Thickness profiles of retinal layers by optical coherence tomography image segmentation.
Thickness profiles of retinal layers by optical coherence tomography image segmentation.
复制标题
DOI：
10.1016/j.ajo.2008.06.010
复制
发表时间：
2008-11
影响因子：
4.2
通讯作者：
Zelkha, Ruth
中科院分区：
文献类型：
--
作者：
Bagci, Ahmet Murat;Shahidi, Mahnaz;Ansari, Rashid;Blair, Michael;Blair, Norman Paul;Zelkha, Ruth
报告了一种图像分割算法，该算法用于光学相干断层扫描（OCT）图像中6层视网膜的定量厚度测量。前瞻性横断面研究。分别对15例和10例正常健康人进行时域和谱域OCT成像。基于二维边缘检测方案，开发了一种专用的边界检测软件算法，增强沿视网膜深度的边缘，同时抑制散斑噪声。将算法得到的自动边界检测和定量厚度测量结果与3名观测者手工标记的边界测量结果进行比较。生成正常受试者视网膜6层的厚度分布图。该算法确定了视网膜神经纤维层（NFL）、内丛状层和神经节细胞层（IPL+GCL）、内核层（INL）、外丛状层（OPL）、外核层和光感受器内段（ONL+PIS）、光感受器外段（POS）等6层的7个边界并测量了厚度。人工和自动边界检测的均方根误差（RMSE）在4 ~ 9微米之间。自动和手动厚度测量之间差异的平均绝对值在3 - 4微米之间，与观察者之间的差异相当。视网膜内部厚度显示最小厚度在中央窝，对应于正常解剖。OPL和ONL+PIS厚度分布分别在中央凹处显示最小和最大厚度。POS厚度分布沿扫描中央凹相对恒定。该图像分割技术的应用为研究视网膜层厚度随疾病进展和治疗干预的变化提供了前景。
To report an image segmentation algorithm that was developed to provide quantitative thickness measurement of 6 retinal layers in optical coherence tomography (OCT) images. Prospective cross-sectional study. Imaging was performed with time and spectral domain OCT instruments in 15 and 10 normal healthy subjects, respectively. A dedicated software algorithm was developed for boundary detection based on a 2-D edge detection scheme, enhancing edges along the retinal depth while suppressing speckle noise. Automated boundary detection and quantitative thickness measurements derived by the algorithm were compared with measurements obtained from boundaries manually marked by 3 observers. Thickness profiles for 6 retinal layers were generated in normal subjects. The algorithm identified 7 boundaries and measured thickness of 6 retinal layers: nerve fiber layer (NFL), inner plexiform layer and ganglion cell layer (IPL+GCL), inner nuclear layer (INL), outer plexiform layer (OPL), outer nuclear layer and photoreceptor inner segments (ONL+PIS), and photoreceptor outer segments (POS). The root mean squared error (RMSE) between the manual and automatic boundary detection ranged between 4 and 9 microns. The mean absolute values of differences between automated and manual thickness measurements were between 3 – 4 microns, and comparable to inter-observer differences. Inner retinal thickness profiles demonstrated minimum thickness at the fovea, corresponding to normal anatomy. The OPL and ONL+PIS thickness profiles displayed a minimum and maximum thickness at the fovea, respectively. The POS thickness profile was relatively constant along the scan through the fovea. The application of this image segmentation technique is promising for investigating thickness changes of retinal layers due to disease progression and therapeutic intervention.
登录
查看更多内容
影响因子：
4.4
作者：
Ishikawa, H;Stein, DM;Schuman, JS
通讯作者：
Schuman, JS
DOI：
10.1111/j.2517-6161.1977.tb01600.x
发表时间：
1977-01-01
期刊：
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL
影响因子：
--
作者：
DEMPSTER, AP;LAIRD, NM;RUBIN, DB
通讯作者：
RUBIN, DB
DOI：
10.1097/00006982-200607000-00011
发表时间：
2006-07-01
影响因子：
3.3
作者：
Chan, Annie;Duker, Jay S.;Fujimoto, James G.
通讯作者：
Fujimoto, James G.
影响因子：
1.9
作者：
Hoang, QV;Linsenmeier, RA;Curcio, CA
通讯作者：
Curcio, CA
影响因子：
3.8
作者：
Mujat, M;Chan, RC;de Boer, JF
通讯作者：
de Boer, JF