Shi Peng, Zhou Xiaobo, Li Qing, Baron Matthew, Teylan Merilee A, Kim Yong, Wong Stephen T C
Center for Biotechnology and Informatics, The Methodist Hospital Research Institute, and Department of Radiology, The Methodist Hospital, Weill Cornell Medical College, Houston, TX 77030, USA.
Proc IEEE Int Symp Biomed Imaging. 2009 Jun 28:1019-1022. doi: 10.1109/ISBI.2009.5193228.
Recent studies on neuron imaging show that there is a strong relationship between the functional properties of a neuron and its morphology, especially its dendritic spine structures. However, most of the current methods for morphological spine classification only concern features in two-dimensional (2D) space, which consequently decreases the accuracy of dendritic spine analysis. In this paper, we propose a semi-supervised learning (SSL) framework, in which spine phenotypes in three-dimensional (3D) space are considered. With training only on a few pre-classified inputs, the rest of the spines can be identified effectively. We also derived a new scheme using an affinity matrix between features to further improve the accuracy. Our experimental results indicate that a small training dataset is sufficient to classify detected dendritic spines.
近期关于神经元成像的研究表明，神经元的功能特性与其形态，尤其是其树突棘结构之间存在着密切关系。然而，当前大多数用于形态学棘分类的方法仅关注二维（2D）空间中的特征，这导致树突棘分析的准确性降低。在本文中，我们提出了一种半监督学习（SSL）框架，其中考虑了三维（3D）空间中的棘表型。仅通过对少数预分类输入进行训练，就可以有效地识别其余的棘。我们还推导了一种使用特征之间的亲和矩阵的新方案，以进一步提高准确性。我们的实验结果表明，一个小的训练数据集就足以对检测到的树突棘进行分类。
