Nagasawa Toshihiko, Tabuchi Hitoshi, Masumoto Hiroki, Enno Hiroki, Niki Masanori, Ohara Zaigen, Yoshizumi Yuki, Ohsugi Hideharu, Mitamura Yoshinori
Department of Ophthalmology, Saneikai Tsukazaki Hospital, 68-1 Aboshi Waku, Himeji City, Hyogo Prefecture, 671-1227, Japan.
Rist Inc., Tokyo, Japan.
Int Ophthalmol. 2019 Oct;39(10):2153-2159. doi: 10.1007/s10792-019-01074-z. Epub 2019 Feb 23.
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).
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.
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.
Our findings suggested that PDR could be diagnosed using wide-angle camera images and deep learning.
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）。
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。
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。
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。
