Classification of calcified regions in atherosclerotic lesions of the carotid artery in computed tomography angiography images
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1007/s00521-019-04183-z http://hdl.handle.net/11449/197726 |
Resumo: | The identification of atherosclerotic plaque components, extraction and analysis of their morphology represent an important role towards the prediction of cardiovascular events. In this article, the classification of regions representing calcified components in computed tomography angiography (CTA) images of the carotid artery is tackled. The proposed classification model has two main steps: the classification per pixel and the classification per region. Features extracted from each pixel inside the carotid artery are submitted to four classifiers in order to determine the correct class, i.e. calcification or non-calcification. Then, geometrical and intensity features extracted from each candidate region resulting from the pixel classification step are submitted to the classification per region in order to determine the correct regions of calcified components. In order to evaluate the classification accuracy, the results of the proposed classification model were compared against ground truths of calcifications obtained from micro-computed tomography images of excised atherosclerotic plaques that were registered with in vivo CTA images. The average values of the Spearman correlation coefficient obtained by the linear discriminant classifier were higher than 0.80 for the relative volume of the calcified components. Moreover, the average values of the absolute error between the relative volumes of the classified calcium regions and the ones calculated from the corresponding ground truths were lower than 3%. The new classification model seems to be adequate as an auxiliary diagnostic tool for identifying calcifications and allowing their morphology assessment. |
id |
UNSP_485e1232575943f62cae446908756694 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/197726 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Classification of calcified regions in atherosclerotic lesions of the carotid artery in computed tomography angiography imagesMedical imagingPattern recognitionClassificationAtherosclerosisThe identification of atherosclerotic plaque components, extraction and analysis of their morphology represent an important role towards the prediction of cardiovascular events. In this article, the classification of regions representing calcified components in computed tomography angiography (CTA) images of the carotid artery is tackled. The proposed classification model has two main steps: the classification per pixel and the classification per region. Features extracted from each pixel inside the carotid artery are submitted to four classifiers in order to determine the correct class, i.e. calcification or non-calcification. Then, geometrical and intensity features extracted from each candidate region resulting from the pixel classification step are submitted to the classification per region in order to determine the correct regions of calcified components. In order to evaluate the classification accuracy, the results of the proposed classification model were compared against ground truths of calcifications obtained from micro-computed tomography images of excised atherosclerotic plaques that were registered with in vivo CTA images. The average values of the Spearman correlation coefficient obtained by the linear discriminant classifier were higher than 0.80 for the relative volume of the calcified components. Moreover, the average values of the absolute error between the relative volumes of the classified calcium regions and the ones calculated from the corresponding ground truths were lower than 3%. The new classification model seems to be adequate as an auxiliary diagnostic tool for identifying calcifications and allowing their morphology assessment.Minist Educ Brazil, CAPES Fdn, BR-70040020 Brasilia, DF, BrazilUniv Porto, Fac Engn, Inst Ciencia & Inovacao Engn Mecan & Engn Ind, Rua Dr Roberto Frias S-N, P-4200465 Porto, PortugalUniv Estadual Paulista, Rua Cristovao Colombo 2265, BR-15054000 Sao Jose Do Rio Preto, BrazilUniv Estadual Paulista, Rua Cristovao Colombo 2265, BR-15054000 Sao Jose Do Rio Preto, BrazilSpringerMinist Educ BrazilUniv PortoUniversidade Estadual Paulista (Unesp)Jodas, Danilo SamuelPereira, Aledir Silveira [UNESP]Tavares, Joao Manuel R. S.2020-12-11T15:15:15Z2020-12-11T15:15:15Z2020-04-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article2553-2573http://dx.doi.org/10.1007/s00521-019-04183-zNeural Computing & Applications. London: Springer London Ltd, v. 32, n. 7, p. 2553-2573, 2020.0941-0643http://hdl.handle.net/11449/19772610.1007/s00521-019-04183-zWOS:000522553100050Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengNeural Computing & Applicationsinfo:eu-repo/semantics/openAccess2021-10-22T21:09:46Zoai:repositorio.unesp.br:11449/197726Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T18:01:53.118257Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Classification of calcified regions in atherosclerotic lesions of the carotid artery in computed tomography angiography images |
title |
Classification of calcified regions in atherosclerotic lesions of the carotid artery in computed tomography angiography images |
spellingShingle |
Classification of calcified regions in atherosclerotic lesions of the carotid artery in computed tomography angiography images Jodas, Danilo Samuel Medical imaging Pattern recognition Classification Atherosclerosis |
title_short |
Classification of calcified regions in atherosclerotic lesions of the carotid artery in computed tomography angiography images |
title_full |
Classification of calcified regions in atherosclerotic lesions of the carotid artery in computed tomography angiography images |
title_fullStr |
Classification of calcified regions in atherosclerotic lesions of the carotid artery in computed tomography angiography images |
title_full_unstemmed |
Classification of calcified regions in atherosclerotic lesions of the carotid artery in computed tomography angiography images |
title_sort |
Classification of calcified regions in atherosclerotic lesions of the carotid artery in computed tomography angiography images |
author |
Jodas, Danilo Samuel |
author_facet |
Jodas, Danilo Samuel Pereira, Aledir Silveira [UNESP] Tavares, Joao Manuel R. S. |
author_role |
author |
author2 |
Pereira, Aledir Silveira [UNESP] Tavares, Joao Manuel R. S. |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Minist Educ Brazil Univ Porto Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Jodas, Danilo Samuel Pereira, Aledir Silveira [UNESP] Tavares, Joao Manuel R. S. |
dc.subject.por.fl_str_mv |
Medical imaging Pattern recognition Classification Atherosclerosis |
topic |
Medical imaging Pattern recognition Classification Atherosclerosis |
description |
The identification of atherosclerotic plaque components, extraction and analysis of their morphology represent an important role towards the prediction of cardiovascular events. In this article, the classification of regions representing calcified components in computed tomography angiography (CTA) images of the carotid artery is tackled. The proposed classification model has two main steps: the classification per pixel and the classification per region. Features extracted from each pixel inside the carotid artery are submitted to four classifiers in order to determine the correct class, i.e. calcification or non-calcification. Then, geometrical and intensity features extracted from each candidate region resulting from the pixel classification step are submitted to the classification per region in order to determine the correct regions of calcified components. In order to evaluate the classification accuracy, the results of the proposed classification model were compared against ground truths of calcifications obtained from micro-computed tomography images of excised atherosclerotic plaques that were registered with in vivo CTA images. The average values of the Spearman correlation coefficient obtained by the linear discriminant classifier were higher than 0.80 for the relative volume of the calcified components. Moreover, the average values of the absolute error between the relative volumes of the classified calcium regions and the ones calculated from the corresponding ground truths were lower than 3%. The new classification model seems to be adequate as an auxiliary diagnostic tool for identifying calcifications and allowing their morphology assessment. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-12-11T15:15:15Z 2020-12-11T15:15:15Z 2020-04-01 |
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://dx.doi.org/10.1007/s00521-019-04183-z Neural Computing & Applications. London: Springer London Ltd, v. 32, n. 7, p. 2553-2573, 2020. 0941-0643 http://hdl.handle.net/11449/197726 10.1007/s00521-019-04183-z WOS:000522553100050 |
url |
http://dx.doi.org/10.1007/s00521-019-04183-z http://hdl.handle.net/11449/197726 |
identifier_str_mv |
Neural Computing & Applications. London: Springer London Ltd, v. 32, n. 7, p. 2553-2573, 2020. 0941-0643 10.1007/s00521-019-04183-z WOS:000522553100050 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Neural Computing & Applications |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
2553-2573 |
dc.publisher.none.fl_str_mv |
Springer |
publisher.none.fl_str_mv |
Springer |
dc.source.none.fl_str_mv |
Web of Science reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128886976806912 |