Beyond Retinal Layers: A Deep Voting Model for Automated Geographic Atrophy Segmentation in SD-OCT Images.
Beyond Retinal Layers: A Deep Voting Model for Automated Geographic Atrophy Segmentation in SD-OCT Images.
复制标题
超越视网膜层：SD-OCT 图像中自动地理萎缩分割的深度投票模型
DOI：
10.1167/tvst.7.1.1
复制
发表时间：
2018-01
影响因子：
3
通讯作者：
Rubin DL
中科院分区：
文献类型：
--
作者：
Ji Z;Chen Q;Niu S;Leng T;Rubin DL
目的 通过构建深度神经网络投票系统，在不使用视网膜层分割的情况下，自动准确地分割谱域光学相干断层扫描（SD-OCT）图像中的地理萎缩（GA）。方法构建基于深度网络的SD-OCT图像自动GA分割方法。深度网络的结构由五层组成，包括一层输入层、三层隐藏层和一层输出层。在训练阶段，将具有 1024 个特征的标记 A 扫描直接输入网络作为输入层以获得深度表示。然后训练软最大分类器来确定每个像素的标签。最后，使用投票决策策略来细化 10 个经过训练的模型的分割结果。结果使用两个带有遗传算法的图像数据集来评估模型。对于第一个数据集，我们的算法获得平均重叠率（OR）86.94％±8.75％，绝对面积差（AAD）11.49％±11.50％，相关系数（CC）0.9857；对于第二个数据集，该方法的平均 OR、AAD 和 CC 分别为 81.66% ± 10.93%、8.30% ± 9.09% 和 0.9952。与两个数据集上的几种最先进的算法相比，所提出的算法能够分别提高超过 5% 和 10% 的分割精度。结论 与依赖视网膜层分割结果的最先进方法相比，在没有视网膜层分割的情况下，所提出的算法可以产生更高的分割精度并且更稳定。我们的模型可以从 SD-OCT 图像中提供可靠的 GA 分割，并可用于晚期非渗出性 AMD 的临床诊断。转化相关性 本研究基于深度神经网络，提出了一种准确的 SD-OCT 图像 GA 分割方法，无需使用任何视网膜层分割结果，并可能有助于提高对高级非渗出性 AMD 的理解。
Purpose To automatically and accurately segment geographic atrophy (GA) in spectral-domain optical coherence tomography (SD-OCT) images by constructing a voting system with deep neural networks without the use of retinal layer segmentation. Methods An automatic GA segmentation method for SD-OCT images based on the deep network was constructed. The structure of the deep network was composed of five layers, including one input layer, three hidden layers, and one output layer. During the training phase, the labeled A-scans with 1024 features were directly fed into the network as the input layer to obtain the deep representations. Then a soft-max classifier was trained to determine the label of each individual pixel. Finally, a voting decision strategy was used to refine the segmentation results among 10 trained models. Results Two image data sets with GA were used to evaluate the model. For the first dataset, our algorithm obtained a mean overlap ratio (OR) 86.94% ± 8.75%, absolute area difference (AAD) 11.49% ± 11.50%, and correlation coefficients (CC) 0.9857; for the second dataset, the mean OR, AAD, and CC of the proposed method were 81.66% ± 10.93%, 8.30% ± 9.09%, and 0.9952, respectively. The proposed algorithm was capable of improving over 5% and 10% segmentation accuracy, respectively, when compared with several state-of-the-art algorithms on two data sets. Conclusions Without retinal layer segmentation, the proposed algorithm could produce higher segmentation accuracy and was more stable when compared with state-of-the-art methods that relied on retinal layer segmentation results. Our model may provide reliable GA segmentations from SD-OCT images and be useful in the clinical diagnosis of advanced nonexudative AMD. Translational Relevance Based on the deep neural networks, this study presents an accurate GA segmentation method for SD-OCT images without using any retinal layer segmentation results, and may contribute to improved understanding of advanced nonexudative AMD.
登录
查看更多内容
DOI：
10.1097/01.iae.0000433986.32991.1e
发表时间：
2014-03-01
影响因子：
3.3
作者：
Panthier, Christophe;Querques, Giuseppe;Souied, Eric H.
通讯作者：
Souied, Eric H.
影响因子：
13.7
作者：
Niu, Sijie;de Sisternes, Luis;Leng, Theodore
通讯作者：
Leng, Theodore
影响因子：
4.4
作者：
Abramoff, Michael David;Lou, Yiyue;Niemeijer, Meindert
通讯作者：
Niemeijer, Meindert
影响因子：
7.7
作者：
Feeny AK;Tadarati M;Freund DE;Bressler NM;Burlina P
通讯作者：
Burlina P
影响因子：
13.7
作者：
Klein, Ronald;Klein, Barbara E. K.;Gangnon, Ronald E.
通讯作者：
Gangnon, Ronald E.