Segmentation of pathological liver tissue with Dilated Fully Convolutional Networks: A Preliminary Study
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , |
Tipo de documento: | Livro |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://hdl.handle.net/10216/119744 |
Resumo: | Early detection of liver cancer, whether from primary occurrence or from metastization is highly important to establish informed treatment decisions. Accurate delineation of the liver tissues of interest facilitates quantitative assessment of the regions of interest, treatment application, and prognosis. Segmentation of the liver in Computer Tomography (CT) images allows the extraction of the three-dimensional (3D) structure of the liver tissues in which the observation of their relative position to one another is particularly important in treatment scenarios of radiation therapy or interventional surgery planning. The adequate receptive field for the segmentation of such a big organ in CT images, from the remaining neighbouring organs was very successfully improved by the use of the state-of-the-art Convolutional Neural Networks (CNN) algorithms, however, certain issues still arise and are highly dependent of pre-or post-processing methods to refine the final segmentations. Here, the effects of Dilated Convolutional Networks is proposed, for the purpose of improving segmentation of liver tissues in CT. The introduction of a dilation module allowed the concatenation of feature maps with a richer contextual information. The hierarchical learning process given by different dilated convolutional layers is analysed quantitatively. Experiments on the MICCAI Lits challenge dataset are described achieving segmentations with a mean Dice coefficients of 95.57% and 59.36% for the liver and liver tumour, using a total number 30 CT test volumes. |
id |
RCAP_ccc4a163291843d5c7113af0f289b822 |
---|---|
oai_identifier_str |
oai:repositorio-aberto.up.pt:10216/119744 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Segmentation of pathological liver tissue with Dilated Fully Convolutional Networks: A Preliminary StudyCiências Tecnológicas, Ciências médicas e da saúdeTechnological sciences, Medical and Health sciencesEarly detection of liver cancer, whether from primary occurrence or from metastization is highly important to establish informed treatment decisions. Accurate delineation of the liver tissues of interest facilitates quantitative assessment of the regions of interest, treatment application, and prognosis. Segmentation of the liver in Computer Tomography (CT) images allows the extraction of the three-dimensional (3D) structure of the liver tissues in which the observation of their relative position to one another is particularly important in treatment scenarios of radiation therapy or interventional surgery planning. The adequate receptive field for the segmentation of such a big organ in CT images, from the remaining neighbouring organs was very successfully improved by the use of the state-of-the-art Convolutional Neural Networks (CNN) algorithms, however, certain issues still arise and are highly dependent of pre-or post-processing methods to refine the final segmentations. Here, the effects of Dilated Convolutional Networks is proposed, for the purpose of improving segmentation of liver tissues in CT. The introduction of a dilation module allowed the concatenation of feature maps with a richer contextual information. The hierarchical learning process given by different dilated convolutional layers is analysed quantitatively. Experiments on the MICCAI Lits challenge dataset are described achieving segmentations with a mean Dice coefficients of 95.57% and 59.36% for the liver and liver tumour, using a total number 30 CT test volumes.2019-022019-02-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/bookapplication/pdfhttps://hdl.handle.net/10216/119744eng10.1109/enbeng.2019.8692479Jessica C. DelmoralDurval C. CostaDiogo FariaJoão Manuel R. S. Tavaresinfo: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:RCAAP2023-11-29T13:17:03Zoai:repositorio-aberto.up.pt:10216/119744Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T23:37:30.277287Repositório 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 |
Segmentation of pathological liver tissue with Dilated Fully Convolutional Networks: A Preliminary Study |
title |
Segmentation of pathological liver tissue with Dilated Fully Convolutional Networks: A Preliminary Study |
spellingShingle |
Segmentation of pathological liver tissue with Dilated Fully Convolutional Networks: A Preliminary Study Jessica C. Delmoral Ciências Tecnológicas, Ciências médicas e da saúde Technological sciences, Medical and Health sciences |
title_short |
Segmentation of pathological liver tissue with Dilated Fully Convolutional Networks: A Preliminary Study |
title_full |
Segmentation of pathological liver tissue with Dilated Fully Convolutional Networks: A Preliminary Study |
title_fullStr |
Segmentation of pathological liver tissue with Dilated Fully Convolutional Networks: A Preliminary Study |
title_full_unstemmed |
Segmentation of pathological liver tissue with Dilated Fully Convolutional Networks: A Preliminary Study |
title_sort |
Segmentation of pathological liver tissue with Dilated Fully Convolutional Networks: A Preliminary Study |
author |
Jessica C. Delmoral |
author_facet |
Jessica C. Delmoral Durval C. Costa Diogo Faria João Manuel R. S. Tavares |
author_role |
author |
author2 |
Durval C. Costa Diogo Faria João Manuel R. S. Tavares |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Jessica C. Delmoral Durval C. Costa Diogo Faria João Manuel R. S. Tavares |
dc.subject.por.fl_str_mv |
Ciências Tecnológicas, Ciências médicas e da saúde Technological sciences, Medical and Health sciences |
topic |
Ciências Tecnológicas, Ciências médicas e da saúde Technological sciences, Medical and Health sciences |
description |
Early detection of liver cancer, whether from primary occurrence or from metastization is highly important to establish informed treatment decisions. Accurate delineation of the liver tissues of interest facilitates quantitative assessment of the regions of interest, treatment application, and prognosis. Segmentation of the liver in Computer Tomography (CT) images allows the extraction of the three-dimensional (3D) structure of the liver tissues in which the observation of their relative position to one another is particularly important in treatment scenarios of radiation therapy or interventional surgery planning. The adequate receptive field for the segmentation of such a big organ in CT images, from the remaining neighbouring organs was very successfully improved by the use of the state-of-the-art Convolutional Neural Networks (CNN) algorithms, however, certain issues still arise and are highly dependent of pre-or post-processing methods to refine the final segmentations. Here, the effects of Dilated Convolutional Networks is proposed, for the purpose of improving segmentation of liver tissues in CT. The introduction of a dilation module allowed the concatenation of feature maps with a richer contextual information. The hierarchical learning process given by different dilated convolutional layers is analysed quantitatively. Experiments on the MICCAI Lits challenge dataset are described achieving segmentations with a mean Dice coefficients of 95.57% and 59.36% for the liver and liver tumour, using a total number 30 CT test volumes. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-02 2019-02-01T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/book |
format |
book |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://hdl.handle.net/10216/119744 |
url |
https://hdl.handle.net/10216/119744 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1109/enbeng.2019.8692479 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
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_ |
1799135688022556672 |