文献类型：期刊文献

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

作者：Li, Meng-Xiao[1];Yu, Su-Qin[2,3];Zhang, Wei[1];Zhou, Hao[2,3];Xu, Xun[2,3];Qian, Tian-Wei[2,3];Wan, Yong-Jing[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Shanghai Jiao Tong Univ, Dept Ophthalmol, Sch Med, Shanghai Gen Hosp, Shanghai 200080, Peoples R China;[3]Shanghai Key Lab Ocular Fundus Dis, Shanghai 200080, Peoples R China

年份：2019

卷号：12

期号：6

起止页码：1012

外文期刊名：INTERNATIONAL JOURNAL OF OPHTHALMOLOGY

收录：;WOS:【SCI-EXPANDED(收录号:WOS:000471923600022)】；

基金：Supported by National Science Foundation of China (No. 81800878); Interdisciplinary Program of Shanghai Jiao Tong University (No. YG2017QN24); Key Technological Research Projects of Songjiang District (No. 18sjkjgg24); Bethune Langmu Ophthalmological Research Fund for Young and Middle-aged People (No. BJ-LM2018002J).

语种：英文

外文关键词：optical coherence tomography images; fluid segmentation; 2D fully convolutional network; 3D fully convolutional network

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 F-1 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 F-1 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.