Combining machine learning and texture analysis to differentiate mediastinal lymph nodes in lung cancer patients
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1007/s13246-021-00988-2 http://hdl.handle.net/11449/209270 |
Resumo: | Evaluate whether texture analysis associated with machine learning approaches could differentiate between malignant and benign lymph nodes. A total 18 patients with lung cancer were selected, with 39 lymph nodes, being 15 malignant and 24 benign. Retrospective computed tomography scans were utilized both with and without contrast medium. The great differential of this work was the use of 15 textures from mediastinal lymph nodes, with five different physicians as operators. First and second order statistical textures such as gray level run length and co-occurrence matrix were extracted and applied to three different machine learning classifiers. The best machine learning classifier demonstrated a variability of less than 5% among operators. The support vector machine (SVM) classifier presented 95% of the area under the ROC curve (AUC) and 89% of sensitivity for sequences without contrast medium. SVM classifier presented 93% of AUC and 86% of sensitivity for sequences with contrast medium. Texture analysis and machine learning may be helpful in the differentiation between malign and benign lymph nodes. This study can aid the physician in diagnosis and staging of lymph nodes and potentially reduce the number of invasive analysis to histopathological confirmation. |
id |
UNSP_6d7920a8fcbaff956d80b0f92da7ea7e |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/209270 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Combining machine learning and texture analysis to differentiate mediastinal lymph nodes in lung cancer patientsLymph nodesTexturesMachine learningImageEvaluate whether texture analysis associated with machine learning approaches could differentiate between malignant and benign lymph nodes. A total 18 patients with lung cancer were selected, with 39 lymph nodes, being 15 malignant and 24 benign. Retrospective computed tomography scans were utilized both with and without contrast medium. The great differential of this work was the use of 15 textures from mediastinal lymph nodes, with five different physicians as operators. First and second order statistical textures such as gray level run length and co-occurrence matrix were extracted and applied to three different machine learning classifiers. The best machine learning classifier demonstrated a variability of less than 5% among operators. The support vector machine (SVM) classifier presented 95% of the area under the ROC curve (AUC) and 89% of sensitivity for sequences without contrast medium. SVM classifier presented 93% of AUC and 86% of sensitivity for sequences with contrast medium. Texture analysis and machine learning may be helpful in the differentiation between malign and benign lymph nodes. This study can aid the physician in diagnosis and staging of lymph nodes and potentially reduce the number of invasive analysis to histopathological confirmation.Sao Paulo State Univ Julio de Mesquita Filho, Med Sch, Aracatuba, BrazilSao Paulo State Univ Julio de Mesquita Filho, Inst Biosci, Aracatuba, BrazilSao Paulo State Univ Julio de Mesquita Filho, Med Sch, Aracatuba, BrazilSao Paulo State Univ Julio de Mesquita Filho, Inst Biosci, Aracatuba, BrazilSpringerUniversidade Estadual Paulista (Unesp)Alves, Allan F. F. [UNESP]Souza, Sergio A. [UNESP]Ruiz, Raul L. [UNESP]Reis, Tarcisio A. [UNESP]Ximenes, Aglaia M. G. [UNESP]Hasimoto, Erica N. [UNESP]Pires, Rodrigo L. [UNESP]Miranda, Jose Ricardo A. [UNESP]Pina, Diana R. [UNESP]2021-06-25T11:54:44Z2021-06-25T11:54:44Z2021-03-17info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article8http://dx.doi.org/10.1007/s13246-021-00988-2Physical And Engineering Sciences In Medicine. Dordrecht: Springer, 8 p., 2021.2662-4729http://hdl.handle.net/11449/20927010.1007/s13246-021-00988-2WOS:000629908800001Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengPhysical And Engineering Sciences In Medicineinfo:eu-repo/semantics/openAccess2021-10-23T19:23:41Zoai:repositorio.unesp.br:11449/209270Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-23T19:23:41Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Combining machine learning and texture analysis to differentiate mediastinal lymph nodes in lung cancer patients |
title |
Combining machine learning and texture analysis to differentiate mediastinal lymph nodes in lung cancer patients |
spellingShingle |
Combining machine learning and texture analysis to differentiate mediastinal lymph nodes in lung cancer patients Alves, Allan F. F. [UNESP] Lymph nodes Textures Machine learning Image |
title_short |
Combining machine learning and texture analysis to differentiate mediastinal lymph nodes in lung cancer patients |
title_full |
Combining machine learning and texture analysis to differentiate mediastinal lymph nodes in lung cancer patients |
title_fullStr |
Combining machine learning and texture analysis to differentiate mediastinal lymph nodes in lung cancer patients |
title_full_unstemmed |
Combining machine learning and texture analysis to differentiate mediastinal lymph nodes in lung cancer patients |
title_sort |
Combining machine learning and texture analysis to differentiate mediastinal lymph nodes in lung cancer patients |
author |
Alves, Allan F. F. [UNESP] |
author_facet |
Alves, Allan F. F. [UNESP] Souza, Sergio A. [UNESP] Ruiz, Raul L. [UNESP] Reis, Tarcisio A. [UNESP] Ximenes, Aglaia M. G. [UNESP] Hasimoto, Erica N. [UNESP] Pires, Rodrigo L. [UNESP] Miranda, Jose Ricardo A. [UNESP] Pina, Diana R. [UNESP] |
author_role |
author |
author2 |
Souza, Sergio A. [UNESP] Ruiz, Raul L. [UNESP] Reis, Tarcisio A. [UNESP] Ximenes, Aglaia M. G. [UNESP] Hasimoto, Erica N. [UNESP] Pires, Rodrigo L. [UNESP] Miranda, Jose Ricardo A. [UNESP] Pina, Diana R. [UNESP] |
author2_role |
author author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Alves, Allan F. F. [UNESP] Souza, Sergio A. [UNESP] Ruiz, Raul L. [UNESP] Reis, Tarcisio A. [UNESP] Ximenes, Aglaia M. G. [UNESP] Hasimoto, Erica N. [UNESP] Pires, Rodrigo L. [UNESP] Miranda, Jose Ricardo A. [UNESP] Pina, Diana R. [UNESP] |
dc.subject.por.fl_str_mv |
Lymph nodes Textures Machine learning Image |
topic |
Lymph nodes Textures Machine learning Image |
description |
Evaluate whether texture analysis associated with machine learning approaches could differentiate between malignant and benign lymph nodes. A total 18 patients with lung cancer were selected, with 39 lymph nodes, being 15 malignant and 24 benign. Retrospective computed tomography scans were utilized both with and without contrast medium. The great differential of this work was the use of 15 textures from mediastinal lymph nodes, with five different physicians as operators. First and second order statistical textures such as gray level run length and co-occurrence matrix were extracted and applied to three different machine learning classifiers. The best machine learning classifier demonstrated a variability of less than 5% among operators. The support vector machine (SVM) classifier presented 95% of the area under the ROC curve (AUC) and 89% of sensitivity for sequences without contrast medium. SVM classifier presented 93% of AUC and 86% of sensitivity for sequences with contrast medium. Texture analysis and machine learning may be helpful in the differentiation between malign and benign lymph nodes. This study can aid the physician in diagnosis and staging of lymph nodes and potentially reduce the number of invasive analysis to histopathological confirmation. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-06-25T11:54:44Z 2021-06-25T11:54:44Z 2021-03-17 |
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/s13246-021-00988-2 Physical And Engineering Sciences In Medicine. Dordrecht: Springer, 8 p., 2021. 2662-4729 http://hdl.handle.net/11449/209270 10.1007/s13246-021-00988-2 WOS:000629908800001 |
url |
http://dx.doi.org/10.1007/s13246-021-00988-2 http://hdl.handle.net/11449/209270 |
identifier_str_mv |
Physical And Engineering Sciences In Medicine. Dordrecht: Springer, 8 p., 2021. 2662-4729 10.1007/s13246-021-00988-2 WOS:000629908800001 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Physical And Engineering Sciences In Medicine |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
8 |
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_ |
1799964868966612992 |