Please use this identifier to cite or link to this item: https://open.uns.ac.rs/handle/123456789/6127
DC FieldValueLanguage
dc.contributor.authorGrbatinić, Ivanen_US
dc.contributor.authorMarić, Dušicaen_US
dc.contributor.authorMilošević, Nebojšaen_US
dc.date.accessioned2019-09-30T08:52:49Z-
dc.date.available2019-09-30T08:52:49Z-
dc.date.issued2015-04-07-
dc.identifier.issn00225193en_US
dc.identifier.urihttps://open.uns.ac.rs/handle/123456789/6127-
dc.description.abstract© 2015 Elsevier Ltd. 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.en
dc.relation.ispartofJournal of Theoretical Biologyen
dc.titleNeurons from the adult human dentate nucleus: Neural networks in the neuron classificationen_US
dc.typeJournal/Magazine Articleen_US
dc.identifier.doi10.1016/j.jtbi.2015.01.024-
dc.identifier.scopus2-s2.0-84922713822-
dc.identifier.urlhttps://api.elsevier.com/content/abstract/scopus_id/84922713822-
dc.description.versionUnknownen_US
dc.relation.lastpage20en
dc.relation.firstpage11en
dc.relation.volume370en
item.grantfulltextnone-
item.fulltextNo Fulltext-
crisitem.author.deptMedicinski fakultet, Katedra za anatomiju-
crisitem.author.parentorgMedicinski fakultet-
Appears in Collections:MDF Publikacije/Publications
Show simple item record

SCOPUSTM   
Citations

10
checked on Mar 15, 2024

Page view(s)

15
Last Week
12
Last month
0
checked on May 3, 2024

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.