Automatic differentiation of Glaucoma visual field from non-glaucoma visual filed using deep convolutional neural network.
Automatic differentiation of Glaucoma visual field from non-glaucoma visual filed using deep convolutional neural network.
复制标题
使用深度卷积神经网络自动区分青光眼视野和非青光眼视野。
DOI：
10.1186/s12880-018-0273-5
复制
发表时间：
2018-10-04
影响因子：
2.7
通讯作者：
Zhang X
中科院分区：
文献类型：
--
作者：
Li F;Wang Z;Qu G;Song D;Yuan Y;Xu Y;Gao K;Luo G;Xiao Z;Lam DSC;Zhong H;Qiao Y;Zhang X
为了建立一个基于视场（VF）测试结果区分青光眼和非青光眼视野的深度神经网络，我们收集了中国大陆3个不同眼科中心的VF测试结果。采集Humphrey 30-2和24-2试验获得的视野。可靠性标准为固定损失小于2/13，假阳性和假阴性率小于15%。我们将来自1352名患者的4012张PD图像分成两组，其中3712张用于训练，另外300张用于验证。左右比值差异无统计学意义（P = 0.6211），年龄（P = 0.0022）、VFI （P = 0.0001）、MD （P = 0.0039）、PSD （P = 0.0001）差异有统计学意义（P = 0.0001）。在300个VFs的验证集上，CNN的准确率为0.876，特异性为0.826，灵敏度为0.932。眼科住院医师、主治医师和青光眼专家的平均准确率分别为0.607、0.585和0.626。AGIS和GSS2的准确率分别为0.459和0.523。对支持向量机（SVM）、随机森林（RF）和k-近邻（k-NN）三种传统机器学习算法进行了实现和实验评估，准确率分别达到0.670、0.644和0.591。我们基于CNN的算法在青光眼和非青光眼VFs的鉴别上，比人类眼科医生和传统规则（AGIS和GSS2）取得了更高的准确率。本文的在线版本（10.1186/s12880-018-0273-5）包含补充资料，仅供授权用户使用。
To develop a deep neural network able to differentiate glaucoma from non-glaucoma visual fields based on visual filed (VF) test results, we collected VF tests from 3 different ophthalmic centers in mainland China. Visual fields obtained by both Humphrey 30–2 and 24–2 tests were collected. Reliability criteria were established as fixation losses less than 2/13, false positive and false negative rates of less than 15%. We split a total of 4012 PD images from 1352 patients into two sets, 3712 for training and another 300 for validation. There is no significant difference between left to right ratio (P = 0.6211), while age (P = 0.0022), VFI (P = 0.0001), MD (P = 0.0039) and PSD (P = 0.0001) exhibited obvious statistical differences. On the validation set of 300 VFs, CNN achieves the accuracy of 0.876, while the specificity and sensitivity are 0.826 and 0.932, respectively. For ophthalmologists, the average accuracies are 0.607, 0.585 and 0.626 for resident ophthalmologists, attending ophthalmologists and glaucoma experts, respectively. AGIS and GSS2 achieved accuracy of 0.459 and 0.523 respectively. Three traditional machine learning algorithms, namely support vector machine (SVM), random forest (RF), and k-nearest neighbor (k-NN) were also implemented and evaluated in the experiments, which achieved accuracy of 0.670, 0.644, and 0.591 respectively. Our algorithm based on CNN has achieved higher accuracy compared to human ophthalmologists and traditional rules (AGIS and GSS2) in differentiation of glaucoma and non-glaucoma VFs. The online version of this article (10.1186/s12880-018-0273-5) contains supplementary material, which is available to authorized users.
登录
查看更多内容
影响因子：
4.4
作者：
Liang, Yuan Bo;Friedman, David S.;Wang, Ning Li
通讯作者：
Wang, Ning Li
影响因子：
168.9
作者：
Quigley, Harry A.
通讯作者：
Quigley, Harry A.
影响因子：
19.5
作者：
Russakovsky, Olga;Deng, Jia;Fei-Fei, Li
通讯作者：
Fei-Fei, Li
影响因子：
13.7
作者：
Atalay, Eray;Nongpiur, Monisha E.;Aung, Tin
通讯作者：
Aung, Tin
影响因子：
7.5
作者：
CORTES, C;VAPNIK, V
通讯作者：
VAPNIK, V