Multiple analyses suggests texture features can indicate the presence of tumor in the prostate tissue

Detalhes bibliográficos
Autor(a) principal: Souza, Sérgio Augusto Santana [UNESP]
Data de Publicação: 2022
Outros Autores: Reis, Leonardo Oliveira, Alves, Allan Felipe Fattori [UNESP], Silva, Letícia Cotinguiba [UNESP], Medeiros, Maria Clara Korndorfer, Andrade, Danilo Leite, Billis, Athanase, Amaro, João Luiz [UNESP], Martins, Daniel Lahan, Trindade, André Petean [UNESP], Miranda, José Ricardo Arruda [UNESP], Pina, Diana Rodrigues [UNESP]
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1007/s13246-022-01118-2
http://hdl.handle.net/11449/230681
Resumo: Several studies have demonstrated statistical and texture analysis abilities to differentiate cancerous from healthy tissue in magnetic resonance imaging. This study developed a method based on texture analysis and machine learning to differentiate prostate findings. Forty-eight male patients with PI-RADS classification and subsequent radical prostatectomy histopathological analysis were used as gold standard. Experienced radiologists delimited the regions of interest in magnetic resonance images. Six different groups of images were used to perform multiple analyses (seven analyses variations). Those analyses were outlined by specialists in urology as those of most significant importance for the classification. Forty texture features were extracted from each image and processed with Random Forest, Support Vector Machine, K-Nearest Neighbors, and Naive Bayes. Those seven analyses variation results were described in terms of area under the ROC curve (AUC), accuracy, F-score, precision and sensitivity. The highest AUC (93.7%) and accuracy (88.8%) were obtained when differentiating the group with both MRI and histopathology positive findings against the group with both negative MRI and histopathology. When differentiating the group with both MRI and histopathology positive findings versus the peripheral image zone group the AUC value was 86.6%. When differentiating the group with negative MRI/positive histopathology versus the group with both negative MRI and histopathology the AUC value was 80.7%. The evaluation of statistical and texture analysis promoted very suggestive indications for future work in prostate cancer suspicious regions. The method is fast for both region of interest selection and classification with machine learning and the result brings original contributions in the classification of different groups of patients. This tool is low-cost, and can be used to assist diagnostic decisions.
id UNSP_b069256412f9ca13f635b5fe62297375
oai_identifier_str oai:repositorio.unesp.br:11449/230681
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Multiple analyses suggests texture features can indicate the presence of tumor in the prostate tissueHistopathologyMachine learningMagnetic resonance imagingProstate cancerTexture analysisSeveral studies have demonstrated statistical and texture analysis abilities to differentiate cancerous from healthy tissue in magnetic resonance imaging. This study developed a method based on texture analysis and machine learning to differentiate prostate findings. Forty-eight male patients with PI-RADS classification and subsequent radical prostatectomy histopathological analysis were used as gold standard. Experienced radiologists delimited the regions of interest in magnetic resonance images. Six different groups of images were used to perform multiple analyses (seven analyses variations). Those analyses were outlined by specialists in urology as those of most significant importance for the classification. Forty texture features were extracted from each image and processed with Random Forest, Support Vector Machine, K-Nearest Neighbors, and Naive Bayes. Those seven analyses variation results were described in terms of area under the ROC curve (AUC), accuracy, F-score, precision and sensitivity. The highest AUC (93.7%) and accuracy (88.8%) were obtained when differentiating the group with both MRI and histopathology positive findings against the group with both negative MRI and histopathology. When differentiating the group with both MRI and histopathology positive findings versus the peripheral image zone group the AUC value was 86.6%. When differentiating the group with negative MRI/positive histopathology versus the group with both negative MRI and histopathology the AUC value was 80.7%. The evaluation of statistical and texture analysis promoted very suggestive indications for future work in prostate cancer suspicious regions. The method is fast for both region of interest selection and classification with machine learning and the result brings original contributions in the classification of different groups of patients. This tool is low-cost, and can be used to assist diagnostic decisions.São Paulo State University Júlio de Mesquita Filho, R. Prof. Dr. Antônio Celso Wagner Zanin, 250 - Distrito de Rubião Junior, SPDepartment of Urology UroScience State University of Campinas Unicamp and Pontifical Catholic University of Campinas PUC-Campinas, Av. John Boyd Dunlop-Jardim Ipaussurama, SPBotucatu Medical School Clinics Hospital Medical Physics and Radioprotection Nucleus, Av. Prof. Mário Rubens Guimarães Montenegro, s/n - UNESP - Campus de Botucatu, SPDepartment of Radiology Pontifical Catholic University of Campinas, SPDepartment of Anatomic Pathology and Urology School of Medical Sciences State University of Campinas (Unicamp)Department of Urology Botucatu Medical School São Paulo State University (UNESP), SPDepartment of Radiology University of Campinas (UNICAMP), SPBotucatu Medical School São Paulo State University Júlio de Mesquita Filho, Av. Prof. Mário Rubens Guimarães Montenegro, s/n - UNESP - Campus de Botucatu, SPInstitute of Bioscience São Paulo State University Júlio de Mesquita Filho, R. Prof. Dr. Antônio Celso Wagner Zanin, 250 - Distrito de Rubião Junior, SPSão Paulo State University Júlio de Mesquita Filho, R. Prof. Dr. Antônio Celso Wagner Zanin, 250 - Distrito de Rubião Junior, SPBotucatu Medical School Clinics Hospital Medical Physics and Radioprotection Nucleus, Av. Prof. Mário Rubens Guimarães Montenegro, s/n - UNESP - Campus de Botucatu, SPDepartment of Urology Botucatu Medical School São Paulo State University (UNESP), SPBotucatu Medical School São Paulo State University Júlio de Mesquita Filho, Av. Prof. Mário Rubens Guimarães Montenegro, s/n - UNESP - Campus de Botucatu, SPInstitute of Bioscience São Paulo State University Júlio de Mesquita Filho, R. Prof. Dr. Antônio Celso Wagner Zanin, 250 - Distrito de Rubião Junior, SPUniversidade Estadual Paulista (UNESP)Universidade Estadual de Campinas (UNICAMP)Souza, Sérgio Augusto Santana [UNESP]Reis, Leonardo OliveiraAlves, Allan Felipe Fattori [UNESP]Silva, Letícia Cotinguiba [UNESP]Medeiros, Maria Clara KorndorferAndrade, Danilo LeiteBillis, AthanaseAmaro, João Luiz [UNESP]Martins, Daniel LahanTrindade, André Petean [UNESP]Miranda, José Ricardo Arruda [UNESP]Pina, Diana Rodrigues [UNESP]2022-04-29T08:41:29Z2022-04-29T08:41:29Z2022-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1007/s13246-022-01118-2Physical and Engineering Sciences in Medicine.2662-47372662-4729http://hdl.handle.net/11449/23068110.1007/s13246-022-01118-22-s2.0-85127617059Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengPhysical and Engineering Sciences in Medicineinfo:eu-repo/semantics/openAccess2024-09-03T14:29:55Zoai:repositorio.unesp.br:11449/230681Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestrepositoriounesp@unesp.bropendoar:29462024-09-03T14:29:55Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Multiple analyses suggests texture features can indicate the presence of tumor in the prostate tissue
title Multiple analyses suggests texture features can indicate the presence of tumor in the prostate tissue
spellingShingle Multiple analyses suggests texture features can indicate the presence of tumor in the prostate tissue
Souza, Sérgio Augusto Santana [UNESP]
Histopathology
Machine learning
Magnetic resonance imaging
Prostate cancer
Texture analysis
title_short Multiple analyses suggests texture features can indicate the presence of tumor in the prostate tissue
title_full Multiple analyses suggests texture features can indicate the presence of tumor in the prostate tissue
title_fullStr Multiple analyses suggests texture features can indicate the presence of tumor in the prostate tissue
title_full_unstemmed Multiple analyses suggests texture features can indicate the presence of tumor in the prostate tissue
title_sort Multiple analyses suggests texture features can indicate the presence of tumor in the prostate tissue
author Souza, Sérgio Augusto Santana [UNESP]
author_facet Souza, Sérgio Augusto Santana [UNESP]
Reis, Leonardo Oliveira
Alves, Allan Felipe Fattori [UNESP]
Silva, Letícia Cotinguiba [UNESP]
Medeiros, Maria Clara Korndorfer
Andrade, Danilo Leite
Billis, Athanase
Amaro, João Luiz [UNESP]
Martins, Daniel Lahan
Trindade, André Petean [UNESP]
Miranda, José Ricardo Arruda [UNESP]
Pina, Diana Rodrigues [UNESP]
author_role author
author2 Reis, Leonardo Oliveira
Alves, Allan Felipe Fattori [UNESP]
Silva, Letícia Cotinguiba [UNESP]
Medeiros, Maria Clara Korndorfer
Andrade, Danilo Leite
Billis, Athanase
Amaro, João Luiz [UNESP]
Martins, Daniel Lahan
Trindade, André Petean [UNESP]
Miranda, José Ricardo Arruda [UNESP]
Pina, Diana Rodrigues [UNESP]
author2_role author
author
author
author
author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (UNESP)
Universidade Estadual de Campinas (UNICAMP)
dc.contributor.author.fl_str_mv Souza, Sérgio Augusto Santana [UNESP]
Reis, Leonardo Oliveira
Alves, Allan Felipe Fattori [UNESP]
Silva, Letícia Cotinguiba [UNESP]
Medeiros, Maria Clara Korndorfer
Andrade, Danilo Leite
Billis, Athanase
Amaro, João Luiz [UNESP]
Martins, Daniel Lahan
Trindade, André Petean [UNESP]
Miranda, José Ricardo Arruda [UNESP]
Pina, Diana Rodrigues [UNESP]
dc.subject.por.fl_str_mv Histopathology
Machine learning
Magnetic resonance imaging
Prostate cancer
Texture analysis
topic Histopathology
Machine learning
Magnetic resonance imaging
Prostate cancer
Texture analysis
description Several studies have demonstrated statistical and texture analysis abilities to differentiate cancerous from healthy tissue in magnetic resonance imaging. This study developed a method based on texture analysis and machine learning to differentiate prostate findings. Forty-eight male patients with PI-RADS classification and subsequent radical prostatectomy histopathological analysis were used as gold standard. Experienced radiologists delimited the regions of interest in magnetic resonance images. Six different groups of images were used to perform multiple analyses (seven analyses variations). Those analyses were outlined by specialists in urology as those of most significant importance for the classification. Forty texture features were extracted from each image and processed with Random Forest, Support Vector Machine, K-Nearest Neighbors, and Naive Bayes. Those seven analyses variation results were described in terms of area under the ROC curve (AUC), accuracy, F-score, precision and sensitivity. The highest AUC (93.7%) and accuracy (88.8%) were obtained when differentiating the group with both MRI and histopathology positive findings against the group with both negative MRI and histopathology. When differentiating the group with both MRI and histopathology positive findings versus the peripheral image zone group the AUC value was 86.6%. When differentiating the group with negative MRI/positive histopathology versus the group with both negative MRI and histopathology the AUC value was 80.7%. The evaluation of statistical and texture analysis promoted very suggestive indications for future work in prostate cancer suspicious regions. The method is fast for both region of interest selection and classification with machine learning and the result brings original contributions in the classification of different groups of patients. This tool is low-cost, and can be used to assist diagnostic decisions.
publishDate 2022
dc.date.none.fl_str_mv 2022-04-29T08:41:29Z
2022-04-29T08:41:29Z
2022-01-01
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/s13246-022-01118-2
Physical and Engineering Sciences in Medicine.
2662-4737
2662-4729
http://hdl.handle.net/11449/230681
10.1007/s13246-022-01118-2
2-s2.0-85127617059
url http://dx.doi.org/10.1007/s13246-022-01118-2
http://hdl.handle.net/11449/230681
identifier_str_mv Physical and Engineering Sciences in Medicine.
2662-4737
2662-4729
10.1007/s13246-022-01118-2
2-s2.0-85127617059
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.source.none.fl_str_mv Scopus
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 repositoriounesp@unesp.br
_version_ 1810021358433730560