Barrett’s esophagus analysis using surf features
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Outros Autores: | , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1007/978-3-662-54345-0_34 http://hdl.handle.net/11449/232609 |
Resumo: | The development of adenocarcinoma in Barrett’s esophagus is difficult to detect by endoscopic surveillance of patients with signs of dysplasia. Computer assisted diagnosis of endoscopic images (CAD) could therefore be most helpful in the demarcation and classification of neoplastic lesions. In this study we tested the feasibility of a CAD method based on Speeded up Robust Feature Detection (SURF). A given database containing 100 images from 39 patients served as benchmark for feature based classification models. Half of the images had previously been diagnosed by five clinical experts as being ”cancerous”, the other half as ”non-cancerous”. Cancerous image regions had been visibly delineated (masked) by the clinicians. SURF features acquired from full images as well as from masked areas were utilized for the supervised training and testing of an SVM classifier. The predictive accuracy of the developed CAD system is illustrated by sensitivity and specificity values. The results based on full image matching where 0.78 (sensitivity) and 0.82 (specificity) were achieved, while the masked region approach generated results of 0.90 and 0.95, respectively. |
id |
UNSP_fba07a55ceaaeef18fe889c17dd374e8 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/232609 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Barrett’s esophagus analysis using surf featuresThe development of adenocarcinoma in Barrett’s esophagus is difficult to detect by endoscopic surveillance of patients with signs of dysplasia. Computer assisted diagnosis of endoscopic images (CAD) could therefore be most helpful in the demarcation and classification of neoplastic lesions. In this study we tested the feasibility of a CAD method based on Speeded up Robust Feature Detection (SURF). A given database containing 100 images from 39 patients served as benchmark for feature based classification models. Half of the images had previously been diagnosed by five clinical experts as being ”cancerous”, the other half as ”non-cancerous”. Cancerous image regions had been visibly delineated (masked) by the clinicians. SURF features acquired from full images as well as from masked areas were utilized for the supervised training and testing of an SVM classifier. The predictive accuracy of the developed CAD system is illustrated by sensitivity and specificity values. The results based on full image matching where 0.78 (sensitivity) and 0.82 (specificity) were achieved, while the masked region approach generated results of 0.90 and 0.95, respectively.Department of Computing Faculty of Sciences São Paulo State UniversityRegensburg Medical Image Computing (ReMIC) Ostbayerische Technische Hochschule Regensburg (OTH Regensburg)Regensburg Center of Biomedical Engineering (RCBE) OTH Regensburg and Regensburg UniversityDepartment of Computing Faculty of Sciences São Paulo State UniversityUniversidade Estadual Paulista (UNESP)Ostbayerische Technische Hochschule Regensburg (OTH Regensburg)OTH Regensburg and Regensburg UniversitySouza, Luis [UNESP]Hook, ChristianPapa, João P. [UNESP]Palm, Christoph2022-04-30T00:06:41Z2022-04-30T00:06:41Z2017-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject141-146http://dx.doi.org/10.1007/978-3-662-54345-0_34Informatik aktuell, p. 141-146.1431-472Xhttp://hdl.handle.net/11449/23260910.1007/978-3-662-54345-0_342-s2.0-85019922992Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengInformatik aktuellinfo:eu-repo/semantics/openAccess2024-04-23T16:11:19Zoai:repositorio.unesp.br:11449/232609Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T16:30:44.558522Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Barrett’s esophagus analysis using surf features |
title |
Barrett’s esophagus analysis using surf features |
spellingShingle |
Barrett’s esophagus analysis using surf features Souza, Luis [UNESP] |
title_short |
Barrett’s esophagus analysis using surf features |
title_full |
Barrett’s esophagus analysis using surf features |
title_fullStr |
Barrett’s esophagus analysis using surf features |
title_full_unstemmed |
Barrett’s esophagus analysis using surf features |
title_sort |
Barrett’s esophagus analysis using surf features |
author |
Souza, Luis [UNESP] |
author_facet |
Souza, Luis [UNESP] Hook, Christian Papa, João P. [UNESP] Palm, Christoph |
author_role |
author |
author2 |
Hook, Christian Papa, João P. [UNESP] Palm, Christoph |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) Ostbayerische Technische Hochschule Regensburg (OTH Regensburg) OTH Regensburg and Regensburg University |
dc.contributor.author.fl_str_mv |
Souza, Luis [UNESP] Hook, Christian Papa, João P. [UNESP] Palm, Christoph |
description |
The development of adenocarcinoma in Barrett’s esophagus is difficult to detect by endoscopic surveillance of patients with signs of dysplasia. Computer assisted diagnosis of endoscopic images (CAD) could therefore be most helpful in the demarcation and classification of neoplastic lesions. In this study we tested the feasibility of a CAD method based on Speeded up Robust Feature Detection (SURF). A given database containing 100 images from 39 patients served as benchmark for feature based classification models. Half of the images had previously been diagnosed by five clinical experts as being ”cancerous”, the other half as ”non-cancerous”. Cancerous image regions had been visibly delineated (masked) by the clinicians. SURF features acquired from full images as well as from masked areas were utilized for the supervised training and testing of an SVM classifier. The predictive accuracy of the developed CAD system is illustrated by sensitivity and specificity values. The results based on full image matching where 0.78 (sensitivity) and 0.82 (specificity) were achieved, while the masked region approach generated results of 0.90 and 0.95, respectively. |
publishDate |
2017 |
dc.date.none.fl_str_mv |
2017-01-01 2022-04-30T00:06:41Z 2022-04-30T00:06:41Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1007/978-3-662-54345-0_34 Informatik aktuell, p. 141-146. 1431-472X http://hdl.handle.net/11449/232609 10.1007/978-3-662-54345-0_34 2-s2.0-85019922992 |
url |
http://dx.doi.org/10.1007/978-3-662-54345-0_34 http://hdl.handle.net/11449/232609 |
identifier_str_mv |
Informatik aktuell, p. 141-146. 1431-472X 10.1007/978-3-662-54345-0_34 2-s2.0-85019922992 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Informatik aktuell |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
141-146 |
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_ |
1808128663881777152 |