Deep learning networks reflect cytoarchitectonic features used in brain mapping

Abstract The 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 mappi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kai Kiwitz, Christian Schiffer, Hannah Spitzer, Timo Dickscheid, Katrin Amunts
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/67bde2c876a64ebc9c7c1c47d04d06a8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:67bde2c876a64ebc9c7c1c47d04d06a8
record_format	dspace
spelling	oai:doaj.org-article:67bde2c876a64ebc9c7c1c47d04d06a82021-12-02T13:34:00ZDeep learning networks reflect cytoarchitectonic features used in brain mapping10.1038/s41598-020-78638-y2045-2322https://doaj.org/article/67bde2c876a64ebc9c7c1c47d04d06a82020-12-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-78638-yhttps://doaj.org/toc/2045-2322Abstract The 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.Kai KiwitzChristian SchifferHannah SpitzerTimo DickscheidKatrin AmuntsNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-15 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Kai Kiwitz Christian Schiffer Hannah Spitzer Timo Dickscheid Katrin Amunts Deep learning networks reflect cytoarchitectonic features used in brain mapping
description	Abstract The 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.
format	article
author	Kai Kiwitz Christian Schiffer Hannah Spitzer Timo Dickscheid Katrin Amunts
author_facet	Kai Kiwitz Christian Schiffer Hannah Spitzer Timo Dickscheid Katrin Amunts
author_sort	Kai Kiwitz
title	Deep learning networks reflect cytoarchitectonic features used in brain mapping
title_short	Deep learning networks reflect cytoarchitectonic features used in brain mapping
title_full	Deep learning networks reflect cytoarchitectonic features used in brain mapping
title_fullStr	Deep learning networks reflect cytoarchitectonic features used in brain mapping
title_full_unstemmed	Deep learning networks reflect cytoarchitectonic features used in brain mapping
title_sort	deep learning networks reflect cytoarchitectonic features used in brain mapping
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/67bde2c876a64ebc9c7c1c47d04d06a8
work_keys_str_mv	AT kaikiwitz deeplearningnetworksreflectcytoarchitectonicfeaturesusedinbrainmapping AT christianschiffer deeplearningnetworksreflectcytoarchitectonicfeaturesusedinbrainmapping AT hannahspitzer deeplearningnetworksreflectcytoarchitectonicfeaturesusedinbrainmapping AT timodickscheid deeplearningnetworksreflectcytoarchitectonicfeaturesusedinbrainmapping AT katrinamunts deeplearningnetworksreflectcytoarchitectonicfeaturesusedinbrainmapping
_version_	1718392800283721728

Deep learning networks reflect cytoarchitectonic features used in brain mapping

Ejemplares similares