Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://hdl.handle.net/1822/74448 |
Resumo: | The majority of current systems for automatic diagnosis considers the detection of a unique and previously known pathology. Considering specifically the diagnosis of lesions in the small bowel using endoscopic capsule images, very few consider the possible existence of more than one pathology and when they do, they are mainly detection based systems therefore unable to localize the suspected lesions. Such systems do not fully satisfy the medical community, that in fact needs a system that detects any pathology and eventually more than one, when they coexist. In addition, besides the diagnostic capability of these systems, localizing the lesions in the image has been of great interest to the medical community, mainly for training medical personnel purposes. So, nowadays, the inclusion of the lesion location in automatic diagnostic systems is practically mandatory. Multi-pathology detection can be seen as a multi-object detection task and as each frame can contain different instances of the same lesion, instance segmentation seems to be appropriate for the purpose. Consequently, we argue that a multi-pathology system benefits from using the instance segmentation approach, since classification and segmentation modules are both required complementing each other in lesion detection and localization. According to our best knowledge such a system does not yet exist for the detection of WCE pathologies. This paper proposes a multi-pathology system that can be applied to WCE images, which uses the Mask Improved RCNN (MI-RCNN), a new mask subnet scheme which has shown to significantly improve mask predictions of the high performing state-of-the-art Mask-RCNN and PANet systems. A novel training strategy based on the second momentum is also proposed for the first time for training Mask-RCNN and PANet based systems. These approaches were tested using the public database KID, and the included pathologies were bleeding, angioectasias, polyps and inflammatory lesions. Experimental results show significant improvements for the pr |
id |
RCAP_31167b0d872e0b05f93d625ba5dd75fc |
---|---|
oai_identifier_str |
oai:repositorium.sdum.uminho.pt:1822/74448 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approachInstance segmentationLesion localizationMask-RCNNMulti-pathology detectionPANetWireless capsule endoscopyCiências Médicas::Medicina BásicaScience & TechnologyThe majority of current systems for automatic diagnosis considers the detection of a unique and previously known pathology. Considering specifically the diagnosis of lesions in the small bowel using endoscopic capsule images, very few consider the possible existence of more than one pathology and when they do, they are mainly detection based systems therefore unable to localize the suspected lesions. Such systems do not fully satisfy the medical community, that in fact needs a system that detects any pathology and eventually more than one, when they coexist. In addition, besides the diagnostic capability of these systems, localizing the lesions in the image has been of great interest to the medical community, mainly for training medical personnel purposes. So, nowadays, the inclusion of the lesion location in automatic diagnostic systems is practically mandatory. Multi-pathology detection can be seen as a multi-object detection task and as each frame can contain different instances of the same lesion, instance segmentation seems to be appropriate for the purpose. Consequently, we argue that a multi-pathology system benefits from using the instance segmentation approach, since classification and segmentation modules are both required complementing each other in lesion detection and localization. According to our best knowledge such a system does not yet exist for the detection of WCE pathologies. This paper proposes a multi-pathology system that can be applied to WCE images, which uses the Mask Improved RCNN (MI-RCNN), a new mask subnet scheme which has shown to significantly improve mask predictions of the high performing state-of-the-art Mask-RCNN and PANet systems. A novel training strategy based on the second momentum is also proposed for the first time for training Mask-RCNN and PANet based systems. These approaches were tested using the public database KID, and the included pathologies were bleeding, angioectasias, polyps and inflammatory lesions. Experimental results show significant improvements for the prFCT national funds, under the national support to R&D units grant, through the reference project UIDB/04436/2020 and UIDP/04436/2020 and through the PhD Grants with the references SFRH/BD/92143/2013 and SFRH/BD/139061/2018ElsevierUniversidade do MinhoVieira, Pedro MiguelFreitas, Nuno Renato AzevedoLima, Veríssimo B.Costa, Dalila Amélia AmorimRolanda, CarlaLima, C. S.2021-09-012021-09-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/1822/74448engVieira, P. M., Freitas, N. R., Lima, V. B., Costa, D., Rolanda, C., & Lima, C. S. (2021). Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach. Artificial Intelligence in Medicine, 119, 1021410933-365710.1016/j.artmed.2021.10214134531016https://www.sciencedirect.com/science/article/pii/S0933365721001342info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-07-21T12:45:55Zoai:repositorium.sdum.uminho.pt:1822/74448Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T19:43:51.399647Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach |
title |
Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach |
spellingShingle |
Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach Vieira, Pedro Miguel Instance segmentation Lesion localization Mask-RCNN Multi-pathology detection PANet Wireless capsule endoscopy Ciências Médicas::Medicina Básica Science & Technology |
title_short |
Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach |
title_full |
Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach |
title_fullStr |
Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach |
title_full_unstemmed |
Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach |
title_sort |
Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach |
author |
Vieira, Pedro Miguel |
author_facet |
Vieira, Pedro Miguel Freitas, Nuno Renato Azevedo Lima, Veríssimo B. Costa, Dalila Amélia Amorim Rolanda, Carla Lima, C. S. |
author_role |
author |
author2 |
Freitas, Nuno Renato Azevedo Lima, Veríssimo B. Costa, Dalila Amélia Amorim Rolanda, Carla Lima, C. S. |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Universidade do Minho |
dc.contributor.author.fl_str_mv |
Vieira, Pedro Miguel Freitas, Nuno Renato Azevedo Lima, Veríssimo B. Costa, Dalila Amélia Amorim Rolanda, Carla Lima, C. S. |
dc.subject.por.fl_str_mv |
Instance segmentation Lesion localization Mask-RCNN Multi-pathology detection PANet Wireless capsule endoscopy Ciências Médicas::Medicina Básica Science & Technology |
topic |
Instance segmentation Lesion localization Mask-RCNN Multi-pathology detection PANet Wireless capsule endoscopy Ciências Médicas::Medicina Básica Science & Technology |
description |
The majority of current systems for automatic diagnosis considers the detection of a unique and previously known pathology. Considering specifically the diagnosis of lesions in the small bowel using endoscopic capsule images, very few consider the possible existence of more than one pathology and when they do, they are mainly detection based systems therefore unable to localize the suspected lesions. Such systems do not fully satisfy the medical community, that in fact needs a system that detects any pathology and eventually more than one, when they coexist. In addition, besides the diagnostic capability of these systems, localizing the lesions in the image has been of great interest to the medical community, mainly for training medical personnel purposes. So, nowadays, the inclusion of the lesion location in automatic diagnostic systems is practically mandatory. Multi-pathology detection can be seen as a multi-object detection task and as each frame can contain different instances of the same lesion, instance segmentation seems to be appropriate for the purpose. Consequently, we argue that a multi-pathology system benefits from using the instance segmentation approach, since classification and segmentation modules are both required complementing each other in lesion detection and localization. According to our best knowledge such a system does not yet exist for the detection of WCE pathologies. This paper proposes a multi-pathology system that can be applied to WCE images, which uses the Mask Improved RCNN (MI-RCNN), a new mask subnet scheme which has shown to significantly improve mask predictions of the high performing state-of-the-art Mask-RCNN and PANet systems. A novel training strategy based on the second momentum is also proposed for the first time for training Mask-RCNN and PANet based systems. These approaches were tested using the public database KID, and the included pathologies were bleeding, angioectasias, polyps and inflammatory lesions. Experimental results show significant improvements for the pr |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-09-01 2021-09-01T00:00:00Z |
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 |
https://hdl.handle.net/1822/74448 |
url |
https://hdl.handle.net/1822/74448 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Vieira, P. M., Freitas, N. R., Lima, V. B., Costa, D., Rolanda, C., & Lima, C. S. (2021). Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach. Artificial Intelligence in Medicine, 119, 102141 0933-3657 10.1016/j.artmed.2021.102141 34531016 https://www.sciencedirect.com/science/article/pii/S0933365721001342 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799132996906778624 |