Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina; Department of Biomedical Engineering, Duke University, Durham, North Carolina; Department of Electrical & Computer Engineering, Duke University, Durham, North Carolina.
Department of Biomedical Engineering, Duke University, Durham, North Carolina.
Ophthalmology. 2014 Jan;121(1):162-172. doi: 10.1016/j.ophtha.2013.07.013. Epub 2013 Aug 29.
To define quantitative indicators for the presence of intermediate age-related macular degeneration (AMD) via spectral-domain optical coherence tomography (SD-OCT) imaging of older adults.
Evaluation of diagnostic test and technology.
One eye from 115 elderly subjects without AMD and 269 subjects with intermediate AMD from the Age-Related Eye Disease Study 2 (AREDS2) Ancillary SD-OCT Study.
We semiautomatically delineated the retinal pigment epithelium (RPE) and RPE drusen complex (RPEDC, the axial distance from the apex of the drusen and RPE layer to Bruch's membrane) and total retina (TR, the axial distance between the inner limiting and Bruch's membranes) boundaries. We registered and averaged the thickness maps from control subjects to generate a map of "normal" non-AMD thickness. We considered RPEDC thicknesses larger or smaller than 3 standard deviations from the mean as abnormal, indicating drusen or geographic atrophy (GA), respectively. We measured TR volumes, RPEDC volumes, and abnormal RPEDC thickening and thinning volumes for each subject. By using different combinations of these 4 disease indicators, we designed 5 automated classifiers for the presence of AMD on the basis of the generalized linear model regression framework. We trained and evaluated the performance of these classifiers using the leave-one-out method.
The range and topographic distribution of the RPEDC and TR thicknesses in a 5-mm diameter cylinder centered at the fovea.
The most efficient method for separating AMD and control eyes required all 4 disease indicators. The area under the curve (AUC) of the receiver operating characteristic (ROC) for this classifier was >0.99. Overall neurosensory retinal thickening in eyes with AMD versus control eyes in our study contrasts with previous smaller studies.
We identified and validated efficient biometrics to distinguish AMD from normal eyes by analyzing the topographic distribution of normal and abnormal RPEDC thicknesses across a large atlas of eyes. We created an online atlas to share the 38 400 SD-OCT images in this study, their corresponding segmentations, and quantitative measurements.
通过对老年人的光谱域光学相干断层扫描（SD-OCT）成像来定义中间年龄相关性黄斑变性（AMD）存在的定量指标。
诊断测试和技术的评估。
无 AMD 的 115 名老年受试者和来自年龄相关性眼病研究 2（AREDS2）辅助 SD-OCT 研究的 269 名中间 AMD 受试者的一只眼。
我们半自动描绘视网膜色素上皮（RPE）和 RPE 斑复合物（RPEDC，从斑和 RPE 层的顶点到布鲁赫膜的轴向距离）和总视网膜（TR，内界膜和布鲁赫膜之间的轴向距离）边界。我们注册并平均对照受试者的厚度图以生成“正常”非 AMD 厚度图。我们认为 RPEDC 厚度大于或小于平均值 3 个标准差的表示异常，分别表示斑或地理萎缩（GA）。我们为每个受试者测量 TR 体积、RPEDC 体积以及异常 RPEDC 增厚和变薄体积。通过使用这 4 种疾病指标的不同组合，我们基于广义线性模型回归框架为 AMD 的存在设计了 5 种自动化分类器。我们使用留一法训练和评估这些分类器的性能。
以黄斑为中心的 5 毫米直径圆柱内 RPEDC 和 TR 厚度的范围和地形分布。
用于分离 AMD 和对照眼的最有效方法需要所有 4 种疾病指标。该分类器的接收器工作特征（ROC）曲线下面积（AUC）>0.99。与之前的较小研究相比，我们的研究中 AMD 眼与对照眼的神经感觉视网膜整体增厚。
我们通过分析正常和异常 RPEDC 厚度的地形分布，确定并验证了有效的生物统计学方法，以区分 AMD 眼和正常眼。我们创建了一个在线图谱，以共享本研究中的 38400 张 SD-OCT 图像、它们的相应分割和定量测量值。
