Please use this identifier to cite or link to this item: https://doi.org/10.15480/882.3819
DC FieldValueLanguage
dc.contributor.authorHolzapfel, Gerhard A.-
dc.contributor.authorLinka, Kevin-
dc.contributor.authorSherifova, Selda-
dc.contributor.authorCyron, Christian J.-
dc.date.accessioned2021-10-08T11:54:32Z-
dc.date.available2021-10-08T11:54:32Z-
dc.date.issued2021-09-08-
dc.identifier.citationJournal of the Royal Society, Interface 18 (182): 20210411 (2021)de_DE
dc.identifier.issn1742-5662de_DE
dc.identifier.urihttp://hdl.handle.net/11420/10482-
dc.description.abstractThe constitutive modelling of soft biological tissues has rapidly gained attention over the last 20 years. Current constitutive models can describe the mechanical properties of arterial tissue. Predicting these properties from microstructural information, however, remains an elusive goal. To address this challenge, we are introducing a novel hybrid modelling framework that combines advanced theoretical concepts with deep learning. It uses data from mechanical tests, histological analysis and images from second-harmonic generation. In this first proof of concept study, our hybrid modelling framework is trained with data from 27 tissue samples only. Even such a small amount of data is sufficient to be able to predict the stress-stretch curves of tissue samples with a median coefficient of determination of R2 = 0.97 from microstructural information, as long as one limits the scope to tissue samples whose mechanical properties remain in the range commonly encountered. This finding suggests that deep learning could have a transformative impact on the way we model the constitutive properties of soft biological tissues.en
dc.language.isoende_DE
dc.publisherThe Royal Scocietyde_DE
dc.relation.ispartofInterface : journal of the Royal Societyde_DE
dc.rightsCC BY 4.0de_DE
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/de_DE
dc.subjectconstitutive modellingde_DE
dc.subjectdata-driven modellingde_DE
dc.subjectdeep learningde_DE
dc.subjecthybrid modellingde_DE
dc.subjectsoft biological tissuesde_DE
dc.subject.ddc570: Biowissenschaften, Biologiede_DE
dc.titlePredictive constitutive modelling of arteries by deep learningde_DE
dc.typeArticlede_DE
dc.identifier.doi10.15480/882.3819-
dc.type.diniarticle-
dcterms.DCMITypeText-
tuhh.identifier.urnurn:nbn:de:gbv:830-882.0147153-
tuhh.oai.showtruede_DE
tuhh.abstract.englishThe constitutive modelling of soft biological tissues has rapidly gained attention over the last 20 years. Current constitutive models can describe the mechanical properties of arterial tissue. Predicting these properties from microstructural information, however, remains an elusive goal. To address this challenge, we are introducing a novel hybrid modelling framework that combines advanced theoretical concepts with deep learning. It uses data from mechanical tests, histological analysis and images from second-harmonic generation. In this first proof of concept study, our hybrid modelling framework is trained with data from 27 tissue samples only. Even such a small amount of data is sufficient to be able to predict the stress-stretch curves of tissue samples with a median coefficient of determination of R2 = 0.97 from microstructural information, as long as one limits the scope to tissue samples whose mechanical properties remain in the range commonly encountered. This finding suggests that deep learning could have a transformative impact on the way we model the constitutive properties of soft biological tissues.de_DE
tuhh.publisher.doi10.1098/rsif.2021.0411-
tuhh.publication.instituteKontinuums- und Werkstoffmechanik M-15de_DE
tuhh.identifier.doi10.15480/882.3819-
tuhh.type.opus(wissenschaftlicher) Artikel-
dc.type.driverarticle-
dc.type.casraiJournal Article-
tuhh.container.issue182de_DE
tuhh.container.volume18de_DE
dc.relation.projectVaskuläre Wachstums- und Umbildungsprozesse in Aneurysmende_DE
dc.relation.projectI³-Lab - Modell-gestütztes maschinelles Lernen für die Weichgewebsmodellierung in der Medizinde_DE
dc.identifier.pmid34493095de_DE
dc.rights.nationallicensefalsede_DE
dc.identifier.scopus2-s2.0-85115982101de_DE
tuhh.container.articlenumber2021.0411de_DE
local.status.inpressfalsede_DE
local.type.versionacceptedVersionde_DE
item.openairecristypehttp://purl.org/coar/resource_type/c_6501-
item.creatorOrcidHolzapfel, Gerhard A.-
item.creatorOrcidLinka, Kevin-
item.creatorOrcidSherifova, Selda-
item.creatorOrcidCyron, Christian J.-
item.cerifentitytypePublications-
item.mappedtypeArticle-
item.openairetypeArticle-
item.fulltextWith Fulltext-
item.grantfulltextopen-
item.creatorGNDHolzapfel, Gerhard A.-
item.creatorGNDLinka, Kevin-
item.creatorGNDSherifova, Selda-
item.creatorGNDCyron, Christian J.-
item.languageiso639-1en-
crisitem.project.funderDeutsche Forschungsgemeinschaft (DFG)-
crisitem.project.funderTechnische Universität Hamburg-
crisitem.project.funderid501100001659-
crisitem.project.funderrorid018mejw64-
crisitem.project.funderrorid04bs1pb34-
crisitem.author.deptKontinuums- und Werkstoffmechanik M-15-
crisitem.author.deptKontinuums- und Werkstoffmechanik M-15-
crisitem.author.orcid0000-0001-8119-5775-
crisitem.author.orcid0000-0002-1239-4778-
crisitem.author.orcid0000-0001-8264-0885-
crisitem.author.parentorgStudiendekanat Maschinenbau-
crisitem.author.parentorgStudiendekanat Maschinenbau-
Appears in Collections:Publications with fulltext
Files in This Item:
File Description SizeFormat
rsif.2021.0411.pdfVerlagsversion1,16 MBAdobe PDFView/Open
Thumbnail
Show simple item record

Page view(s)

83
Last Week
3
Last month
15
checked on Dec 5, 2021

Download(s)

19
checked on Dec 5, 2021

Google ScholarTM

Check

Note about this record

Cite this record

Export

This item is licensed under a Creative Commons License Creative Commons