Development and validation of a deep-learning algorithm for the detection of neovascular age-related macular degeneration from colour fundus photographs
Development and validation of a deep-learning algorithm for the detection of neovascular age-related macular degeneration from colour fundus photographs
复制标题
用于从彩色眼底照片中检测新生血管性年龄相关性黄斑变性的深度学习算法的开发与验证
DOI：
10.1111/ceo.13575
复制
发表时间：
2019-07-25
影响因子：
4
通讯作者：
He, Mingguang
中科院分区：
文献类型：
--
作者：
Keel, Stuart;Li, Zhixi;He, Mingguang
重要性 检测早发性新生血管性年龄相关性黄斑变性 (AMD) 对于保护视力至关重要。背景 描述用于检测新生血管性年龄相关性黄斑变性的深度学习算法 (DLA) 的开发和验证。使用回顾性数据集设计 DLA 的开发和验证。参与者 我们使用 56 113 幅视网膜图像和来自独立数据集的额外 86 162 幅图像来开发和训练 DLA，以从外部验证 DLA。所有图像都是非立体的并且是回顾性收集的。方法内部验证数据集来自中国的真实临床环境。当三位眼科医生达成共识后，即可指定金标准分级。 DLA 将 31 247 幅图像分类为可分级，24 866 幅图像分类为不可分级（质量差或视野清晰度差）。这些不可分级的图像用于创建图像质量的分类模型。使用来自墨尔本协作队列研究的 86 162 张图像测试了效率和诊断准确性。一只或两只眼睛的新生血管性 AMD 和/或不可分级的结果被认为是可参考的。主要结果指标 受试者工作特征曲线下面积 (AUC)、敏感性和特异性。结果 在内部验证数据集中，DLA 对新生血管性 AMD 的 AUC、敏感性和特异性分别为 0.995、96.7%、96.4%。针对独立外部数据集进行的测试的 AUC、敏感性和特异性分别为 0.967、100% 和 93.4%。超过 60% 的假阳性病例显示其他黄斑病变。在假阴性病例中（仅限内部验证数据集），超过一半 (57.2%) 被证明是未检测到的神经感觉视网膜或 RPE 层脱离。结论和相关性 该 DLA 在来自多种族样本和不同成像协议的视网膜图像中检测新生血管性 AMD 方面表现出强大的性能。需要进一步的研究来调查该技术在筛选和研究环境中的最佳利用位置。
Importance Detection of early onset neovascular age-related macular degeneration (AMD) is critical to protecting vision. Background To describe the development and validation of a deep-learning algorithm (DLA) for the detection of neovascular age-related macular degeneration. Design Development and validation of a DLA using retrospective datasets. Participants We developed and trained the DLA using 56 113 retinal images and an additional 86 162 images from an independent dataset to externally validate the DLA. All images were non-stereoscopic and retrospectively collected. Methods The internal validation dataset was derived from real-world clinical settings in China. Gold standard grading was assigned when consensus was reached by three individual ophthalmologists. The DLA classified 31 247 images as gradable and 24 866 as ungradable (poor quality or poor field definition). These ungradable images were used to create a classification model for image quality. Efficiency and diagnostic accuracy were tested using 86 162 images derived from the Melbourne Collaborative Cohort Study. Neovascular AMD and/or ungradable outcome in one or both eyes was considered referable. Main Outcome Measures Area under the receiver operating characteristic curve (AUC), sensitivity and specificity. Results In the internal validation dataset, the AUC, sensitivity and specificity of the DLA for neovascular AMD was 0.995, 96.7%, 96.4%, respectively. Testing against the independent external dataset achieved an AUC, sensitivity and specificity of 0.967, 100% and 93.4%, respectively. More than 60% of false positive cases displayed other macular pathologies. Amongst the false negative cases (internal validation dataset only), over half (57.2%) proved to be undetected detachment of the neurosensory retina or RPE layer. Conclusions and Relevance This DLA shows robust performance for the detection of neovascular AMD amongst retinal images from a multi-ethnic sample and under different imaging protocols. Further research is warranted to investigate where this technology could be best utilized within screening and research settings.