei;Cheung, Carol Yim-Lui;Wong, Tien Yin
重要性深度学习系统（DLS）是一种机器学习技术，具有筛查糖尿病视网膜病变及相关眼病的潜力。目的评估DLS在社区和临床多种族糖尿病人群中检测可诊断糖尿病视网膜病变、威胁视力的糖尿病视网膜病变、可能的青光眼和年龄相关性黄斑变性（AMD）的性能。设计，设置，和参与者使用494661张视网膜图像评价DLS对糖尿病视网膜病变和相关眼病的诊断性能。训练DLS用于检测糖尿病视网膜病变（使用76 370张图像）、可能的青光眼（125 189张图像）和AMD（72 610张图像），并评价DLS用于检测糖尿病视网膜病变（使用112 648张图像）、可能的青光眼（71 896张图像）和AMD（35 948张图像）的性能。DLS的培训于2016年5月完成，并于2017年5月完成了DLS的验证，用于检测可诊断的糖尿病视网膜病变（中度非增殖性糖尿病视网膜病变或更严重）和威胁视力的糖尿病视网膜病变（重度非增殖性糖尿病视网膜病变或更严重）使用新加坡国家糖尿病视网膜病筛查计划和10个多种族糖尿病队列的主要验证数据集。暴露使用主要结果和指标受试者工作特征曲线下面积（AUC）以及专业评分员DLS的灵敏度和特异性（视网膜专家、普通眼科医生、经过培训的分级者或验光师）作为参考标准。（n = 14880例患者; 71896张图像;平均[SD]年龄，60.2 [2.2]岁; 54.6%为男性），可诊断的糖尿病视网膜病变的患病率为3.0%;威胁视力的糖尿病视网膜病变，0.6%;可能的青光眼，0.1%; AMD，2.5%。DLS对可诊断糖尿病视网膜病变的AUC为0.936（95% CI，0.925-0.943），灵敏度为90.5%（95% CI，87.3%-93.0%），特异性为91.6%（95% CI，91.0%-92.2%）。对于威胁视力的糖尿病视网膜病变，AUC为0.958（95% CI，0.956-0.961），灵敏度为100%（95% CI，94.1%-100.0%），特异性为91.1%（95% CI，90.7%-91.4%）。对于可能的青光眼，AUC为0.942（95% CI，0.929-0.954），灵敏度为96.4%（95% CI，81.7%-99.9%），特异性为87.2%（95% CI，86.8%-87.5%）。对于AMD，AUC为0.931（95% CI，0.928-0.935），灵敏度为93.2%（95% CI，91.1%-99.8%），特异性为88.7%（95% CI，88.3%-89.0%）。对于额外10个数据集中的可参考糖尿病视网膜病变，AUC范围为0.889至0.983（n = 40 752张图像）。结论和相关性在对多种族糖尿病患者队列的视网膜图像进行的这项评估中，DLS对于识别糖尿病视网膜病变和相关眼部疾病具有高灵敏度和特异性。有必要进行进一步研究，以评估DLS在医疗保健环境中的适用性以及DLS改善视力结果的实用性。
IMPORTANCE A deep learning system (DLS) is a machine learning technology with potential for screening diabetic retinopathy and related eye diseases.OBJECTIVE To evaluate the performance of a DLS in detecting referable diabetic retinopathy, vision-threatening diabetic retinopathy, possible glaucoma, and age-related macular degeneration (AMD) in community and clinic-based multiethnic populations with diabetes.DESIGN, SETTING, AND PARTICIPANTS Diagnostic performance of a DLS for diabetic retinopathy and related eye diseases was evaluated using 494 661 retinal images. A DLS was trained for detecting diabetic retinopathy (using 76 370 images), possible glaucoma (125 189 images), and AMD(72 610 images), and performance of DLS was evaluated for detecting diabetic retinopathy (using 112 648 images), possible glaucoma (71 896 images), and AMD(35 948 images). Training of the DLS was completed in May 2016, and validation of the DLS was completed in May 2017 for detection of referable diabetic retinopathy (moderate nonproliferative diabetic retinopathy or worse) and vision-threatening diabetic retinopathy (severe nonproliferative diabetic retinopathy orworse) using a primary validation data set in the Singapore National Diabetic Retinopathy Screening Program and 10 multiethnic cohorts with diabetes.EXPOSURES Use of a deep learning system.MAIN OUTCOMES AND MEASURES Area under the receiver operating characteristic curve (AUC) and sensitivity and specificity of the DLS with professional graders (retinal specialists, general ophthalmologists, trained graders, or optometrists) as the reference standard.RESULTS In the primary validation dataset (n = 14 880 patients; 71 896 images; mean [SD] age, 60.2 [2.2] years; 54.6% men), the prevalence of referable diabetic retinopathy was 3.0%; vision-threatening diabetic retinopathy, 0.6%; possible glaucoma, 0.1%; and AMD, 2.5%. The AUC of the DLS for referable diabetic retinopathy was 0.936 (95% CI, 0.925-0.943), sensitivity was 90.5%(95% CI, 87.3%-93.0%), and specificity was 91.6% (95% CI, 91.0%-92.2%). For vision-threatening diabetic retinopathy, AUC was 0.958 (95% CI, 0.956-0.961), sensitivity was 100% (95% CI, 94.1%-100.0%), and specificity was 91.1% (95% CI, 90.7%-91.4%). For possible glaucoma, AUC was 0.942 (95% CI, 0.929-0.954), sensitivity was 96.4%(95% CI, 81.7%-99.9%), and specificity was 87.2%(95% CI, 86.8%-87.5%). For AMD, AUC was 0.931 (95% CI, 0.928-0.935), sensitivity was 93.2%(95% CI, 91.1%-99.8%), and specificity was 88.7%(95% CI, 88.3%-89.0%). For referable diabetic retinopathy in the 10 additional datasets, AUC range was 0.889 to 0.983 (n = 40 752 images).CONCLUSIONS AND RELEVANCE In this evaluation of retinal images from multiethnic cohorts of patients with diabetes, the DLS had high sensitivity and specificity for identifying diabetic retinopathy and related eye diseases. Further research is necessary to evaluate the applicability of the DLS in health care settings and the utility of the DLS to improve vision outcomes.