Lymphoma images analysis using morphological and non-morphological descriptors for classification
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.cmpb.2018.05.035 http://hdl.handle.net/11449/176402 |
Resumo: | Mantle cell lymphoma, follicular lymphoma and chronic lymphocytic leukemia are the principle subtypes of the non-Hodgkin lymphomas. The diversity of clinical presentations and the histopathological features have made diagnosis of such lymphomas a complex task for specialists. Computer aided diagnosis systems employ computational vision and image processing techniques, which contribute toward the detection, diagnosis and prognosis of digitised images of histological samples. Studies aimed at improving the understanding of morphological and non-morphological features for classification of lymphoma remain a challenge in this area. This work presents a new approach for the classification of information extracted from morphological and non-morphological features of nuclei of lymphoma images. We extracted data of the RGB model of the image and employed contrast limited adaptive histogram equalisation and 2D order-statistics filter methods to enhance the contrast and remove noise. The regions of interest were identified by the global thresholding method. The flood-fill and watershed techniques were used to remove the small false positive regions. The area, extent, perimeter, convex area, solidity, eccentricity, equivalent diameter, minor axis and major axis measurements were computed for the regions detected in the nuclei. In the feature selection stage, we applied the ANOVA, Ansari-Bradley and Wilcoxon rank sum methods. Finally, we employed the polynomial, support vector machine, random forest and decision tree classifiers in order to evaluate the performance of the proposed approach. The non-morphological features achieved higher AUC and AC values for all cases: the obtained rates were between 95% and 100%. These results are relevant, especially when we consider the difficulties of clinical practice in distinguishing the studied groups. The proposed approach is useful as an automated protocol for the diagnosis of lymphoma histological tissue. |
id |
UNSP_20452bae534f86edeb572f98995c80a3 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/176402 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Lymphoma images analysis using morphological and non-morphological descriptors for classificationHistological imageLymphomaMorphological and non-morphological featuresPolynomialSVMMantle cell lymphoma, follicular lymphoma and chronic lymphocytic leukemia are the principle subtypes of the non-Hodgkin lymphomas. The diversity of clinical presentations and the histopathological features have made diagnosis of such lymphomas a complex task for specialists. Computer aided diagnosis systems employ computational vision and image processing techniques, which contribute toward the detection, diagnosis and prognosis of digitised images of histological samples. Studies aimed at improving the understanding of morphological and non-morphological features for classification of lymphoma remain a challenge in this area. This work presents a new approach for the classification of information extracted from morphological and non-morphological features of nuclei of lymphoma images. We extracted data of the RGB model of the image and employed contrast limited adaptive histogram equalisation and 2D order-statistics filter methods to enhance the contrast and remove noise. The regions of interest were identified by the global thresholding method. The flood-fill and watershed techniques were used to remove the small false positive regions. The area, extent, perimeter, convex area, solidity, eccentricity, equivalent diameter, minor axis and major axis measurements were computed for the regions detected in the nuclei. In the feature selection stage, we applied the ANOVA, Ansari-Bradley and Wilcoxon rank sum methods. Finally, we employed the polynomial, support vector machine, random forest and decision tree classifiers in order to evaluate the performance of the proposed approach. The non-morphological features achieved higher AUC and AC values for all cases: the obtained rates were between 95% and 100%. These results are relevant, especially when we consider the difficulties of clinical practice in distinguishing the studied groups. The proposed approach is useful as an automated protocol for the diagnosis of lymphoma histological tissue.Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG)UFU - FACOM, av. João Neves de Ávila 2121, Bl.BIFTM, r. Belarmino Vilela Junqueira S/NUFABC - CMCC, av. dos Estados 5001, Bl.BUNESP - DCCE, r. Cristóvão Colombo 2265UNESP - DCCE, r. Cristóvão Colombo 2265CNPq: 427114/2016-0FAPEMIG: TEC-APQ-02885-15UFU - FACOMIFTMUniversidade Federal do ABC (UFABC)Universidade Estadual Paulista (Unesp)do Nascimento, Marcelo ZanchettaMartins, Alessandro SantanaAzevedo Tosta, Thaína AparecidaNeves, Leandro Alves [UNESP]2018-12-11T17:20:40Z2018-12-11T17:20:40Z2018-09-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article65-77application/pdfhttp://dx.doi.org/10.1016/j.cmpb.2018.05.035Computer Methods and Programs in Biomedicine, v. 163, p. 65-77.1872-75650169-2607http://hdl.handle.net/11449/17640210.1016/j.cmpb.2018.05.0352-s2.0-850480757932-s2.0-85048075793.pdfScopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengComputer Methods and Programs in Biomedicine0,786info:eu-repo/semantics/openAccess2023-11-07T06:14:24Zoai:repositorio.unesp.br:11449/176402Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T17:06:29.618022Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Lymphoma images analysis using morphological and non-morphological descriptors for classification |
title |
Lymphoma images analysis using morphological and non-morphological descriptors for classification |
spellingShingle |
Lymphoma images analysis using morphological and non-morphological descriptors for classification do Nascimento, Marcelo Zanchetta Histological image Lymphoma Morphological and non-morphological features Polynomial SVM |
title_short |
Lymphoma images analysis using morphological and non-morphological descriptors for classification |
title_full |
Lymphoma images analysis using morphological and non-morphological descriptors for classification |
title_fullStr |
Lymphoma images analysis using morphological and non-morphological descriptors for classification |
title_full_unstemmed |
Lymphoma images analysis using morphological and non-morphological descriptors for classification |
title_sort |
Lymphoma images analysis using morphological and non-morphological descriptors for classification |
author |
do Nascimento, Marcelo Zanchetta |
author_facet |
do Nascimento, Marcelo Zanchetta Martins, Alessandro Santana Azevedo Tosta, Thaína Aparecida Neves, Leandro Alves [UNESP] |
author_role |
author |
author2 |
Martins, Alessandro Santana Azevedo Tosta, Thaína Aparecida Neves, Leandro Alves [UNESP] |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
UFU - FACOM IFTM Universidade Federal do ABC (UFABC) Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
do Nascimento, Marcelo Zanchetta Martins, Alessandro Santana Azevedo Tosta, Thaína Aparecida Neves, Leandro Alves [UNESP] |
dc.subject.por.fl_str_mv |
Histological image Lymphoma Morphological and non-morphological features Polynomial SVM |
topic |
Histological image Lymphoma Morphological and non-morphological features Polynomial SVM |
description |
Mantle cell lymphoma, follicular lymphoma and chronic lymphocytic leukemia are the principle subtypes of the non-Hodgkin lymphomas. The diversity of clinical presentations and the histopathological features have made diagnosis of such lymphomas a complex task for specialists. Computer aided diagnosis systems employ computational vision and image processing techniques, which contribute toward the detection, diagnosis and prognosis of digitised images of histological samples. Studies aimed at improving the understanding of morphological and non-morphological features for classification of lymphoma remain a challenge in this area. This work presents a new approach for the classification of information extracted from morphological and non-morphological features of nuclei of lymphoma images. We extracted data of the RGB model of the image and employed contrast limited adaptive histogram equalisation and 2D order-statistics filter methods to enhance the contrast and remove noise. The regions of interest were identified by the global thresholding method. The flood-fill and watershed techniques were used to remove the small false positive regions. The area, extent, perimeter, convex area, solidity, eccentricity, equivalent diameter, minor axis and major axis measurements were computed for the regions detected in the nuclei. In the feature selection stage, we applied the ANOVA, Ansari-Bradley and Wilcoxon rank sum methods. Finally, we employed the polynomial, support vector machine, random forest and decision tree classifiers in order to evaluate the performance of the proposed approach. The non-morphological features achieved higher AUC and AC values for all cases: the obtained rates were between 95% and 100%. These results are relevant, especially when we consider the difficulties of clinical practice in distinguishing the studied groups. The proposed approach is useful as an automated protocol for the diagnosis of lymphoma histological tissue. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-12-11T17:20:40Z 2018-12-11T17:20:40Z 2018-09-01 |
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/10.1016/j.cmpb.2018.05.035 Computer Methods and Programs in Biomedicine, v. 163, p. 65-77. 1872-7565 0169-2607 http://hdl.handle.net/11449/176402 10.1016/j.cmpb.2018.05.035 2-s2.0-85048075793 2-s2.0-85048075793.pdf |
url |
http://dx.doi.org/10.1016/j.cmpb.2018.05.035 http://hdl.handle.net/11449/176402 |
identifier_str_mv |
Computer Methods and Programs in Biomedicine, v. 163, p. 65-77. 1872-7565 0169-2607 10.1016/j.cmpb.2018.05.035 2-s2.0-85048075793 2-s2.0-85048075793.pdf |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Computer Methods and Programs in Biomedicine 0,786 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
65-77 application/pdf |
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 |
|
_version_ |
1808128756450066432 |