A deep learning model for the detection of both advanced and early glaucoma using fundus photography.
A deep learning model for the detection of both advanced and early glaucoma using fundus photography.
复制标题
DOI：
10.1371/journal.pone.0207982
复制
发表时间：
2018
期刊：
影响因子：
3.7
通讯作者：
Kim US
中科院分区：
文献类型：
--
作者：
Ahn JM;Kim S;Ahn KS;Cho SH;Lee KB;Kim US
建立使用眼底摄影诊断青光眼的深度学习模型。横断面案例研究 受试者、参与者和对照：通过眼底摄影获得总共 1,542 张照片（786 名正常对照、467 名晚期青光眼和 289 名早期青光眼患者）。整个数据集包含 1,542 张图像，分为 754 个训练数据集、324 个验证数据集和 464 个测试数据集。这些数据集用于使用 Tensorflow 构建简单的逻辑分类和卷积神经网络。相同的数据集用于微调预训练的 GoogleNet Inception v3 模型。简单逻辑分类模型的训练准确率为 82.9%，验证准确率为 79.9%，测试准确率为 77.2%。卷积神经网络在训练数据上实现了 92.2% 和 0.98 的准确率和受试者工作特征曲线下面积 (AUROC)，在验证数据上实现了 88.6% 和 0.95，在测试数据上实现了 87.9% 和 0.94。迁移学习的 GoogleNet Inception v3 模型在训练数据上实现了 99.7% 和 0.99 的准确率和 AUROC，在验证数据上实现了 87.7% 和 0.95，在测试数据上实现了 84.5% 和 0.93。仅使用眼底照片，就可以通过机器学习正确检测晚期和早期青光眼。我们使用卷积神经网络训练的新模型比以前发布的模型更有效地诊断早期青光眼。
To build a deep learning model to diagnose glaucoma using fundus photography. Cross sectional case study Subjects, Participants and Controls: A total of 1,542 photos (786 normal controls, 467 advanced glaucoma and 289 early glaucoma patients) were obtained by fundus photography. The whole dataset of 1,542 images were split into 754 training, 324 validation and 464 test datasets. These datasets were used to construct simple logistic classification and convolutional neural network using Tensorflow. The same datasets were used to fine tune pre-trained GoogleNet Inception v3 model. The simple logistic classification model showed a training accuracy of 82.9%, validation accuracy of 79.9% and test accuracy of 77.2%. Convolutional neural network achieved accuracy and area under the receiver operating characteristic curve (AUROC) of 92.2% and 0.98 on the training data, 88.6% and 0.95 on the validation data, and 87.9% and 0.94 on the test data. Transfer-learned GoogleNet Inception v3 model achieved accuracy and AUROC of 99.7% and 0.99 on training data, 87.7% and 0.95 on validation data, and 84.5% and 0.93 on test data. Both advanced and early glaucoma could be correctly detected via machine learning, using only fundus photographs. Our new model that is trained using convolutional neural network is more efficient for the diagnosis of early glaucoma than previously published models.
登录
查看更多内容
影响因子：
1.9
作者：
Barella KA;Costa VP;Gonçalves Vidotti V;Silva FR;Dias M;Gomi ES
通讯作者：
Gomi ES
影响因子：
4.6
作者：
Chan, KL;Lee, TW;Sejnowski, ATJ
通讯作者：
Sejnowski, ATJ
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S
影响因子：
3.6
作者：
Wu, Songtao;Zhong, Shenghua;Liu, Yan
通讯作者：
Liu, Yan
影响因子：
3.4
作者：
Bizios, Dimitrios;Heijl, Anders;Bengtsson, Boel
通讯作者：
Bengtsson, Boel