期刊
INTERNATIONAL OPHTHALMOLOGY
卷 39, 期 10, 页码 2153-2159出版社
SPRINGER
DOI: 10.1007/s10792-019-01074-z
关键词
Ultrawide-field fundus ophthalmoscopy; Proliferative diabetic retinopathy; Deep learning; Deep convolutional neural network
PurposeWe investigated using ultrawide-field fundus images with a deep convolutional neural network (DCNN), which is a machine learning technology, to detect treatment-naive proliferative diabetic retinopathy (PDR).MethodsWe conducted training with the DCNN using 378 photographic images (132 PDR and 246 non-PDR) and constructed a deep learning model. The area under the curve (AUC), sensitivity, and specificity were examined.ResultThe constructed deep learning model demonstrated a high sensitivity of 94.7% and a high specificity of 97.2%, with an AUC of 0.969.ConclusionOur findings suggested that PDR could be diagnosed using wide-angle camera images and deep learning.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据