Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation times

Detalhes bibliográficos
Autor(a) principal: Dionisio,Fernando Carrasco Ferreira
Data de Publicação: 2021
Outros Autores: Oliveira,Larissa Santos, Hernandes,Mateus de Andrade, Engel,Edgard Eduard, Azevedo-Marques,Paulo Mazzoncini de, Nogueira-Barbosa,Marcello Henrique
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Radiologia Brasileira (Online)
Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-39842021000300155
Resumo: Abstract Objective: To evaluate the degree of similarity between manual and semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging (MRI). Materials and Methods: This was a retrospective study of 15 MRI examinations of patients with histopathologically confirmed soft-tissue sarcomas acquired before therapeutic intervention. Manual and semiautomatic segmentations were performed by three radiologists, working independently, using the software 3D Slicer. The Dice similarity coefficient (DSC) and the Hausdorff distance were calculated in order to evaluate the similarity between manual and semiautomatic segmentation. To compare the two modalities in terms of the tumor volumes obtained, we also calculated descriptive statistics and intraclass correlation coefficients (ICCs). Results: In the comparison between manual and semiautomatic segmentation, the DSC values ranged from 0.871 to 0.973. The comparison of the volumes segmented by the two modalities resulted in ICCs between 0.9927 and 0.9990. The DSC values ranged from 0.849 to 0.979 for intraobserver variability and from 0.741 to 0.972 for interobserver variability. There was no significant difference between the semiautomatic and manual modalities in terms of the segmentation times (p > 0.05). Conclusion: There appears to be a high degree of similarity between manual and semiautomatic segmentation, with no significant difference between the two modalities in terms of the time required for segmentation.
id CBR-1_e8e8e84217ffde274bc8d45998085c58
oai_identifier_str oai:scielo:S0100-39842021000300155
network_acronym_str CBR-1
network_name_str Radiologia Brasileira (Online)
repository_id_str
spelling Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation timesImage processing, computer-assistedSarcoma/diagnostic imagingSoft tissue neoplasms/diagnostic imagingMagnetic resonance imagingReproducibility of resultsAbstract Objective: To evaluate the degree of similarity between manual and semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging (MRI). Materials and Methods: This was a retrospective study of 15 MRI examinations of patients with histopathologically confirmed soft-tissue sarcomas acquired before therapeutic intervention. Manual and semiautomatic segmentations were performed by three radiologists, working independently, using the software 3D Slicer. The Dice similarity coefficient (DSC) and the Hausdorff distance were calculated in order to evaluate the similarity between manual and semiautomatic segmentation. To compare the two modalities in terms of the tumor volumes obtained, we also calculated descriptive statistics and intraclass correlation coefficients (ICCs). Results: In the comparison between manual and semiautomatic segmentation, the DSC values ranged from 0.871 to 0.973. The comparison of the volumes segmented by the two modalities resulted in ICCs between 0.9927 and 0.9990. The DSC values ranged from 0.849 to 0.979 for intraobserver variability and from 0.741 to 0.972 for interobserver variability. There was no significant difference between the semiautomatic and manual modalities in terms of the segmentation times (p > 0.05). Conclusion: There appears to be a high degree of similarity between manual and semiautomatic segmentation, with no significant difference between the two modalities in terms of the time required for segmentation.Publicação do Colégio Brasileiro de Radiologia e Diagnóstico por Imagem2021-06-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-39842021000300155Radiologia Brasileira v.54 n.3 2021reponame:Radiologia Brasileira (Online)instname:Colégio Brasileiro de Radiologia e Diagnóstico por Imagem (CBR)instacron:CBR10.1590/0100-3984.2020.0028info:eu-repo/semantics/openAccessDionisio,Fernando Carrasco FerreiraOliveira,Larissa SantosHernandes,Mateus de AndradeEngel,Edgard EduardAzevedo-Marques,Paulo Mazzoncini deNogueira-Barbosa,Marcello Henriqueeng2021-05-20T00:00:00Zoai:scielo:S0100-39842021000300155Revistahttps://www.scielo.br/j/rb/https://old.scielo.br/oai/scielo-oai.phpradiologiabrasileira@cbr.org.br1678-70990100-3984opendoar:2021-05-20T00:00Radiologia Brasileira (Online) - Colégio Brasileiro de Radiologia e Diagnóstico por Imagem (CBR)false
dc.title.none.fl_str_mv Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation times
title Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation times
spellingShingle Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation times
Dionisio,Fernando Carrasco Ferreira
Image processing, computer-assisted
Sarcoma/diagnostic imaging
Soft tissue neoplasms/diagnostic imaging
Magnetic resonance imaging
Reproducibility of results
title_short Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation times
title_full Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation times
title_fullStr Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation times
title_full_unstemmed Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation times
title_sort Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation times
author Dionisio,Fernando Carrasco Ferreira
author_facet Dionisio,Fernando Carrasco Ferreira
Oliveira,Larissa Santos
Hernandes,Mateus de Andrade
Engel,Edgard Eduard
Azevedo-Marques,Paulo Mazzoncini de
Nogueira-Barbosa,Marcello Henrique
author_role author
author2 Oliveira,Larissa Santos
Hernandes,Mateus de Andrade
Engel,Edgard Eduard
Azevedo-Marques,Paulo Mazzoncini de
Nogueira-Barbosa,Marcello Henrique
author2_role author
author
author
author
author
dc.contributor.author.fl_str_mv Dionisio,Fernando Carrasco Ferreira
Oliveira,Larissa Santos
Hernandes,Mateus de Andrade
Engel,Edgard Eduard
Azevedo-Marques,Paulo Mazzoncini de
Nogueira-Barbosa,Marcello Henrique
dc.subject.por.fl_str_mv Image processing, computer-assisted
Sarcoma/diagnostic imaging
Soft tissue neoplasms/diagnostic imaging
Magnetic resonance imaging
Reproducibility of results
topic Image processing, computer-assisted
Sarcoma/diagnostic imaging
Soft tissue neoplasms/diagnostic imaging
Magnetic resonance imaging
Reproducibility of results
description Abstract Objective: To evaluate the degree of similarity between manual and semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging (MRI). Materials and Methods: This was a retrospective study of 15 MRI examinations of patients with histopathologically confirmed soft-tissue sarcomas acquired before therapeutic intervention. Manual and semiautomatic segmentations were performed by three radiologists, working independently, using the software 3D Slicer. The Dice similarity coefficient (DSC) and the Hausdorff distance were calculated in order to evaluate the similarity between manual and semiautomatic segmentation. To compare the two modalities in terms of the tumor volumes obtained, we also calculated descriptive statistics and intraclass correlation coefficients (ICCs). Results: In the comparison between manual and semiautomatic segmentation, the DSC values ranged from 0.871 to 0.973. The comparison of the volumes segmented by the two modalities resulted in ICCs between 0.9927 and 0.9990. The DSC values ranged from 0.849 to 0.979 for intraobserver variability and from 0.741 to 0.972 for interobserver variability. There was no significant difference between the semiautomatic and manual modalities in terms of the segmentation times (p > 0.05). Conclusion: There appears to be a high degree of similarity between manual and semiautomatic segmentation, with no significant difference between the two modalities in terms of the time required for segmentation.
publishDate 2021
dc.date.none.fl_str_mv 2021-06-01
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-39842021000300155
url http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-39842021000300155
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.1590/0100-3984.2020.0028
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv text/html
dc.publisher.none.fl_str_mv Publicação do Colégio Brasileiro de Radiologia e Diagnóstico por Imagem
publisher.none.fl_str_mv Publicação do Colégio Brasileiro de Radiologia e Diagnóstico por Imagem
dc.source.none.fl_str_mv Radiologia Brasileira v.54 n.3 2021
reponame:Radiologia Brasileira (Online)
instname:Colégio Brasileiro de Radiologia e Diagnóstico por Imagem (CBR)
instacron:CBR
instname_str Colégio Brasileiro de Radiologia e Diagnóstico por Imagem (CBR)
instacron_str CBR
institution CBR
reponame_str Radiologia Brasileira (Online)
collection Radiologia Brasileira (Online)
repository.name.fl_str_mv Radiologia Brasileira (Online) - Colégio Brasileiro de Radiologia e Diagnóstico por Imagem (CBR)
repository.mail.fl_str_mv radiologiabrasileira@cbr.org.br
_version_ 1754208941031555072