Glaucoma Diagnosis with Machine Learning Based on Optical Coherence Tomography and Color Fundus Images
Glaucoma Diagnosis with Machine Learning Based on Optical Coherence Tomography and Color Fundus Images
复制标题
DOI：
10.1155/2019/4061313
复制
发表时间：
2019-01-01
影响因子：
--
通讯作者：
Nakazawa, Toru
中科院分区：
文献类型：
--
作者：
An, Guangzhou;Omodaka, Kazuko;Nakazawa, Toru
本研究旨在开发一种基于机器学习的算法，用于开角型青光眼患者的青光眼诊断，基于三维光学相干断层扫描（OCT）数据和彩色眼底图像。在这项研究中，208例青光眼和149例健康的眼睛，彩色眼底图像和体积OCT数据从这些眼睛的视盘和黄斑区的光谱域OCT（3D OCT-2000，Topcon）捕获。使用分割算法创建厚度和偏差图。卷积神经网络（CNN）的迁移学习与以下类型的输入图像一起使用：（1）灰度格式的视盘的眼底图像，（2）视盘视网膜神经纤维层（RNFL）厚度图，（3）黄斑神经节细胞复合体（GCC）厚度图，（4）视盘RNFL偏差图，和（5）黄斑GCC偏差图。执行数据增强和丢弃以训练CNN。为了组合来自每个CNN模型的结果，训练随机森林（RF）以使用每个输入图像的特征向量表示对健康和昏迷眼睛的盘眼底图像进行分类，去除第二个完全连接层。使用10倍交叉验证（CV）的受试者工作特征曲线下面积（AUC）来评价模型。CNN的10倍CV AUC对于彩色眼底图像为0.940，对于RNFL厚度图为0.942，对于黄斑GCC厚度图为0.944，对于椎间盘RNFL偏差图为0.949，对于黄斑GCC偏差图为0.952。RF结合五个单独的CNN模型将10倍CV AUC提高到0.963。因此，这里描述的机器学习系统可以基于从OCT数据和彩色眼底图像中提取的图像来准确地区分健康受试者和昏迷受试者。该系统应有助于提高青光眼诊断的准确性。
This study aimed to develop a machine learning-based algorithm for glaucoma diagnosis in patients with open-angle glaucoma, based on three-dimensional optical coherence tomography (OCT) data and color fundus images. In this study, 208 glaucomatous and 149 healthy eyes were enrolled, and color fundus images and volumetric OCT data from the optic disc and macular area of these eyes were captured with a spectral-domain OCT (3D OCT-2000, Topcon). Thickness and deviation maps were created with a segmentation algorithm. Transfer learning of convolutional neural network (CNN) was used with the following types of input images: (1) fundus image of optic disc in grayscale format, (2) disc retinal nerve fiber layer (RNFL) thickness map, (3) macular ganglion cell complex (GCC) thickness map, (4) disc RNFL deviation map, and (5) macular GCC deviation map. Data augmentation and dropout were performed to train the CNN. For combining the results from each CNN model, a random forest (RF) was trained to classify the disc fundus images of healthy and glaucomatous eyes using feature vector representation of each input image, removing the second fully connected layer. The area under receiver operating characteristic curve (AUC) of a 10-fold cross validation (CV) was used to evaluate the models. The 10-fold CV AUCs of the CNNs were 0.940 for color fundus images, 0.942 for RNFL thickness maps, 0.944 for macular GCC thickness maps, 0.949 for disc RNFL deviation maps, and 0.952 for macular GCC deviation maps. The RF combining the five separate CNN models improved the 10-fold CV AUC to 0.963. Therefore, the machine learning system described here can accurately differentiate between healthy and glaucomatous subjects based on their extracted images from OCT data and color fundus images. This system should help to improve the diagnostic accuracy in glaucoma.