Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiforme

Autores
Mulet de Los Reyes, Alexander; Hyde Lord, Victoria; Buemi, María Elena; Gandia, Daniel Enrique; Gómez Déniz, Luis; Noriega Alemán, Maikel; Suárez, Cecilia Ana
Año de publicación
2024
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Glioblastoma multiforme (GBM) is the most prevalent and aggressive primary brain tumor that has the worst prognosis in adults. Currently, the automatic segmentation of this kind of tumor is being intensively studied. Here, the automatic three-dimensional segmentation of the GBM is achieved with its related subzones (active tumor, inner necrosis, and peripheral edema). Preliminary segmentations were first defined based on the four basic magnetic resonance imaging modalities and classic image processing methods (multithreshold Otsu, Chan-Vese active contours, and morphological erosion). After an automatic gap-filling post processing step, these preliminary segmentations were combined and corrected by a supervised artificial neural network of multilayer perceptron type with a hidden layer of 80 neurons, fed by 30 selected radiomic features of gray intensity and texture. Network classification has an overall accuracy of 83.9%, while the complete combined algorithm achieves average Dice similarity coefficients of 89.3%, 80.7%, 79.7% and 66.4% for the entire region of interest, active tumor, edema, and necrosis segmentations, respectively. These values are in the range of the best reported in the present bibliography, but even with better Hausdorff distances and lower computational costs. Results presented here evidence that it is possible to achieve the automatic segmentationof this kind of tumor by traditional radiomics. This has relevant clinical potential at the time of diagnosis, precision radiotherapy planning, or post-treatment response evaluation.
Fil: Mulet de Los Reyes, Alexander. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física del Plasma. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física del Plasma; Argentina
Fil: Hyde Lord, Victoria. Instituto Tecnológico de Buenos Aires; Argentina
Fil: Buemi, María Elena. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina
Fil: Gandia, Daniel Enrique. No especifíca;
Fil: Gómez Déniz, Luis. Universidad de Las Palmas de Gran Canaria; España
Fil: Noriega Alemán, Maikel. Universidad de Oriente. Facultad de Ingenieria En Telecomunicaciones, Informatica y Biomedica.; Cuba
Fil: Suárez, Cecilia Ana. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física del Plasma. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física del Plasma; Argentina
Materia
GLIOBLASTOMA MULTIFORME
AUTOMATIC SEGMENTION
IMAGE PROCESSING
RADIOMICS
ARTIFICIAL NEURAL NETWORKS
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/265372
Acceder
id CONICETDig_b7a834e10e8d1899325bb664787722de
oai_identifier_str oai:ri.conicet.gov.ar:11336/265372
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiformeMulet de Los Reyes, AlexanderHyde Lord, VictoriaBuemi, María ElenaGandia, Daniel EnriqueGómez Déniz, LuisNoriega Alemán, MaikelSuárez, Cecilia AnaGLIOBLASTOMA MULTIFORMEAUTOMATIC SEGMENTIONIMAGE PROCESSINGRADIOMICSARTIFICIAL NEURAL NETWORKShttps://purl.org/becyt/ford/3.5https://purl.org/becyt/ford/3https://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1Glioblastoma multiforme (GBM) is the most prevalent and aggressive primary brain tumor that has the worst prognosis in adults. Currently, the automatic segmentation of this kind of tumor is being intensively studied. Here, the automatic three-dimensional segmentation of the GBM is achieved with its related subzones (active tumor, inner necrosis, and peripheral edema). Preliminary segmentations were first defined based on the four basic magnetic resonance imaging modalities and classic image processing methods (multithreshold Otsu, Chan-Vese active contours, and morphological erosion). After an automatic gap-filling post processing step, these preliminary segmentations were combined and corrected by a supervised artificial neural network of multilayer perceptron type with a hidden layer of 80 neurons, fed by 30 selected radiomic features of gray intensity and texture. Network classification has an overall accuracy of 83.9%, while the complete combined algorithm achieves average Dice similarity coefficients of 89.3%, 80.7%, 79.7% and 66.4% for the entire region of interest, active tumor, edema, and necrosis segmentations, respectively. These values are in the range of the best reported in the present bibliography, but even with better Hausdorff distances and lower computational costs. Results presented here evidence that it is possible to achieve the automatic segmentationof this kind of tumor by traditional radiomics. This has relevant clinical potential at the time of diagnosis, precision radiotherapy planning, or post-treatment response evaluation.Fil: Mulet de Los Reyes, Alexander. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física del Plasma. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física del Plasma; ArgentinaFil: Hyde Lord, Victoria. Instituto Tecnológico de Buenos Aires; ArgentinaFil: Buemi, María Elena. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; ArgentinaFil: Gandia, Daniel Enrique. No especifíca;Fil: Gómez Déniz, Luis. Universidad de Las Palmas de Gran Canaria; EspañaFil: Noriega Alemán, Maikel. Universidad de Oriente. Facultad de Ingenieria En Telecomunicaciones, Informatica y Biomedica.; CubaFil: Suárez, Cecilia Ana. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física del Plasma. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física del Plasma; ArgentinaWiley Blackwell Publishing, Inc2024-03info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/265372Mulet de Los Reyes, Alexander; Hyde Lord, Victoria; Buemi, María Elena; Gandia, Daniel Enrique; Gómez Déniz, Luis; et al.; Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiforme; Wiley Blackwell Publishing, Inc; Expert Systems; 41; 9; 3-2024; 1-140266-4720CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.1111/exsy.13598info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T09:55:03Zoai:ri.conicet.gov.ar:11336/265372instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 09:55:04.177CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiforme
title Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiforme
spellingShingle Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiforme
Mulet de Los Reyes, Alexander
GLIOBLASTOMA MULTIFORME
AUTOMATIC SEGMENTION
IMAGE PROCESSING
RADIOMICS
ARTIFICIAL NEURAL NETWORKS
title_short Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiforme
title_full Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiforme
title_fullStr Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiforme
title_full_unstemmed Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiforme
title_sort Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiforme
dc.creator.none.fl_str_mv Mulet de Los Reyes, Alexander
Hyde Lord, Victoria
Buemi, María Elena
Gandia, Daniel Enrique
Gómez Déniz, Luis
Noriega Alemán, Maikel
Suárez, Cecilia Ana
author Mulet de Los Reyes, Alexander
author_facet Mulet de Los Reyes, Alexander
Hyde Lord, Victoria
Buemi, María Elena
Gandia, Daniel Enrique
Gómez Déniz, Luis
Noriega Alemán, Maikel
Suárez, Cecilia Ana
author_role author
author2 Hyde Lord, Victoria
Buemi, María Elena
Gandia, Daniel Enrique
Gómez Déniz, Luis
Noriega Alemán, Maikel
Suárez, Cecilia Ana
author2_role author
author
author
author
author
author
dc.subject.none.fl_str_mv GLIOBLASTOMA MULTIFORME
AUTOMATIC SEGMENTION
IMAGE PROCESSING
RADIOMICS
ARTIFICIAL NEURAL NETWORKS
topic GLIOBLASTOMA MULTIFORME
AUTOMATIC SEGMENTION
IMAGE PROCESSING
RADIOMICS
ARTIFICIAL NEURAL NETWORKS
purl_subject.fl_str_mv https://purl.org/becyt/ford/3.5
https://purl.org/becyt/ford/3
https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Glioblastoma multiforme (GBM) is the most prevalent and aggressive primary brain tumor that has the worst prognosis in adults. Currently, the automatic segmentation of this kind of tumor is being intensively studied. Here, the automatic three-dimensional segmentation of the GBM is achieved with its related subzones (active tumor, inner necrosis, and peripheral edema). Preliminary segmentations were first defined based on the four basic magnetic resonance imaging modalities and classic image processing methods (multithreshold Otsu, Chan-Vese active contours, and morphological erosion). After an automatic gap-filling post processing step, these preliminary segmentations were combined and corrected by a supervised artificial neural network of multilayer perceptron type with a hidden layer of 80 neurons, fed by 30 selected radiomic features of gray intensity and texture. Network classification has an overall accuracy of 83.9%, while the complete combined algorithm achieves average Dice similarity coefficients of 89.3%, 80.7%, 79.7% and 66.4% for the entire region of interest, active tumor, edema, and necrosis segmentations, respectively. These values are in the range of the best reported in the present bibliography, but even with better Hausdorff distances and lower computational costs. Results presented here evidence that it is possible to achieve the automatic segmentationof this kind of tumor by traditional radiomics. This has relevant clinical potential at the time of diagnosis, precision radiotherapy planning, or post-treatment response evaluation.
Fil: Mulet de Los Reyes, Alexander. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física del Plasma. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física del Plasma; Argentina
Fil: Hyde Lord, Victoria. Instituto Tecnológico de Buenos Aires; Argentina
Fil: Buemi, María Elena. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina
Fil: Gandia, Daniel Enrique. No especifíca;
Fil: Gómez Déniz, Luis. Universidad de Las Palmas de Gran Canaria; España
Fil: Noriega Alemán, Maikel. Universidad de Oriente. Facultad de Ingenieria En Telecomunicaciones, Informatica y Biomedica.; Cuba
Fil: Suárez, Cecilia Ana. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física del Plasma. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física del Plasma; Argentina
description Glioblastoma multiforme (GBM) is the most prevalent and aggressive primary brain tumor that has the worst prognosis in adults. Currently, the automatic segmentation of this kind of tumor is being intensively studied. Here, the automatic three-dimensional segmentation of the GBM is achieved with its related subzones (active tumor, inner necrosis, and peripheral edema). Preliminary segmentations were first defined based on the four basic magnetic resonance imaging modalities and classic image processing methods (multithreshold Otsu, Chan-Vese active contours, and morphological erosion). After an automatic gap-filling post processing step, these preliminary segmentations were combined and corrected by a supervised artificial neural network of multilayer perceptron type with a hidden layer of 80 neurons, fed by 30 selected radiomic features of gray intensity and texture. Network classification has an overall accuracy of 83.9%, while the complete combined algorithm achieves average Dice similarity coefficients of 89.3%, 80.7%, 79.7% and 66.4% for the entire region of interest, active tumor, edema, and necrosis segmentations, respectively. These values are in the range of the best reported in the present bibliography, but even with better Hausdorff distances and lower computational costs. Results presented here evidence that it is possible to achieve the automatic segmentationof this kind of tumor by traditional radiomics. This has relevant clinical potential at the time of diagnosis, precision radiotherapy planning, or post-treatment response evaluation.
publishDate 2024
dc.date.none.fl_str_mv 2024-03
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/265372
Mulet de Los Reyes, Alexander; Hyde Lord, Victoria; Buemi, María Elena; Gandia, Daniel Enrique; Gómez Déniz, Luis; et al.; Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiforme; Wiley Blackwell Publishing, Inc; Expert Systems; 41; 9; 3-2024; 1-14
0266-4720
CONICET Digital
CONICET
url http://hdl.handle.net/11336/265372
identifier_str_mv Mulet de Los Reyes, Alexander; Hyde Lord, Victoria; Buemi, María Elena; Gandia, Daniel Enrique; Gómez Déniz, Luis; et al.; Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiforme; Wiley Blackwell Publishing, Inc; Expert Systems; 41; 9; 3-2024; 1-14
0266-4720
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1111/exsy.13598
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Wiley Blackwell Publishing, Inc
publisher.none.fl_str_mv Wiley Blackwell Publishing, Inc
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844613662369644544
score 13.070432

Publicaciones similares