Automatic segmentation and skeletonization of neurons from confocal microscopy images based on the 3-D wavelet transform
Automatic segmentation and skeletonization of neurons from confocal microscopy images based on the 3-D wavelet transform
复制标题
DOI：
10.1109/tip.2002.800888
复制
发表时间：
2002-07-01
影响因子：
10.6
通讯作者：
Obermayer, K
中科院分区：
文献类型：
--
作者：
Dima, A;Scholz, M;Obermayer, K
在这项工作中，我们专注于从三维（3-D）共聚焦显微镜图像中预处理神经元的方法，这是后续详细形态学分析所需的[7]。由于共焦显微镜扫描的特定图像特性，我们必须包括几种基于多尺度边缘的启发式方法[17]，以保证有意义的结果：1）与图像对比度无关的不同尺寸的对象的可靠分割，以及2）基于该分割，沿着分支中心轴计算骨架点，以及3）分支点和问题区域的可靠检测。这些是预处理步骤，用于收集后续构建表示神经元几何形状的图形[27]和最终表面重建[31]所需的信息。
In this work, we focus on methods for the preprocessing of neurons from three-dimensional (3-D) confocal microscopy images, which are needed for a subsequent detailed morphologic analysis [7]. Due to the specific image properties of confocal microscopy scans, we had to include several heuristic approaches which are based on multiscale edges [17] to guarantee meaningful results: 1) a reliable segmentation of objects of different sizes independent of image contrast, and, based on it, 2) the computation of skeleton points along the branch central axes, and 3) the reliable detection of branching points and of problematic regions. These are preprocessing steps to gather information which is needed by the subsequent construction of a graph representing the geometry of the neuron [27] and a final surface reconstruction [31].