Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/62446
Registo completo
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor.author | Vieira, Pedro M. | por |
dc.contributor.author | Pinto, Catarina | por |
dc.contributor.author | Costa, Dalila | por |
dc.contributor.author | Vaz, A. Ismael F. | por |
dc.contributor.author | Rolanda, Carla | por |
dc.contributor.author | Lima, Carlos S. | por |
dc.date.accessioned | 2019-11-27T15:58:57Z | - |
dc.date.issued | 2019 | - |
dc.identifier.issn | 0090-6964 | - |
dc.identifier.uri | https://hdl.handle.net/1822/62446 | - |
dc.description.abstract | Angioectasias are lesions that occur in the blood vessels of the bowel and are the cause of more than 8% of all gastrointestinal bleeding episodes. They are usually classified as bleeding related lesions, however current state-of-the-art bleeding detection algorithms present low sensitivity in the detection of these lesions. This paper proposes a methodology for the automatic detection of angioectasias in wireless capsule endoscopy (WCE) videos. This method relies on the automatic selection of a region of interest, selected by using an image segmentation module based on the Maximum a Posteriori (MAP) approach where a new accelerated version of the Expectation-Maximization (EM) algorithm is also proposed. Spatial context information is modeled in the prior probability density function by using Markov Random Fields with the inclusion of a weighted boundary function. Higher order statistics computed in the CIELab color space with the luminance component removed and intensity normalization of high reflectance regions, showed to be effective features regarding angioectasia detection. The proposed method outperforms some current state of the art algorithms, achieving sensitivity and specificity values of more than 96% in a database containing 800 WCE frames labeled by two gastroenterologists. | por |
dc.description.sponsorship | This work is supported by FCT (Fundação para a Ciência e Tecnologia) with the reference project UID/EEA/04436/2013, by FEDER funds through the COMPETE 2020 Programa Operacional Competitividade e Internacionalização (POCI) with the reference project POCI01-0145-FEDER-006941 and with the grant SFRH/BD/92143/2013. | por |
dc.language.iso | eng | por |
dc.publisher | Springer | por |
dc.relation | info:eu-repo/grantAgreement/FCT/5876/147325/PT | por |
dc.relation | info:eu-repo/grantAgreement/FCT/5876/147325/PT | - |
dc.relation | SFRH/BD/92143/2013 | - |
dc.rights | closedAccess | por |
dc.subject | Algorithms | por |
dc.subject | Gastrointestinal Hemorrhage | por |
dc.subject | Humans | por |
dc.subject | Image Interpretation, Computer-Assisted | por |
dc.subject | Capsule Endoscopy | por |
dc.subject | Intestine, Small | por |
dc.subject | EM Segmentation | por |
dc.subject | Machine learning | por |
dc.subject | Markov Random Fields | por |
dc.subject | Angioectasias | por |
dc.title | Automatic segmentation and detection of small bowel angioectasias in WCE images | por |
dc.type | article | por |
dc.peerreviewed | yes | por |
oaire.citationStartPage | 1446 | por |
oaire.citationEndPage | 1462 | por |
oaire.citationIssue | 6 | por |
oaire.citationVolume | 47 | por |
dc.identifier.eissn | 1573-9686 | - |
dc.identifier.doi | 10.1007/s10439-019-02248-7 | - |
dc.date.embargo | 10000-01-01 | - |
dc.identifier.pmid | 30919139 | por |
dc.subject.wos | Science & Technology | por |
sdum.journal | Annals of Biomedical Engineering | por |
Aparece nas coleções: | ICVS - Artigos em revistas internacionais / Papers in international journals MEtRICs - Artigos em revistas internacionais/Papers in international journals |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
Artigo_AnnalsBiomEng.pdf Acesso restrito! | 2,05 MB | Adobe PDF | Ver/Abrir |