Segmentation of retinal fluid based on deep learning:application of three-dimensional fully convolutional neural networks in optical coherence tomography images

Meng-Xiao Li1; Su-Qin Yu2; Wei Zhang1; Hao Zhou2; Xun Xu2; Tian-Wei Qian2; Yong-Jing Wan1

首页> 外文期刊>国际眼科杂志：英文版 >Segmentation of retinal fluid based on deep learning:application of three-dimensional fully convolutional neural networks in optical coherence tomography images

【24h】

Segmentation of retinal fluid based on deep learning:application of three-dimensional fully convolutional neural networks in optical coherence tomography images

机译：基于深度学习的视网膜液分割：三维全卷积神经网络在光学相干断层扫描图像中的应用

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

页面导航

摘要
著录项
相关主题

摘要

AIM: To explore a segmentation algorithm based on deep learning to achieve accurate diagnosis and treatment of patients with retinal fluid.METHODS: A two-dimensional(2D) fully convolutional network for retinal segmentation was employed. In order to solve the category imbalance in retinal optical coherence tomography(OCT) images, the network parameters and loss function based on the 2D fully convolutional network were modified. For this network, the correlations of corresponding positions among adjacent images in space are ignored. Thus, we proposed a three-dimensional(3D) fully convolutional network for segmentation in the retinal OCT images.RESULTS: The algorithm was evaluated according to segmentation accuracy, Kappa coefficient, and F1 score. For the 3D fully convolutional network proposed in this paper, the overall segmentation accuracy rate is 99.56%, Kappa coefficient is 98.47%, and F1 score of retinal fluid is 95.50%. CONCLUSION: The OCT image segmentation algorithm based on deep learning is primarily founded on the 2D convolutional network. The 3D network architecture proposed in this paper reduces the influence of category imbalance, realizes end-to-end segmentation of volume images, and achieves optimal segmentation results. The segmentation maps are practically the same as the manual annotations of doctors, and can provide doctors with more accurate diagnostic data.

机译：目的：探索一种基于深度学习的分割算法，对视网膜液患者进行准确的诊断和治疗。方法：采用二维（2D）全卷积网络进行视网膜分割。为了解决视网膜光学相干断层扫描（OCT）图像中的类别不平衡问题，修改了基于二维全卷积网络的网络参数和损失函数。对于该网络，空间中相邻图像之间的对应位置的相关性被忽略。因此，我们提出了一种三维（3D）全卷积网络用于视网膜OCT图像的分割。结果：根据分割精度，Kappa系数和F1分数对算法进行了评估。对于本文提出的3D全卷积网络，整体分割准确率为99.56％，Kappa系数为98.47％，视网膜液的F1分数为95.50％。结论：基于深度学习的OCT图像分割算法主要建立在二维卷积网络上。本文提出的3D网络架构减少了类别不平衡的影响，实现了体积图像的端到端分割，并获得了最佳的分割效果。分割图实际上与医生的手动注释相同，并且可以为医生提供更准确的诊断数据。

著录项

来源
《国际眼科杂志：英文版》 |2019年第6期|P.1012-1020|共9页
作者
Meng-Xiao Li1; Su-Qin Yu2; Wei Zhang1; Hao Zhou2; Xun Xu2; Tian-Wei Qian2; Yong-Jing Wan1;
展开▼
作者单位

[1]School of Information Science and Engineering,East China University of Science and Technology,Shanghai 200237,China;

[2]Department of Ophthalmology,Shanghai General Hospital,Shanghai Jiaotong University School of Medicine,Shanghai Key Laboratory of Ocular Fundus Diseases,Shanghai 200080,China;

[1]School of Information Science and Engineering,East China University of Science and Technology,Shanghai 200237,China;

[2]Department of Ophthalmology,Shanghai General Hospital,Shanghai Jiaotong University School of Medicine,Shanghai Key Laboratory of Ocular Fundus Diseases,Shanghai 200080,China;

[2]Department of Ophthalmology,Shanghai General Hospital,Shanghai Jiaotong University School of Medicine,Shanghai Key Laboratory of Ocular Fundus Diseases,Shanghai 200080,China;

[2]Department of Ophthalmology,Shanghai General Hospital,Shanghai Jiaotong University School of Medicine,Shanghai Key Laboratory of Ocular Fundus Diseases,Shanghai 200080,China;

[1]School of Information Science and Engineering,East China University of Science and Technology,Shanghai 200237,China;

展开▼
收录信息
原文格式 PDF
正文语种 CHI
中图分类视网膜疾病;
关键词
optical coherence tomography images; fluid segmentation; 2D fully convolutional network; 3D fully convolutional network;

机译：光学相干断层扫描图像;流体分割;2D全卷积网络;3D全卷积网络;

Segmentation of retinal fluid based on deep learning:application of three-dimensional fully convolutional neural networks in optical coherence tomography images

摘要

著录项

相关主题

期刊订阅