Lung disease detection using feature extraction and extreme learning machine
Autor(a) principal: | |
---|---|
Data de Publicação: | 2014 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Revista Brasileira de Engenharia Biomédica (Online) |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1517-31512014000300002 |
Resumo: | INTRODUCTION: The World Health Organization estimates that by 2030 the Chronic Obstructive Pulmonary Disease (COPD) will be the third leading cause of death worldwide. Computerized Tomography (CT) images of lungs comprise a number of structures that are relevant for pulmonary disease diagnosis and analysis. METHODS: In this paper, we employ the Adaptive Crisp Active Contour Models (ACACM) for lung structure segmentation. And we propose a novel method for lung disease detection based on feature extraction of ACACM segmented images within the cooccurrence statistics framework. The spatial interdependence matrix (SIM) synthesizes the structural information of lung image structures in terms of three attributes. Finally, we perform a classification experiment on this set of attributes to discriminate two types of lung diseases and health lungs. We evaluate the discrimination ability of the proposed lung image descriptors using an extreme learning machine neural network (ELMNN) comprising 4-10 neurons in the hidden layer and 3 neurons in the output layer to map each pulmonary condition. This network was trained and validated by applying a holdout procedure. RESULTS: The experimental results achieved 96% accuracy demonstrating the effectiveness of the proposed method on identifying normal lungs and diseases as COPD and fibrosis. CONCLUSION: Our results lead to conclude that the method is suitable to integrate clinical decision support systems for pulmonary screening and diagnosis. |
id |
SBEB-2_5ef3df6a62ac36777b40a388569ad9a8 |
---|---|
oai_identifier_str |
oai:scielo:S1517-31512014000300002 |
network_acronym_str |
SBEB-2 |
network_name_str |
Revista Brasileira de Engenharia Biomédica (Online) |
repository_id_str |
|
spelling |
Lung disease detection using feature extraction and extreme learning machineLung diseasesChest CT imagesActive contour modelsSpatial interdependence matrixFeature extractionImage segmentationINTRODUCTION: The World Health Organization estimates that by 2030 the Chronic Obstructive Pulmonary Disease (COPD) will be the third leading cause of death worldwide. Computerized Tomography (CT) images of lungs comprise a number of structures that are relevant for pulmonary disease diagnosis and analysis. METHODS: In this paper, we employ the Adaptive Crisp Active Contour Models (ACACM) for lung structure segmentation. And we propose a novel method for lung disease detection based on feature extraction of ACACM segmented images within the cooccurrence statistics framework. The spatial interdependence matrix (SIM) synthesizes the structural information of lung image structures in terms of three attributes. Finally, we perform a classification experiment on this set of attributes to discriminate two types of lung diseases and health lungs. We evaluate the discrimination ability of the proposed lung image descriptors using an extreme learning machine neural network (ELMNN) comprising 4-10 neurons in the hidden layer and 3 neurons in the output layer to map each pulmonary condition. This network was trained and validated by applying a holdout procedure. RESULTS: The experimental results achieved 96% accuracy demonstrating the effectiveness of the proposed method on identifying normal lungs and diseases as COPD and fibrosis. CONCLUSION: Our results lead to conclude that the method is suitable to integrate clinical decision support systems for pulmonary screening and diagnosis.SBEB - Sociedade Brasileira de Engenharia Biomédica2014-09-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S1517-31512014000300002Revista Brasileira de Engenharia Biomédica v.30 n.3 2014reponame:Revista Brasileira de Engenharia Biomédica (Online)instname:Sociedade Brasileira de Engenharia Biomédica (SBEB)instacron:SBEB10.1590/rbeb.2014.019info:eu-repo/semantics/openAccessRamalho,Geraldo Luis BezerraRebouças Filho,Pedro PedrosaMedeiros,Fátima Nelsizeuma Sombra deCortez,Paulo Césareng2014-09-24T00:00:00Zoai:scielo:S1517-31512014000300002Revistahttp://www.scielo.br/rbebONGhttps://old.scielo.br/oai/scielo-oai.php||rbeb@rbeb.org.br1984-77421517-3151opendoar:2014-09-24T00:00Revista Brasileira de Engenharia Biomédica (Online) - Sociedade Brasileira de Engenharia Biomédica (SBEB)false |
dc.title.none.fl_str_mv |
Lung disease detection using feature extraction and extreme learning machine |
title |
Lung disease detection using feature extraction and extreme learning machine |
spellingShingle |
Lung disease detection using feature extraction and extreme learning machine Ramalho,Geraldo Luis Bezerra Lung diseases Chest CT images Active contour models Spatial interdependence matrix Feature extraction Image segmentation |
title_short |
Lung disease detection using feature extraction and extreme learning machine |
title_full |
Lung disease detection using feature extraction and extreme learning machine |
title_fullStr |
Lung disease detection using feature extraction and extreme learning machine |
title_full_unstemmed |
Lung disease detection using feature extraction and extreme learning machine |
title_sort |
Lung disease detection using feature extraction and extreme learning machine |
author |
Ramalho,Geraldo Luis Bezerra |
author_facet |
Ramalho,Geraldo Luis Bezerra Rebouças Filho,Pedro Pedrosa Medeiros,Fátima Nelsizeuma Sombra de Cortez,Paulo César |
author_role |
author |
author2 |
Rebouças Filho,Pedro Pedrosa Medeiros,Fátima Nelsizeuma Sombra de Cortez,Paulo César |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Ramalho,Geraldo Luis Bezerra Rebouças Filho,Pedro Pedrosa Medeiros,Fátima Nelsizeuma Sombra de Cortez,Paulo César |
dc.subject.por.fl_str_mv |
Lung diseases Chest CT images Active contour models Spatial interdependence matrix Feature extraction Image segmentation |
topic |
Lung diseases Chest CT images Active contour models Spatial interdependence matrix Feature extraction Image segmentation |
description |
INTRODUCTION: The World Health Organization estimates that by 2030 the Chronic Obstructive Pulmonary Disease (COPD) will be the third leading cause of death worldwide. Computerized Tomography (CT) images of lungs comprise a number of structures that are relevant for pulmonary disease diagnosis and analysis. METHODS: In this paper, we employ the Adaptive Crisp Active Contour Models (ACACM) for lung structure segmentation. And we propose a novel method for lung disease detection based on feature extraction of ACACM segmented images within the cooccurrence statistics framework. The spatial interdependence matrix (SIM) synthesizes the structural information of lung image structures in terms of three attributes. Finally, we perform a classification experiment on this set of attributes to discriminate two types of lung diseases and health lungs. We evaluate the discrimination ability of the proposed lung image descriptors using an extreme learning machine neural network (ELMNN) comprising 4-10 neurons in the hidden layer and 3 neurons in the output layer to map each pulmonary condition. This network was trained and validated by applying a holdout procedure. RESULTS: The experimental results achieved 96% accuracy demonstrating the effectiveness of the proposed method on identifying normal lungs and diseases as COPD and fibrosis. CONCLUSION: Our results lead to conclude that the method is suitable to integrate clinical decision support systems for pulmonary screening and diagnosis. |
publishDate |
2014 |
dc.date.none.fl_str_mv |
2014-09-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1517-31512014000300002 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1517-31512014000300002 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/rbeb.2014.019 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
SBEB - Sociedade Brasileira de Engenharia Biomédica |
publisher.none.fl_str_mv |
SBEB - Sociedade Brasileira de Engenharia Biomédica |
dc.source.none.fl_str_mv |
Revista Brasileira de Engenharia Biomédica v.30 n.3 2014 reponame:Revista Brasileira de Engenharia Biomédica (Online) instname:Sociedade Brasileira de Engenharia Biomédica (SBEB) instacron:SBEB |
instname_str |
Sociedade Brasileira de Engenharia Biomédica (SBEB) |
instacron_str |
SBEB |
institution |
SBEB |
reponame_str |
Revista Brasileira de Engenharia Biomédica (Online) |
collection |
Revista Brasileira de Engenharia Biomédica (Online) |
repository.name.fl_str_mv |
Revista Brasileira de Engenharia Biomédica (Online) - Sociedade Brasileira de Engenharia Biomédica (SBEB) |
repository.mail.fl_str_mv |
||rbeb@rbeb.org.br |
_version_ |
1754820915124764673 |