Grbatinić Ivan, Marić Dušica L, Milošević Nebojša T
Laboratory of Digital Image Processing, School of Medicine, University of Belgrade, Serbia.
Department of Anatomy, School of Medicine, University of Novi Sad, Novi Sad, Serbia.
J Theor Biol. 2015 Apr 7;370:11-20. doi: 10.1016/j.jtbi.2015.01.024. Epub 2015 Jan 30.
Topological (central vs. border neuron type) and morphological classification of adult human dentate nucleus neurons according to their quantified histomorphological properties using neural networks on real and virtual neuron samples.
In the real sample 53.1% and 14.1% of central and border neurons, respectively, are classified correctly with total of 32.8% of misclassified neurons. The most important result present 62.2% of misclassified neurons in border neurons group which is even greater than number of correctly classified neurons (37.8%) in that group, showing obvious failure of network to classify neurons correctly based on computational parameters used in our study. On the virtual sample 97.3% of misclassified neurons in border neurons group which is much greater than number of correctly classified neurons (2.7%) in that group, again confirms obvious failure of network to classify neurons correctly. Statistical analysis shows that there is no statistically significant difference in between central and border neurons for each measured parameter (p>0.05). Total of 96.74% neurons are morphologically classified correctly by neural networks and each one belongs to one of the four histomorphological types: (a) neurons with small soma and short dendrites, (b) neurons with small soma and long dendrites, (c) neuron with large soma and short dendrites, (d) neurons with large soma and long dendrites. Statistical analysis supports these results (p<0.05).
Human dentate nucleus neurons can be classified in four neuron types according to their quantitative histomorphological properties. These neuron types consist of two neuron sets, small and large ones with respect to their perykarions with subtypes differing in dendrite length i.e. neurons with short vs. long dendrites. Besides confirmation of neuron classification on small and large ones, already shown in literature, we found two new subtypes i.e. neurons with small soma and long dendrites and with large soma and short dendrites. These neurons are most probably equally distributed throughout the dentate nucleus as no significant difference in their topological distribution is observed.
根据真实和虚拟神经元样本的量化组织形态学特性，利用神经网络对成年人类齿状核神经元进行拓扑学（中央神经元与边界神经元类型）和形态学分类。
在真实样本中，中央神经元和边界神经元的正确分类率分别为53.1%和14.1%，总错误分类率为32.8%。最重要的结果是，边界神经元组中错误分类的神经元占62.2%，甚至超过了该组中正确分类的神经元数量（37.8%），这表明基于我们研究中使用的计算参数，网络在正确分类神经元方面明显失败。在虚拟样本中，边界神经元组中97.3%的神经元被错误分类，这一比例远高于该组中正确分类的神经元数量（2.7%），再次证实了网络在正确分类神经元方面明显失败。统计分析表明，每个测量参数在中央神经元和边界神经元之间没有统计学上的显著差异（p>0.05）。神经网络对96.74%的神经元进行了正确的形态学分类，每个神经元都属于四种组织形态学类型之一：（a）胞体小且树突短的神经元，（b）胞体小且树突长的神经元，（c）胞体大且树突短的神经元，（d）胞体大且树突长的神经元。统计分析支持这些结果（p<0.05）。
人类齿状核神经元可根据其定量组织形态学特性分为四种神经元类型。这些神经元类型由两个神经元集合组成，即相对于其核周体大小而言的小神经元和大神经元，其亚型在树突长度上有所不同，即树突短的神经元与树突长的神经元。除了证实文献中已显示的小神经元和大神经元的分类外，我们还发现了两种新的亚型，即胞体小且树突长的神经元和胞体大且树突短的神经元。由于未观察到它们在拓扑分布上的显著差异，这些神经元很可能在整个齿状核中均匀分布。
