Dendritic spine detection using curvilinear structure detector and LDA classifier
Dendritic spine detection using curvilinear structure detector and LDA classifier
复制标题
DOI：
10.1016/j.neuroimage.2007.02.044
复制
发表时间：
2007-06-01
期刊：
影响因子：
5.7
通讯作者：
Wong, Stephen T. C.
中科院分区：
文献类型：
--
作者：
Zhang, Yong;Zhou, Xiaobo;Wong, Stephen T. C.
树突棘是携带突触的小的球状细胞隔室。生物学家一直通过在细胞内水平上检查树突棘的形态学和统计学变化来研究生物化学途径。本文提出了一种新的方法自动检测神经元图像中的树突棘。树突棘被识别为沿着光学方向在图像堆栈的2D投影中附着或分离到多个树突骨干的可变形状的小物体。我们扩展的曲线结构检测器提取的边界以及中心线的树突骨干和棘。我们进一步使用线性判别分析（LDA）构建分类器，将附着的脊椎分类为有效和无效类型，以提高脊椎检测的准确性。我们评估所提出的方法通过比较与手动结果的骨干长度，脊柱数量，脊柱长度和脊柱密度。(c)2007爱思唯尔公司All rights reserved.
Dendritic spines are small, bulbous cellular compartments that carry synapses. Biologists have been studying the biochemical pathways by examining the morphological and statistical changes of the dendritic spines at the intracellular level. In this paper a novel approach is presented for automated detection of dendritic spines in neuron images. The dendritic spines are recognized as small objects of variable shape attached or detached to multiple dendritic backbones in the 2D projection of the image stack along the optical direction. We extend the curvilinear structure detector to extract the boundaries as well as the centerlines for the dendritic backbones and spines. We further build a classifier using Linear Discriminate Analysis (LDA) to classify the attached spines into valid and invalid types to improve the accuracy of the spine detection. We evaluate the proposed approach by comparing with the manual results in terms of backbone length, spine number, spine length, and spine density. (c) 2007 Elsevier Inc. All rights reserved.