SPINNE: An app for human vertebral height estimation based on artificial neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10316/86819 https://doi.org/10.1016/j.forsciint.2019.02.056 |
Resumo: | The absence or poor preservation of vertebrae often prevent the application of the anatomical method for stature estimation. The main objective of this paper was to develop a web app based on artificial neural network (ANN) models to estimate the vertebral height of absent or poorly preserved vertebrae from other vertebrae and thus enable the application of anatomical methods. Artificial neural models were developed based on the vertebral height of vertebrae C2 to S1 of a sample composed of 56 adult male and 69 adult female individuals. The skeletons belong to the Identified Skeletal Collection of the University of Coimbra and the ages at death of these individuals ranged from 22 to 58 years old. Statistical analysis and algorithmic development were performed with the R language, R Core Team (2018). Intra- and inter-observer errors regarding the vertebral height were small for all vertebrae (<0.45 mm). Significant models to estimate vertebral height were obtained for both sexes and for the sex-pooled group, although none with an R2 higher than 0.48 and 0.34 for the C2 and the S1, respectively. The root mean square error (RMSE) regarding the predicted vertebral height and the observed vertebral height was almost always smaller than 1.0 mm while most R2 values were higher than 0.6 although models with worse performances were obtained for some vertebrae located at the ends of the vertebral column (C3, L4, and L5). The ANN models have clear potential to predict vertebral height. This mathematical approach may be used to enable the application of the anatomical method for stature estimation when some vertebrae are absent or poorly preserved. The application of the ANN models can be carried out by using the new web based app SPINNE. |
id |
RCAP_a80e7da5a147d7dd9782390a74913f66 |
---|---|
oai_identifier_str |
oai:estudogeral.uc.pt:10316/86819 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
SPINNE: An app for human vertebral height estimation based on artificial neural networksThe absence or poor preservation of vertebrae often prevent the application of the anatomical method for stature estimation. The main objective of this paper was to develop a web app based on artificial neural network (ANN) models to estimate the vertebral height of absent or poorly preserved vertebrae from other vertebrae and thus enable the application of anatomical methods. Artificial neural models were developed based on the vertebral height of vertebrae C2 to S1 of a sample composed of 56 adult male and 69 adult female individuals. The skeletons belong to the Identified Skeletal Collection of the University of Coimbra and the ages at death of these individuals ranged from 22 to 58 years old. Statistical analysis and algorithmic development were performed with the R language, R Core Team (2018). Intra- and inter-observer errors regarding the vertebral height were small for all vertebrae (<0.45 mm). Significant models to estimate vertebral height were obtained for both sexes and for the sex-pooled group, although none with an R2 higher than 0.48 and 0.34 for the C2 and the S1, respectively. The root mean square error (RMSE) regarding the predicted vertebral height and the observed vertebral height was almost always smaller than 1.0 mm while most R2 values were higher than 0.6 although models with worse performances were obtained for some vertebrae located at the ends of the vertebral column (C3, L4, and L5). The ANN models have clear potential to predict vertebral height. This mathematical approach may be used to enable the application of the anatomical method for stature estimation when some vertebrae are absent or poorly preserved. The application of the ANN models can be carried out by using the new web based app SPINNE.2019-03-06info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10316/86819http://hdl.handle.net/10316/86819https://doi.org/10.1016/j.forsciint.2019.02.056por1872-628330897448Vilas-Boas, D.Wasterlain, S. N.Coelho, J. d'OliveiraNavega, D.Gonçalves, D.info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2021-09-02T11:21:10Zoai:estudogeral.uc.pt:10316/86819Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T21:07:55.165175Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
SPINNE: An app for human vertebral height estimation based on artificial neural networks |
title |
SPINNE: An app for human vertebral height estimation based on artificial neural networks |
spellingShingle |
SPINNE: An app for human vertebral height estimation based on artificial neural networks Vilas-Boas, D. |
title_short |
SPINNE: An app for human vertebral height estimation based on artificial neural networks |
title_full |
SPINNE: An app for human vertebral height estimation based on artificial neural networks |
title_fullStr |
SPINNE: An app for human vertebral height estimation based on artificial neural networks |
title_full_unstemmed |
SPINNE: An app for human vertebral height estimation based on artificial neural networks |
title_sort |
SPINNE: An app for human vertebral height estimation based on artificial neural networks |
author |
Vilas-Boas, D. |
author_facet |
Vilas-Boas, D. Wasterlain, S. N. Coelho, J. d'Oliveira Navega, D. Gonçalves, D. |
author_role |
author |
author2 |
Wasterlain, S. N. Coelho, J. d'Oliveira Navega, D. Gonçalves, D. |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Vilas-Boas, D. Wasterlain, S. N. Coelho, J. d'Oliveira Navega, D. Gonçalves, D. |
description |
The absence or poor preservation of vertebrae often prevent the application of the anatomical method for stature estimation. The main objective of this paper was to develop a web app based on artificial neural network (ANN) models to estimate the vertebral height of absent or poorly preserved vertebrae from other vertebrae and thus enable the application of anatomical methods. Artificial neural models were developed based on the vertebral height of vertebrae C2 to S1 of a sample composed of 56 adult male and 69 adult female individuals. The skeletons belong to the Identified Skeletal Collection of the University of Coimbra and the ages at death of these individuals ranged from 22 to 58 years old. Statistical analysis and algorithmic development were performed with the R language, R Core Team (2018). Intra- and inter-observer errors regarding the vertebral height were small for all vertebrae (<0.45 mm). Significant models to estimate vertebral height were obtained for both sexes and for the sex-pooled group, although none with an R2 higher than 0.48 and 0.34 for the C2 and the S1, respectively. The root mean square error (RMSE) regarding the predicted vertebral height and the observed vertebral height was almost always smaller than 1.0 mm while most R2 values were higher than 0.6 although models with worse performances were obtained for some vertebrae located at the ends of the vertebral column (C3, L4, and L5). The ANN models have clear potential to predict vertebral height. This mathematical approach may be used to enable the application of the anatomical method for stature estimation when some vertebrae are absent or poorly preserved. The application of the ANN models can be carried out by using the new web based app SPINNE. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-03-06 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10316/86819 http://hdl.handle.net/10316/86819 https://doi.org/10.1016/j.forsciint.2019.02.056 |
url |
http://hdl.handle.net/10316/86819 https://doi.org/10.1016/j.forsciint.2019.02.056 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
1872-6283 30897448 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799133970450874368 |