超广角眼底镜辅助深度学习检测初治增殖性糖尿病视网膜病变的准确性。
Accuracy of ultrawide-field fundus ophthalmoscopy-assisted deep learning for detecting treatment-naïve proliferative diabetic retinopathy.
作者信息
Nagasawa Toshihiko, Tabuchi Hitoshi, Masumoto Hiroki, Enno Hiroki, Niki Masanori, Ohara Zaigen, Yoshizumi Yuki, Ohsugi Hideharu, Mitamura Yoshinori
机构信息
Department of Ophthalmology, Saneikai Tsukazaki Hospital, 68-1 Aboshi Waku, Himeji City, Hyogo Prefecture, 671-1227, Japan.
Rist Inc., Tokyo, Japan.
出版信息
Int Ophthalmol. 2019 Oct;39(10):2153-2159. doi: 10.1007/s10792-019-01074-z. Epub 2019 Feb 23.
PURPOSE
We investigated using ultrawide-field fundus images with a deep convolutional neural network (DCNN), which is a machine learning technology, to detect treatment-naïve proliferative diabetic retinopathy (PDR).
METHODS
We 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.
RESULT
The constructed deep learning model demonstrated a high sensitivity of 94.7% and a high specificity of 97.2%, with an AUC of 0.969.
CONCLUSION
Our findings suggested that PDR could be diagnosed using wide-angle camera images and deep learning.
目的
我们研究了使用具有深度卷积神经网络（DCNN，一种机器学习技术）的超广角眼底图像来检测未经治疗的增殖性糖尿病视网膜病变（PDR）。
方法
我们使用378张摄影图像（132张PDR图像和246张非PDR图像）对DCNN进行训练，并构建了一个深度学习模型。检测了曲线下面积（AUC）、敏感性和特异性。
结果
构建的深度学习模型显示出94.7%的高敏感性和97.2%的高特异性，AUC为0.969。
结论
我们的研究结果表明，可使用广角相机图像和深度学习来诊断PDR。
Zotero 插件