000888898 001__ 888898
000888898 005__ 20231123201912.0
000888898 0247_ $$2doi$$a10.1038/s41598-020-78638-y
000888898 0247_ $$2Handle$$a2128/26562
000888898 0247_ $$2altmetric$$aaltmetric:96093589
000888898 0247_ $$2pmid$$a33328511
000888898 0247_ $$2WOS$$aWOS:000603657800005
000888898 037__ $$aFZJ-2020-05303
000888898 082__ $$a530
000888898 1001_ $$0P:(DE-Juel1)171890$$aKiwitz, Kai$$b0$$eCorresponding author$$ufzj
000888898 245__ $$aDeep learning networks reflect cytoarchitectonic features used in brain mapping
000888898 260__ $$aDarmstadt$$bGSI$$c2020
000888898 3367_ $$2DRIVER$$aarticle
000888898 3367_ $$2DataCite$$aOutput Types/Journal article
000888898 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1700723389_27668
000888898 3367_ $$2BibTeX$$aARTICLE
000888898 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000888898 3367_ $$00$$2EndNote$$aJournal Article
000888898 520__ $$aThe distribution of neurons in the cortex (cytoarchitecture) differs between cortical areas and constitutes the basis for structural maps of the human brain. Deep learning approaches provide a promising alternative to overcome throughput limitations of currently used cytoarchitectonic mapping methods, but typically lack insight as to what extent they follow cytoarchitectonic principles. We therefore investigated in how far the internal structure of deep convolutional neural networks trained for cytoarchitectonic brain mapping reflect traditional cytoarchitectonic features, and compared them to features of the current grey level index (GLI) profile approach. The networks consisted of a 10-block deep convolutional architecture trained to segment the primary and secondary visual cortex. Filter activations of the networks served to analyse resemblances to traditional cytoarchitectonic features and comparisons to the GLI profile approach. Our analysis revealed resemblances to cellular, laminar- as well as cortical area related cytoarchitectonic features. The networks learned filter activations that reflect the distinct cytoarchitecture of the segmented cortical areas with special regard to their laminar organization and compared well to statistical criteria of the GLI profile approach. These results confirm an incorporation of relevant cytoarchitectonic features in the deep convolutional neural networks and mark them as a valid support for high-throughput cytoarchitectonic mapping workflows.
000888898 536__ $$0G:(DE-HGF)POF3-571$$a571 - Connectivity and Activity (POF3-571)$$cPOF3-571$$fPOF III$$x0
000888898 536__ $$0G:(EU-Grant)720270$$aHBP SGA1 - Human Brain Project Specific Grant Agreement 1 (720270)$$c720270$$fH2020-Adhoc-2014-20$$x1
000888898 536__ $$0G:(EU-Grant)785907$$aHBP SGA2 - Human Brain Project Specific Grant Agreement 2 (785907)$$c785907$$fH2020-SGA-FETFLAG-HBP-2017$$x2
000888898 536__ $$0G:(EU-Grant)945539$$aHBP SGA3 - Human Brain Project Specific Grant Agreement 3 (945539)$$c945539$$fH2020-SGA-FETFLAG-HBP-2019$$x3
000888898 536__ $$0G:(DE-Juel1)jinm16_20200501$$aAutomatic classification of cytoarchitectonic human cortical brain regions using Deep Learning (jinm16_20200501)$$cjinm16_20200501$$fAutomatic classification of cytoarchitectonic human cortical brain regions using Deep Learning$$x4
000888898 536__ $$0G:(DE-Juel1)HGF-SMHB-2013-2017$$aSMHB - Supercomputing and Modelling for the Human Brain (HGF-SMHB-2013-2017)$$cHGF-SMHB-2013-2017$$fSMHB$$x5
000888898 536__ $$0G:(DE-Juel-1)E.40401.62$$aHelmholtz AI - Helmholtz Artificial Intelligence  Coordination Unit – Local Unit FZJ (E.40401.62)$$cE.40401.62$$x6
000888898 7001_ $$0P:(DE-Juel1)170068$$aSchiffer, Christian$$b1$$ufzj
000888898 7001_ $$0P:(DE-Juel1)167110$$aSpitzer, Hannah$$b2
000888898 7001_ $$0P:(DE-Juel1)165746$$aDickscheid, Timo$$b3$$ufzj
000888898 7001_ $$0P:(DE-Juel1)131631$$aAmunts, Katrin$$b4$$ufzj
000888898 773__ $$0PERI:(DE-600)2104902-6$$a10.1038/s41598-020-78638-y$$p22039$$tScientific Report$$v10$$x0174-0814$$y2020
000888898 8564_ $$uhttps://juser.fz-juelich.de/record/888898/files/Kiwitz_et_al_Scientific_Reports_2020.pdf$$yOpenAccess
000888898 909CO $$ooai:juser.fz-juelich.de:888898$$popenaire$$pdnbdelivery$$pec_fundedresources$$pVDB$$pdriver$$popen_access
000888898 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171890$$aForschungszentrum Jülich$$b0$$kFZJ
000888898 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)170068$$aForschungszentrum Jülich$$b1$$kFZJ
000888898 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)165746$$aForschungszentrum Jülich$$b3$$kFZJ
000888898 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131631$$aForschungszentrum Jülich$$b4$$kFZJ
000888898 9131_ $$0G:(DE-HGF)POF3-571$$1G:(DE-HGF)POF3-570$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lDecoding the Human Brain$$vConnectivity and Activity$$x0
000888898 9132_ $$0G:(DE-HGF)POF4-899$$1G:(DE-HGF)POF4-890$$2G:(DE-HGF)POF4-800$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bProgrammungebundene Forschung$$lohne Programm$$vohne Topic$$x0
000888898 9141_ $$y2020
000888898 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000888898 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000888898 9201_ $$0I:(DE-Juel1)INM-1-20090406$$kINM-1$$lStrukturelle und funktionelle Organisation des Gehirns$$x0
000888898 9201_ $$0I:(DE-82)080012_20140620$$kJARA-HPC$$lJARA - HPC$$x1
000888898 980__ $$ajournal
000888898 980__ $$aVDB
000888898 980__ $$aI:(DE-Juel1)INM-1-20090406
000888898 980__ $$aI:(DE-82)080012_20140620
000888898 980__ $$aUNRESTRICTED
000888898 9801_ $$aFullTexts