Lack of robustness of textural measures obtained from 3D brain tumor MRIs impose a need for standardization

Purpose Textural measures have been widely explored as imaging biomarkers in cancer. However, their robustness under dynamic range and spatial resolution changes in brain 3D magnetic resonance images (MRI) has not been assessed. The aim of this work was to study potential variations of textural meas...

Descripción completa

Detalles Bibliográficos
Autores: Molina, David, Pérez Beteta, Julián, Martínez González, Alicia, Martino González, Juan, Velasquez, Carlos, Arana, Estanislao, Pérez García, Víctor M.
Tipo de recurso: artículo
Fecha de publicación:2017
País:España
Institución:Universidad de Cantabria (UC)
Repositorio:UCrea Repositorio Abierto de la Universidad de Cantabria
Idioma:inglés
OAI Identifier:oai:repositorio.unican.es:10902/12086
Acceso en línea:http://hdl.handle.net/10902/12086
Access Level:acceso abierto
id ES_b2a11e0ddb9db7c84d0f3d93514c829c
oai_identifier_str oai:repositorio.unican.es:10902/12086
network_acronym_str ES
network_name_str España
repository_id_str
spelling Lack of robustness of textural measures obtained from 3D brain tumor MRIs impose a need for standardizationMolina, DavidPérez Beteta, JuliánMartínez González, AliciaMartino González, JuanVelasquez, CarlosArana, EstanislaoPérez García, Víctor M.Purpose Textural measures have been widely explored as imaging biomarkers in cancer. However, their robustness under dynamic range and spatial resolution changes in brain 3D magnetic resonance images (MRI) has not been assessed. The aim of this work was to study potential variations of textural measures due to changes in MRI protocols. Materials and methods Twenty patients harboring glioblastoma with pretreatment 3D T1-weighted MRIs were included in the study. Four different spatial resolution combinations and three dynamic ranges were studied for each patient. Sixteen three-dimensional textural heterogeneity measures were computed for each patient and configuration including co-occurrence matrices (CM) features and run-length matrices (RLM) features. The coefficient of variation was used to assess the robustness of the measures in two series of experiments corresponding to (i) changing the dynamic range and (ii) changing the matrix size. Results No textural measures were robust under dynamic range changes. Entropy was the only textural feature robust under spatial resolution changes (coefficient of variation under 10% in all cases). Conclusion Textural measures of three-dimensional brain tumor images are not robust neither under dynamic range nor under matrix size changes. Standards should be harmonized to use textural features as imaging biomarkers in radiomic-based studies. The implications of this work go beyond the specific tumor type studied here and pose the need for standardization in textural feature calculation of oncological images.Public Library of ScienceUniversidad de Cantabria20172017-01-01journal articlehttp://purl.org/coar/resource_type/c_6501NAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/articlehttp://hdl.handle.net/10902/12086PLoS ONE 12(6): e0178843reponame:UCrea Repositorio Abierto de la Universidad de Cantabriainstname:Universidad de Cantabria (UC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Atribución 3.0 Españahttp://creativecommons.org/licenses/by/3.0/es/info:eu-repo/semantics/openAccessoai:repositorio.unican.es:10902/120862026-06-02T12:39:31Z
dc.title.none.fl_str_mv Lack of robustness of textural measures obtained from 3D brain tumor MRIs impose a need for standardization
title Lack of robustness of textural measures obtained from 3D brain tumor MRIs impose a need for standardization
spellingShingle Lack of robustness of textural measures obtained from 3D brain tumor MRIs impose a need for standardization
Molina, David
title_short Lack of robustness of textural measures obtained from 3D brain tumor MRIs impose a need for standardization
title_full Lack of robustness of textural measures obtained from 3D brain tumor MRIs impose a need for standardization
title_fullStr Lack of robustness of textural measures obtained from 3D brain tumor MRIs impose a need for standardization
title_full_unstemmed Lack of robustness of textural measures obtained from 3D brain tumor MRIs impose a need for standardization
title_sort Lack of robustness of textural measures obtained from 3D brain tumor MRIs impose a need for standardization
dc.creator.none.fl_str_mv Molina, David
Pérez Beteta, Julián
Martínez González, Alicia
Martino González, Juan
Velasquez, Carlos
Arana, Estanislao
Pérez García, Víctor M.
author Molina, David
author_facet Molina, David
Pérez Beteta, Julián
Martínez González, Alicia
Martino González, Juan
Velasquez, Carlos
Arana, Estanislao
Pérez García, Víctor M.
author_role author
author2 Pérez Beteta, Julián
Martínez González, Alicia
Martino González, Juan
Velasquez, Carlos
Arana, Estanislao
Pérez García, Víctor M.
author2_role author
author
author
author
author
author
dc.contributor.none.fl_str_mv Universidad de Cantabria
description Purpose Textural measures have been widely explored as imaging biomarkers in cancer. However, their robustness under dynamic range and spatial resolution changes in brain 3D magnetic resonance images (MRI) has not been assessed. The aim of this work was to study potential variations of textural measures due to changes in MRI protocols. Materials and methods Twenty patients harboring glioblastoma with pretreatment 3D T1-weighted MRIs were included in the study. Four different spatial resolution combinations and three dynamic ranges were studied for each patient. Sixteen three-dimensional textural heterogeneity measures were computed for each patient and configuration including co-occurrence matrices (CM) features and run-length matrices (RLM) features. The coefficient of variation was used to assess the robustness of the measures in two series of experiments corresponding to (i) changing the dynamic range and (ii) changing the matrix size. Results No textural measures were robust under dynamic range changes. Entropy was the only textural feature robust under spatial resolution changes (coefficient of variation under 10% in all cases). Conclusion Textural measures of three-dimensional brain tumor images are not robust neither under dynamic range nor under matrix size changes. Standards should be harmonized to use textural features as imaging biomarkers in radiomic-based studies. The implications of this work go beyond the specific tumor type studied here and pose the need for standardization in textural feature calculation of oncological images.
publishDate 2017
dc.date.none.fl_str_mv 2017
2017-01-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10902/12086
url http://hdl.handle.net/10902/12086
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Atribución 3.0 España
http://creativecommons.org/licenses/by/3.0/es/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Atribución 3.0 España
http://creativecommons.org/licenses/by/3.0/es/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Public Library of Science
publisher.none.fl_str_mv Public Library of Science
dc.source.none.fl_str_mv PLoS ONE 12(6): e0178843
reponame:UCrea Repositorio Abierto de la Universidad de Cantabria
instname:Universidad de Cantabria (UC)
instname_str Universidad de Cantabria (UC)
reponame_str UCrea Repositorio Abierto de la Universidad de Cantabria
collection UCrea Repositorio Abierto de la Universidad de Cantabria
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869417071040790528
score 15,301629

Similares en LA Referencia