Detection of signs of disease in external photographs of the eyes via deep learning.
Detection of signs of disease in external photographs of the eyes via deep learning.
复制标题
通过深度学习从眼睛的外部照片中检测疾病的迹象。
DOI：
10.1038/s41551-022-00867-5
复制
发表时间：
2022-12
影响因子：
28.1
通讯作者：
Liu Y
中科院分区：
文献类型：
--
作者：
Babenko B;Mitani A;Traynis I;Kitade N;Singh P;Maa AY;Cuadros J;Corrado GS;Peng L;Webster DR;Varadarajan A;Hammel N;Liu Y
视网膜眼底照片可用于检测一系列视网膜状况。在这里，我们展示了在眼睛的外部照片上训练的深度学习模型可用于检测糖尿病视网膜病变（DR），糖尿病黄斑水肿和血糖控制不良。我们使用来自301个DR筛查中心的145，832名糖尿病患者的眼部照片开发了模型，并在来自198个额外筛查中心的48，644名患者的四个任务和四个验证数据集上评估了模型。对于所有四项任务，深度学习模型的预测性能显著高于使用自我报告的人口统计学和病史数据的逻辑回归模型的性能，并且预测适用于瞳孔散大的患者，来自不同DR筛查计划的患者以及包括糖尿病患者和非糖尿病患者的一般眼科护理计划。我们还探索了使用深度学习模型来检测血脂水平升高。外眼照片用于疾病诊断和管理的效用应进一步验证来自不同相机和患者人群的图像。与依赖于人口统计和病史数据的模型相比，在外部眼睛照片上训练的深度学习模型可以更准确地检测糖尿病视网膜病变、糖尿病黄斑水肿和血糖控制不良。
Retinal fundus photographs can be used to detect a range of retinal conditions. Here we show that deep-learning models trained instead on external photographs of the eyes can be used to detect diabetic retinopathy (DR), diabetic macular oedema and poor blood glucose control. We developed the models using eye photographs from 145,832 patients with diabetes from 301 DR screening sites and evaluated the models on four tasks and four validation datasets with a total of 48,644 patients from 198 additional screening sites. For all four tasks, the predictive performance of the deep-learning models was significantly higher than the performance of logistic regression models using self-reported demographic and medical history data, and the predictions generalized to patients with dilated pupils, to patients from a different DR screening programme and to a general eye care programme that included diabetics and non-diabetics. We also explored the use of the deep-learning models for the detection of elevated lipid levels. The utility of external eye photographs for the diagnosis and management of diseases should be further validated with images from different cameras and patient populations. Deep-learning models trained on external eye photographs can detect diabetic retinopathy, diabetic macular oedema and poor blood glucose control more accurately than models relying on demographic and medical history data.
登录
查看更多内容
DOI：
10.1097/iop.0000000000001122
发表时间：
2018-07-01
影响因子：
2
作者：
Dutton, Jonathan J
通讯作者：
Dutton, Jonathan J
影响因子：
82.9
作者：
Avram R;Olgin JE;Kuhar P;Hughes JW;Marcus GM;Pletcher MJ;Aschbacher K;Tison GH
通讯作者：
Tison GH
影响因子：
6.1
作者：
Hsiao, Ching-Hsi;Chao, Anning;Lin, Ja-Liang
通讯作者：
Lin, Ja-Liang
影响因子：
8.1
作者：
Keenum, Zachary;McGwin, Gerald, Jr.;Owsley, Cynthia
通讯作者：
Owsley, Cynthia
影响因子：
23.8
作者：
Babic, Boris;Gerke, Sara;Cohen, I. Glenn
通讯作者：
Cohen, I. Glenn