Automated Diabetic Retinopathy Detection Based on Binocular Siamese-Like Convolutional Neural Network
Automated Diabetic Retinopathy Detection Based on Binocular Siamese-Like Convolutional Neural Network
复制标题
基于双目连体卷积神经网络的糖尿病视网膜病变自动检测
DOI：
10.1109/access.2019.2903171
复制
发表时间：
2019-01-01
期刊：
影响因子：
3.9
通讯作者：
Ye, Wenbin
中科院分区：
文献类型：
--
作者：
Zeng, Xianglong;Chen, Haiquan;Ye, Wenbin
糖尿病视网膜病变（DR）是全球范围内致盲的重要原因。然而，DR在早期阶段很难被发现，即使是经验丰富的专家，诊断过程也很耗时。因此，提出了一种基于深度学习算法的计算机辅助诊断方法，通过将彩色视网膜眼底照片分为两个等级来自动诊断可诊断的糖尿病视网膜病变。本文采用迁移学习技术训练了一种新型的具有连体结构的卷积神经网络模型。与以前的工作不同，该模型接受双眼眼底图像作为输入，并学习它们的相关性，以帮助做出预测。在训练集只有28104张图像和测试集7024张图像的情况下，所提出的双目模型获得的接收器工作曲线下的面积为0.951，比现有的单目模型获得的面积高0.011。为了进一步验证双目设计的有效性，还在10%的验证集上训练和评估了用于五类DR检测的双目模型。实验结果表明，该方法的Kappa值为0.829，高于现有的非集成模型。
Diabetic retinopathy (DR) is an important cause of blindness worldwide. However, DR is hard to be detected in the early stages, and the diagnostic procedure can be time-consuming even for the experienced experts. Therefore, a computer-aided diagnosis method based on deep learning algorithms is proposed to automatedly diagnose the referable diabetic retinopathy by classifying color retinal fundus photographs into two grades. In this paper, a novel convolutional neural network model with the Siamese-like architecture is trained with a transfer learning technique. Different from the previous works, the proposed model accepts binocular fundus images as inputs and learns their correlation to help to make a prediction. In the case with a training set of only 28 104 images and a test set of 7024 images, an area under the receiver operating curve of 0.951 is obtained by the proposed binocular model, which is 0.011 higher than that obtained by the existing monocular model. To further verify the effectiveness of the binocular design, a binocular model for five-class DR detection is also trained and evaluated on a 10% validation set. The result shows that it achieves a kappa score of 0.829 which is higher than that of the existing non-ensemble model.