Please use this identifier to cite or link to this item: https://doi.org/10.15480/882.3302
DC FieldValueLanguage
dc.contributor.authorAuf der Mauer, Markus-
dc.contributor.authorJopp-van Well, Eilin-
dc.contributor.authorHerrmann, Jochen-
dc.contributor.authorGroth, Michael-
dc.contributor.authorMorlock, Michael-
dc.contributor.authorMaas, Rainer-
dc.contributor.authorSäring, Dennis-
dc.date.accessioned2021-01-27T08:23:12Z-
dc.date.available2021-01-27T08:23:12Z-
dc.date.issued2020-12-17-
dc.identifier.citationInternational Journal of Legal Medicine 135 (2): 649-663 (2021)de_DE
dc.identifier.issn0937-9827de_DE
dc.identifier.urihttp://hdl.handle.net/11420/8599-
dc.description.abstractAge estimation is a crucial element of forensic medicine to assess the chronological age of living individuals without or lacking valid legal documentation. Methods used in practice are labor-intensive, subjective, and frequently comprise radiation exposure. Recently, also non-invasive methods using magnetic resonance imaging (MRI) have evaluated and confirmed a correlation between growth plate ossification in long bones and the chronological age of young subjects. However, automated and user-independent approaches are required to perform reliable assessments on large datasets. The aim of this study was to develop a fully automated and computer-based method for age estimation based on 3D knee MRIs using machine learning. The proposed solution is based on three parts: image-preprocessing, bone segmentation, and age estimation. A total of 185 coronal and 404 sagittal MR volumes from Caucasian male subjects in the age range of 13 and 21 years were available. The best result of the fivefold cross-validation was a mean absolute error of 0.67 ± 0.49 years in age regression and an accuracy of 90.9%, a sensitivity of 88.6%, and a specificity of 94.2% in classification (18-year age limit) using a combination of convolutional neural networks and tree-based machine learning algorithms. The potential of deep learning for age estimation is reflected in the results and can be further improved if it is trained on even larger and more diverse datasets.en
dc.language.isoende_DE
dc.publisherSpringerde_DE
dc.relation.ispartofInternational journal of legal medicinede_DE
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/de_DE
dc.subject.ddc570: Biowissenschaften, Biologiede_DE
dc.subject.ddc600: Technikde_DE
dc.titleAutomated age estimation of young individuals based on 3D knee MRI using deep learningde_DE
dc.typeArticlede_DE
dc.identifier.doi10.15480/882.3302-
dc.type.diniarticle-
dcterms.DCMITypeText-
tuhh.identifier.urnurn:nbn:de:gbv:830-882.0122659-
tuhh.oai.showtruede_DE
tuhh.abstract.englishAge estimation is a crucial element of forensic medicine to assess the chronological age of living individuals without or lacking valid legal documentation. Methods used in practice are labor-intensive, subjective, and frequently comprise radiation exposure. Recently, also non-invasive methods using magnetic resonance imaging (MRI) have evaluated and confirmed a correlation between growth plate ossification in long bones and the chronological age of young subjects. However, automated and user-independent approaches are required to perform reliable assessments on large datasets. The aim of this study was to develop a fully automated and computer-based method for age estimation based on 3D knee MRIs using machine learning. The proposed solution is based on three parts: image-preprocessing, bone segmentation, and age estimation. A total of 185 coronal and 404 sagittal MR volumes from Caucasian male subjects in the age range of 13 and 21 years were available. The best result of the fivefold cross-validation was a mean absolute error of 0.67 ± 0.49 years in age regression and an accuracy of 90.9%, a sensitivity of 88.6%, and a specificity of 94.2% in classification (18-year age limit) using a combination of convolutional neural networks and tree-based machine learning algorithms. The potential of deep learning for age estimation is reflected in the results and can be further improved if it is trained on even larger and more diverse datasets.de_DE
tuhh.publisher.doi10.1007/s00414-020-02465-z-
tuhh.publication.instituteBiomechanik M-3de_DE
tuhh.identifier.doi10.15480/882.3302-
tuhh.type.opus(wissenschaftlicher) Artikel-
dc.type.driverarticle-
dc.type.casraiJournal Article-
tuhh.container.issue2de_DE
tuhh.container.volume135de_DE
tuhh.container.startpage649de_DE
tuhh.container.endpage663de_DE
dc.relation.projectProjekt DEALde_DE
dc.rights.nationallicensefalsede_DE
local.status.inpressfalsede_DE
local.type.versionpublishedVersionde_DE
local.funding.infoThis project is funded by the German Research Foundation (DFG), Project (SA 2530/6-1) and (JO 1198/2-1).de_DE
item.fulltextWith Fulltext-
item.mappedtypeArticle-
item.cerifentitytypePublications-
item.openairetypeArticle-
item.creatorGNDAuf der Mauer, Markus-
item.creatorGNDJopp-van Well, Eilin-
item.creatorGNDHerrmann, Jochen-
item.creatorGNDGroth, Michael-
item.creatorGNDMorlock, Michael-
item.creatorGNDMaas, Rainer-
item.creatorGNDSäring, Dennis-
item.languageiso639-1en-
item.openairecristypehttp://purl.org/coar/resource_type/c_6501-
item.grantfulltextopen-
item.creatorOrcidAuf der Mauer, Markus-
item.creatorOrcidJopp-van Well, Eilin-
item.creatorOrcidHerrmann, Jochen-
item.creatorOrcidGroth, Michael-
item.creatorOrcidMorlock, Michael-
item.creatorOrcidMaas, Rainer-
item.creatorOrcidSäring, Dennis-
crisitem.author.deptBiomechanik M-3-
crisitem.author.orcid0000-0002-5589-3681-
crisitem.author.orcid0000-0002-5330-2454-
crisitem.author.orcid0000-0002-4487-8814-
crisitem.author.parentorgStudiendekanat Maschinenbau-
Appears in Collections:Publications with fulltext
Files in This Item:
File Description SizeFormat
Mauer2021_Article_AutomatedAgeEstimationOfYoungI-1.pdfVerlags-PDF5,58 MBAdobe PDFView/Open
Thumbnail
Show simple item record

Page view(s)

59
Last Week
2
Last month
7
checked on Apr 12, 2021

Download(s)

8
checked on Apr 12, 2021

Google ScholarTM

Check

Note about this record

Cite this record

Export

This item is licensed under a Creative Commons License Creative Commons