Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images.
Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images.
复制标题
DOI：
10.1109/tmi.2009.2016958
复制
发表时间：
2009-09
影响因子：
10.6
通讯作者：
Sonka M
中科院分区：
文献类型：
--
作者：
Garvin MK;Abràmoff MD;Wu X;Russell SR;Burns TL;Sonka M
随着谱域光学相干断层扫描 (OCT) 的引入，与上一代时域 OCT 相比，通常可以获取更大的图像数据集。因此，对处理此类数据的 3D 分割方法的需求变得越来越重要。我们报告了一种用于同时分割多个 3D 表面的图论分割方法，该方法保证在成本函数方面是最优的，并且可直接适用于 3D 光谱 OCT 图像数据的分割。我们提出了一般分层图分割方法的两个扩展：合并不同可行性约束的能力和合并真实区域信息的能力。从来自 13 位受试者的 13 张谱域 OCT 图像的训练集中学习了适当的可行性约束和成本函数。训练后，我们的方法在来自 14 名受试者的 28 张图像的测试集上进行了测试。当分割七个表面（六层）并使用两名眼科医生手动追踪的平均值作为参考标准时，总体平均无符号边界定位误差为 5.69 ± 2.41 µm。该结果与测量的观察者间变异性 5.71 ± 1.98 µm 非常相似。
With the introduction of spectral-domain optical coherence tomography (OCT), much larger image datasets are routinely acquired compared to what was possible using the previous generation of time-domain OCT. Thus, the need for 3-D segmentation methods for processing such data is becoming increasingly important. We report a graph-theoretic segmentation method for the simultaneous segmentation of multiple 3-D surfaces that is guaranteed to be optimal with respect to the cost function and that is directly applicable to the segmentation of 3-D spectral OCT image data. We present two extensions to the general layered graph segmentation method: the ability to incorporate varying feasibility constraints and the ability to incorporate true regional information. Appropriate feasibility constraints and cost functions were learned from a training set of 13 spectral-domain OCT images from 13 subjects. After training, our approach was tested on a test set of 28 images from 14 subjects. An overall mean unsigned border positioning error of 5.69 ± 2.41 µm was achieved when segmenting seven surfaces (six layers) and using the average of the manual tracings of two ophthalmologists as the reference standard. This result is very comparable to the measured interobserver variability of 5.71 ± 1.98 µm.