Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs
Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs
复制标题
DOI：
10.1001/jama.2016.17216
复制
发表时间：
2016-12-13
影响因子：
120.7
通讯作者：
Webster, R.
中科院分区：
文献类型：
--
作者：
Gulshan, Varun;Peng, Lily;Webster, R.
深度学习是一系列计算方法，它允许算法通过从大量演示所需行为的示例中学习来编程，从而消除了明确指定规则的需要。这些方法在医学成像中的应用需要进一步的评估和验证。目的应用深度学习建立一种自动检测视网膜眼底照片中糖尿病视网膜病变和糖尿病黄斑水肿的算法。在2015年5月至12月期间，由54名美国执业眼科医生和眼科资深住院医师组成的小组对128 175张视网膜图像进行了3至7次的糖尿病视网膜病变、糖尿病黄斑水肿和图像分级，并使用回顾性发展数据集对一种特定类型的神经网络进行了深度卷积神经网络的图像分类优化。最终的算法在2016年1月和2月使用两个独立的数据集进行验证，这两个数据集都由至少7名美国委员会认证的眼科医生评分，具有高度的内部一致性。深度学习训练算法。根据眼科专家小组多数决定的参考标准，生成检测可参考糖尿病视网膜病变（RDR）算法的敏感性和特异性，RDR定义为中度及重度糖尿病视网膜病变、可参考糖尿病黄斑水肿或两者兼有。该算法在开发集中选择的2个操作点进行评估，其中一个选择为高特异性，另一个选择为高灵敏度。EyePACS-1数据集包括来自4997例患者的9963张图像（平均年龄54.4岁，女性62.2%，RDR患病率683/8878张完全可分级图像[7.8%]）；Messidor-2数据集有来自874例患者的1748张图像（平均年龄57.6岁，女性占42.6%，RDR患病率为254/1745张完全可分级图像[14.6%]）。对于检测RDR， EyePACS-1和Messidor-2的受试者工作曲线下面积分别为0.991 （95% CI, 0.988 ~ 0.993）和0.990（95% CI, 0.986 ~ 0.995）。采用高特异性的第一手术切点，EyePACS-1的敏感性为90.3%(95% CI, 87.5% ~ 92.7%)，特异性为98.1%（95% CI, 97.8% ~ 98.5%）。对于messsidor -2，敏感性为87.0%(95% CI, 81.1%-91.0%)，特异性为98.5%（95% CI, 97.7%-99.1%）。在开发集中使用具有高灵敏度的第二个操作点，EyePACS-1的灵敏度为97.5%，特异性为93.4%，而Messidor-2的灵敏度为96.1%，特异性为93.9%。在对成人糖尿病患者视网膜眼底照片的评估中，一种基于深度机器学习的算法在检测可参考的糖尿病视网膜病变方面具有高灵敏度和特异性。需要进一步的研究来确定在临床环境中应用该算法的可行性，并确定与目前的眼科评估相比，使用该算法是否可以改善护理和结果。
IMPORTANCE Deep learning is a family of computational methods that allow an algorithm to program itself by learning from a large set of examples that demonstrate the desired behavior, removing the need to specify rules explicitly. Application of these methods to medical imaging requires further assessment and validation.OBJECTIVE To apply deep learning to create an algorithm for automated detection of diabetic retinopathy and diabetic macular edema in retinal fundus photographs.DESIGN AND SETTING A specific type of neural network optimized for image classification called a deep convolutional neural network was trained using a retrospective development data set of 128 175 retinal images, which were graded 3 to 7 times for diabetic retinopathy, diabetic macular edema, and image gradability by a panel of 54 US licensed ophthalmologists and ophthalmology senior residents between May and December 2015. The resultant algorithm was validated in January and February 2016 using 2 separate data sets, both graded by at least 7 US board-certified ophthalmologists with high intragrader consistency.EXPOSURE Deep learning-trained algorithm.MAIN OUTCOMES AND MEASURES The sensitivity and specificity of the algorithm for detecting referable diabetic retinopathy (RDR), defined as moderate and worse diabetic retinopathy, referable diabetic macular edema, or both, were generated based on the reference standard of the majority decision of the ophthalmologist panel. The algorithm was evaluated at 2 operating points selected from the development set, one selected for high specificity and another for high sensitivity.RESULTS The EyePACS-1 data set consisted of 9963 images from 4997 patients (mean age, 54.4 years; 62.2% women; prevalence of RDR, 683/8878 fully gradable images [7.8%]); the Messidor-2 data set had 1748 images from 874 patients (mean age, 57.6 years; 42.6% women; prevalence of RDR, 254/1745 fully gradable images [14.6%]). For detecting RDR, the algorithm had an area under the receiver operating curve of 0.991 (95% CI, 0.988-0.993) for EyePACS-1 and 0.990(95% CI, 0.986-0.995) for Messidor-2. Using the first operating cut point with high specificity, for EyePACS-1, the sensitivity was 90.3%(95% CI, 87.5%-92.7%) and the specificity was 98.1%(95% CI, 97.8%-98.5%). For Messidor-2, the sensitivity was 87.0%(95% CI, 81.1%-91.0%) and the specificity was 98.5%(95% CI, 97.7%-99.1%). Using a second operating point with high sensitivity in the development set, for EyePACS-1 the sensitivity was 97.5% and specificity was 93.4% and for Messidor-2 the sensitivity was 96.1% and specificity was 93.9%.CONCLUSIONS AND RELEVANCE In this evaluation of retinal fundus photographs from adults with diabetes, an algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy. Further research is necessary to determine the feasibility of applying this algorithm in the clinical setting and to determine whether use of the algorithm could lead to improved care and outcomes compared with current ophthalmologic assessment.