Pao Shu-I, Lin Hong-Zin, Chien Ke-Hung, Tai Ming-Cheng, Chen Jiann-Torng, Lin Gen-Min
Department of Ophthalmology, Tri-Service General Hospital and National Defense Medical Center, Taipei 114, Taiwan.
Department of Ophthalmology, Buddhist Tzu Chi General Hospital, Hualien 970, Taiwan.
J Ophthalmol. 2020 Jun 19;2020:9139713. doi: 10.1155/2020/9139713. eCollection 2020.
Deep learning of fundus photograph has emerged as a practical and cost-effective technique for automatic screening and diagnosis of severer diabetic retinopathy (DR). The entropy image of luminance of fundus photograph has been demonstrated to increase the detection performance for referable DR using a convolutional neural network- (CNN-) based system. In this paper, the entropy image computed by using the green component of fundus photograph is proposed. In addition, image enhancement by unsharp masking (UM) is utilized for preprocessing before calculating the entropy images. The bichannel CNN incorporating the features of both the entropy images of the gray level and the green component preprocessed by UM is also proposed to improve the detection performance of referable DR by deep learning.
眼底照片的深度学习已成为一种用于严重糖尿病视网膜病变（DR）自动筛查和诊断的实用且经济高效的技术。基于卷积神经网络（CNN）的系统已证明，眼底照片亮度的熵图像可提高可参考性DR的检测性能。本文提出了利用眼底照片绿色分量计算的熵图像。此外，在计算熵图像之前，采用非锐化掩膜（UM）进行图像增强预处理。还提出了一种结合灰度级熵图像和经UM预处理的绿色分量特征的双通道CNN，以通过深度学习提高可参考性DR的检测性能。
