Automated macular OCT retinal surface segmentation in cases of severe glaucoma using deep learning
Automated macular OCT retinal surface segmentation in cases of severe glaucoma using deep learning
复制标题
使用深度学习对严重青光眼病例进行自动黄斑 OCT 视网膜表面分割
DOI：
10.1117/12.2611859
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Wu, Xiaodong
中科院分区：
文献类型：
--
作者：
Xie, Hui;Wang, Jui-Kai;Kardon, Randy H.;Garvin, Mona K.;Wu, Xiaodong
青光眼是视神经损伤导致永久性失明的主要原因之一。光学相干断层扫描（OCT）已成为评估神经元丢失引起的结构损伤的重要临床工具。传统的二维和三维方法已成功地应用于定量视网膜内层厚度。然而，在严重青光眼中，当视网膜层变薄且违反算法假设时，这些方法的分割可靠性较差。深度学习（DL）是一种可替代的图像分析方法，因为它具有直接从数据中提取特征的强大能力。最先进的深度学习分割方法可以在正常眼睛的OCT扫描中实现多个视网膜表面的亚像素精度。然而，仍然需要改进的局限性，如尖峰状分割错误（表现为高豪斯多夫距离）和缺乏输入图像的上下文信息。为了解决这些限制，本研究提出了三种新颖的解决方案。首先，为了增强数据，我们通过在垂直和抖动平面重组a扫描来重建更多的b扫描，以使DL暴露于10中遇到的更多特征。其次，将每三个相邻b扫描的平滑和对比度增强图像连接起来，为神经网络提供具有上下文信息的六通道输入图像堆栈。最后，我们在保持视网膜拓扑秩序的同时，合并了水平和垂直b扫描的预测表面。在我们独立测试的数据集中，包括患有严重青光眼的眼睛，所提出的方法在多个表面的平均绝对表面距离，Dice系数和Hausdorff距离方面优于最先进的方法。
Glaucoma is one of the leading causes of permanent blindness due to optic nerve damage. Optical coherence tomography (OCT) has become an important clinical tool for assessing structural damage from the loss of neurons. Traditional 2D and 3D methods have been successfully applied to quantify inner retinal layer thickness. However, these methods show less reliable segmentation in severe glaucoma when the retinal layers have become thin and violate algorithm assumptions. Deep learning (DL) is an alternative image analysis approach due to its powerful ability to extract features directly from data. State-of-the-art DL segmentation approaches can achieve sub-pixel accuracy at multiple retinal surfaces in OCT scans from normal eyes. However, limitations, such as spike-like segmentation errors (showing as high Hausdorff distances) and lack of contextual information from the input image, still need to be improved. To address these limitations, three novel solutions were proposed in this study. First, for data augmentation, we reconstructed more B-scans by reassembling A-scans at the vertical and jittered planes to expose DL to a greater variety of features encountered in OCT. Second, smoothed and contrast-enhanced images of each three adjacent B-scans were concatenated to provide a six-channel input image stack to the neural network with contextual information. Finally, we merged the predicted surfaces from both horizontal and vertical B-scans while maintaining retinal topological order. In our independently tested dataset, which included eyes with severe glaucoma, the proposed approach outperformed the state-of-the-art methods in mean absolute surface distances, Dice coefficients, and Hausdorff distance at multiple surfaces.
登录
查看更多内容
具有标准自动化的圆锥体和刺激大小III和V的青光眼视野进程的有效动态范围。
影响因子：
4.4
作者：
Wall M;Zamba GKD;Artes PH
通讯作者：
Artes PH
影响因子：
13.7
作者：
Tham, Yih-Chung;Li, Xiang;Cheng, Ching-Yu
通讯作者：
Cheng, Ching-Yu
使用完全卷积回归网络的视网膜OCT的结构化层表面分割。
影响因子：
10.9
作者：
He Y;Carass A;Liu Y;Jedynak BM;Solomon SD;Saidha S;Calabresi PA;Prince JL
通讯作者：
Prince JL
影响因子：
3.4
作者：
Shah, Abhay;Zhou, Leixin;Wu, Xiaodong
通讯作者：
Wu, Xiaodong
影响因子：
4.2
作者：
Shin, Joong Won;Sung, Kyung Rim;Song, Min Kyung
通讯作者：
Song, Min Kyung