Neurons from the adult human dentate nucleus: Neural networks in the neuron classification

被引:8
|
作者
Grbatinic, Ivan [1 ]
Maric, Dusica L. [2 ]
Milosevic, Nebojsa T. [3 ]
机构
[1] Univ Belgrade, Sch Med, Lab Digital Image Proc, Belgrade 11001, Serbia
[2] Univ Novi Sad, Sch Med, Dept Anat, Novi Sad, Serbia
[3] Univ Belgrade, Sch Med, Dept Biophys, Belgrade 11001, Serbia
关键词
Dentate nucleus; Neuron types; Neural networks; Classification; SUPRACHIASMATIC NUCLEUS; QUANTITATIVE-ANALYSIS; HUMAN CEREBELLUM; DENDRITIC TREE; CELL; SIZE; CAT;
D O I
10.1016/j.jtbi.2015.01.024
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Objectives: 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. Results: 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). Conclusion: 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. (C) 2015 Elsevier Ltd. All rights reserved.
引用
收藏
页码:11 / 20
页数:10
相关论文
共 50 条
  • [21] Classification Tree Extraction from Trained Artificial Neural Networks
    Bondarenko, Andrey
    Aleksejeva, Ludmila
    Jumutc, Vilen
    Borisov, Arkady
    ICTE 2016, 2017, 104 : 556 - 563
  • [22] Neuron type classification in rat brain based on integrative convolutional and tree-based recurrent neural networks
    Zhang, Tielin
    Zeng, Yi
    Zhang, Yue
    Zhang, Xinhe
    Shi, Mengting
    Tang, Likai
    Zhang, Duzhen
    Xu, Bo
    SCIENTIFIC REPORTS, 2021, 11 (01)
  • [23] Age and gender classification from face images using neural networks
    Nakano, M
    Yasukata, F
    Fukumi, M
    PROCEEDINGS OF THE SIXTH IASTED INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING, 2004, : 69 - 73
  • [24] Binary Neural Networks for Classification of Voice Commands From Throat Microphone
    Ribeiro, Fabio Cisne
    Santos Carvalho, Raphael Torres
    Cortez, Paulo Cesar
    De Albuquerque, Victor Hugo C.
    Reboucas Filho, Pedro Pedrosa
    IEEE ACCESS, 2018, 6 : 70130 - 70144
  • [25] MULTISCALE COMPUTATIONS ON NEURAL NETWORKS: FROM THE INDIVIDUAL NEURON INTERACTIONS TO THE MACROSCOPIC-LEVEL ANALYSIS
    Spiliotis, Konstantinos G.
    Siettos, Constantinos I.
    INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 2010, 20 (01): : 121 - 134
  • [26] Gait Phase Classification from Surface EMG Signals Using Neural Networks
    Morbidoni, Christian
    Principi, Lorenzo
    Mascia, Guido
    Strazza, Annachiara
    Verdini, Federica
    Cucchiarelli, Alessandro
    Di Nardo, Francesco
    XV MEDITERRANEAN CONFERENCE ON MEDICAL AND BIOLOGICAL ENGINEERING AND COMPUTING - MEDICON 2019, 2020, 76 : 75 - 82
  • [27] Estimating Human Activities from Smartwatches with Feedforward Neural Networks
    Basterrech, Sebastian
    INTELLIGENT DATA ANALYSIS AND APPLICATIONS, (ECC 2016), 2017, 535 : 51 - 57
  • [28] Classification of Small Region of Interest from Remote Images Using Neural Networks
    Ichim, Loretta
    Popescu, Dan
    2020 24TH INTERNATIONAL CONFERENCE ON SYSTEM THEORY, CONTROL AND COMPUTING (ICSTCC), 2020, : 862 - 867
  • [29] Automated plankton classification from holographic imagery with deep convolutional neural networks
    Guo, Buyu
    Nyman, Lisa
    Nayak, Aditya R.
    Milmore, David
    McFarland, Malcolm
    Twardowski, Michael S.
    Sullivan, James M.
    Yu, Jia
    Hong, Jiarong
    LIMNOLOGY AND OCEANOGRAPHY-METHODS, 2021, 19 (01): : 21 - 36
  • [30] Classification of Electromyography Signals Using Neural Networks and Features From Various Domains
    Taghizadeh, Zahra
    Nateghi, Sina
    1ST NATIONAL BIOMEDICAL ENGINEERING CONFERENCE (NBEC 2021): ADVANCED TECHNOLOGY FOR MODERN HEALTHCARE, 2021, : 65 - 70