Semiautomated Segmentation of the Choroid in Spectral-Domain Optical Coherence Tomography Volume Scans
Semiautomated Segmentation of the Choroid in Spectral-Domain Optical Coherence Tomography Volume Scans
复制标题
DOI：
10.1167/iovs.12-10578
复制
发表时间：
2013-03-01
影响因子：
4.4
通讯作者：
Sadda, Srinivas R.
中科院分区：
文献类型：
--
作者：
Hu, Zhihong;Wu, Xiaodong;Sadda, Srinivas R.
目的。脉络膜的变化，特别是其厚度，被认为在许多视网膜疾病的病理生理学中具有重要意义。本研究的目的是采用图形搜索算法来半自动识别谱域光学相干断层扫描 (SD-OCT) 体积扫描中的脉络膜层，并将其性能与手动描绘进行比较。方法。基于图形的多级分割方法用于识别脉络膜，脉络膜定义为 RPE 带外缘与脉络膜-巩膜交界处之间的层。从 20 名健康受试者和 10 名非新生血管性 AMD 受试者中随机选择 30 个黄斑 SD-OCT（1024 x 37 x 496 体素，Heidelberg Spectralis）体积。将脉络膜边界的位置和由此产生的厚度与两名分级员进行的一致手动描绘进行比较。为了统计分析的一致性，左眼在x方向水平翻转。 结果。算法定义的 RPE 外缘和脉络膜-巩膜交界处的位置与手动描绘一致，导致健康受试者的脉络膜厚度值高度相关，r = 0.91 至 0.93，非新生血管性 AMD 患者的 r = 0.94。在所有情况下，RPE 外部边界的算法和手动分割之间的平均和绝对差异为 -0.74 +/- 3.27 μm 和 3.15 +/- 3.07 μm；脉络膜-巩膜交界处为-3.90+/-15.93μm和21.39+/-10.71μm。结论。在正常眼睛和非新生血管性 AMD 眼睛中，算法与手动脉络膜分割之间观察到了极好的一致性。 AMD 眼的脉络膜较薄。半自动脉络膜厚度计算可能有助于脉络膜的大规模定量研究。 （投资眼科可见科学。2013 年；54：17221729）DOI：10.1167/iovs.12-10578
PURPOSE. Changes in the choroid, in particular its thickness, are believed to be of importance in the pathophysiology of a number of retinal diseases. The purpose of this study was to adapt the graph search algorithm to semiautomatically identify the choroidal layer in spectral-domain optical coherence tomography (SD-OCT) volume scans and compare its performance to manual delineation.METHODS. A graph-based multistage segmentation approach was used to identify the choroid, defined as the layer between the outer border of the RPE band and the choroid-sclera junction. Thirty randomly chosen macular SD-OCT (1024 x 37 x 496 voxels, Heidelberg Spectralis) volumes were obtained from 20 healthy subjects and 10 subjects with non-neovascular AMD. The positions of the choroidal borders and resultant thickness were compared with consensus manual delineation performed by two graders. For consistency of the statistical analysis, the left eyes were horizontally flipped in the x-direction.RESULTS. The algorithm-defined position of the outer RPE border and choroid-sclera junction was consistent with the manual delineation, resulting in highly correlated choroidal thickness values with r = 0.91 to 0.93 for the healthy subjects and 0.94 for patients with non-neovascular AMD. Across all cases, the mean and absolute differences between the algorithm and manual segmentation for the outer RPE boundary was -0.74 +/- 3.27 mu m and 3.15 +/- 3.07 mu m; and for the choroid-sclera junction was -3.90 +/- 15.93 mu m and 21.39 +/- 10.71 mu m.CONCLUSIONS. Excellent agreement was observed between the algorithm and manual choroidal segmentation in both normal eyes and those with non-neovascular AMD. The choroid was thinner in AMD eyes. Semiautomated choroidal thickness calculation may be useful for large-scale quantitative studies of the choroid. (Invest Ophthalmol Vis Sci. 2013;54:17221729) DOI:10.1167/iovs.12-10578