Haeker Mona, Wu Xiaodong, Abràmoff Michael, Kardon Randy, Sonka Milan
Department of Electrical & Computer Engineering, University of Iowa, Iowa City, IA 52242, USA.
Inf Process Med Imaging. 2007;20:607-18. doi: 10.1007/978-3-540-73273-0_50.
We present a method for the incorporation of regional image information in a 3-D graph-theoretic approach for optimal multiple surface segmentation. By transforming the multiple surface segmentation task into finding a minimum-cost closed set in a vertex-weighted graph, the optimal set of feasible surfaces with respect to an objective function can be found. In the past, this family of graph search applications only used objective functions which incorporated "on-surface" costs. Here, novel "in-region" costs are incorporated. Our new approach is applied to the segmentation of seven intraretinal layer surfaces of 24 3-D macular optical coherence tomography images from 12 subjects. Compared to an expert-defined independent standard, unsigned border positioning errors are comparable to the inter-observer variability (7.8 +/- 5.0 microm and 8.1 +/- 3.6 microm, respectively).
我们提出了一种在三维图论方法中纳入区域图像信息以实现最优多表面分割的方法。通过将多表面分割任务转化为在顶点加权图中寻找最小成本封闭集，可以找到相对于目标函数的最优可行表面集。过去，这类图搜索应用仅使用包含“表面上”成本的目标函数。在此，纳入了新颖的“区域内”成本。我们的新方法应用于对来自12名受试者的24幅三维黄斑光学相干断层扫描图像的七个视网膜内层表面进行分割。与专家定义的独立标准相比，无符号边界定位误差与观察者间的变异性相当（分别为7.8±5.0微米和8.1±3.6微米）。
