Kernel regression based segmentation of optical coherence tomography images with diabetic macular edema
Kernel regression based segmentation of optical coherence tomography images with diabetic macular edema
复制标题
DOI：
10.1364/boe.6.001172
复制
发表时间：
2015-04-01
影响因子：
3.4
通讯作者：
Farsiu, Sina
中科院分区：
文献类型：
--
作者：
Chiu, Stephanie J.;Allingham, Michael J.;Farsiu, Sina
我们提出了一个全自动的算法来识别充满液体的区域和七个视网膜层的光谱域光学相干断层扫描图像的眼睛与糖尿病性黄斑水肿（DME）。为了实现这一点，我们开发了一种基于核回归（KR）的分类方法来估计流体和视网膜层的位置。然后，我们使用这些分类估计作为指导，使用我们先前描述的图论和动态编程（GTDP）框架更准确地分割视网膜层边界。我们验证了我们的算法对110个B型扫描从10例严重DME病理，显示整体平均骰子系数为0.78时，比较我们的KR + GTDP算法的专家分级。这与观察者间Dice系数0.79相当。整个数据集可在线获取，包括我们的自动和手动分割结果。据我们所知，这是第一个经过验证的，全自动的，七层和流体分割方法，已应用于包含严重DME的真实图像。(C)2015美国光学学会
We present a fully automatic algorithm to identify fluid-filled regions and seven retinal layers on spectral domain optical coherence tomography images of eyes with diabetic macular edema (DME). To achieve this, we developed a kernel regression (KR)-based classification method to estimate fluid and retinal layer positions. We then used these classification estimates as a guide to more accurately segment the retinal layer boundaries using our previously described graph theory and dynamic programming (GTDP) framework. We validated our algorithm on 110 B-scans from ten patients with severe DME pathology, showing an overall mean Dice coefficient of 0.78 when comparing our KR + GTDP algorithm to an expert grader. This is comparable to the inter-observer Dice coefficient of 0.79. The entire data set is available online, including our automatic and manual segmentation results. To the best of our knowledge, this is the first validated, fully-automated, seven-layer and fluid segmentation method which has been applied to real-world images containing severe DME. (C) 2015 Optical Society of America