Boundary-aware feature and prediction refinement for polyp segmentation

Polyp segmentation from colonoscopy videos is an essential task in medical image processing for detecting early cancer. However, segmenting a precise boundary is still challenging, even with powerful deep neural networks. We consider the difficulty can be caused by: (1) the ambiguity boundary and (2...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization Ročník 11; číslo 4; s. 1187 - 1196
Hlavní autori: Qiu, Jie, Hayashi, Yuichiro, Oda, Masahiro, Kitasaka, Takayuki, Mori, Kensaku
Médium: Journal Article
Jazyk:English
Japanese
Vydavateľské údaje: Taylor & Francis 04.07.2023
Informa UK Limited
Predmet:
ISSN:2168-1163, 2168-1171
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Polyp segmentation from colonoscopy videos is an essential task in medical image processing for detecting early cancer. However, segmenting a precise boundary is still challenging, even with powerful deep neural networks. We consider the difficulty can be caused by: (1) the ambiguity boundary and (2) some complicated shape makes polyps hard to segment. To address these problems, we propose the Boundary-aware Feature and Prediction Refinement framework (BaFPR) for polyp segmentation. Specifically, we design a segmentation decoder for representation learning with boundary prior and propose a novel consistency loss to learn clues from the polar coordinate. The decoder mainly consists of a boundary prior module (BPM) and a bi-directional fusion module (BiFM). BPM is designed to learn the boundary prior, while BiFM learns to fuse representations of BPM and multi-scale representations from an encoder. To handle these complicated shapes of polyps, we maintain an extra segmentation network that learns with polar transformations of data to provide extra clues for the main segmentation network by our proposed consistency loss. We evaluated BaFPR with five challenging datasets for polyp segmentation and the results showed that our proposal consistently improves the segmentation performance of polyps. Code available at: https://github.com/MoriLabNU/BaFPR .
AbstractList Polyp segmentation from colonoscopy videos is an essential task in medical image processing for detecting early cancer. However, segmenting a precise boundary is still challenging, even with powerful deep neural networks. We consider the difficulty can be caused by: (1) the ambiguity boundary and (2) some complicated shape makes polyps hard to segment. To address these problems, we propose the Boundary-aware Feature and Prediction Refinement framework (BaFPR) for polyp segmentation. Specifically, we design a segmentation decoder for representation learning with boundary prior and propose a novel consistency loss to learn clues from the polar coordinate. The decoder mainly consists of a boundary prior module (BPM) and a bi-directional fusion module (BiFM). BPM is designed to learn the boundary prior, while BiFM learns to fuse representations of BPM and multi-scale representations from an encoder. To handle these complicated shapes of polyps, we maintain an extra segmentation network that learns with polar transformations of data to provide extra clues for the main segmentation network by our proposed consistency loss. We evaluated BaFPR with five challenging datasets for polyp segmentation and the results showed that our proposal consistently improves the segmentation performance of polyps. Code available at: https://github.com/MoriLabNU/BaFPR .
Author Oda, Masahiro
Qiu, Jie
Hayashi, Yuichiro
Kitasaka, Takayuki
Mori, Kensaku
Author_xml – sequence: 1
  givenname: Jie
  surname: Qiu
  fullname: Qiu, Jie
  email: jieqiu@mori.m.is.nagoya-u.ac.jp
  organization: Nagoya University
– sequence: 2
  givenname: Yuichiro
  surname: Hayashi
  fullname: Hayashi, Yuichiro
  organization: Nagoya University
– sequence: 3
  givenname: Masahiro
  orcidid: 0000-0001-7714-422X
  surname: Oda
  fullname: Oda, Masahiro
  organization: Nagoya University
– sequence: 4
  givenname: Takayuki
  surname: Kitasaka
  fullname: Kitasaka, Takayuki
  organization: Aichi Institute of Technology
– sequence: 5
  givenname: Kensaku
  orcidid: 0000-0002-0100-4797
  surname: Mori
  fullname: Mori, Kensaku
  email: kensaku@is.nagoya-u.ac.jp
  organization: National Institute of Informatics
BackLink https://cir.nii.ac.jp/crid/1873961342830394880$$DView record in CiNii
BookMark eNp9UMtOwzAQtFCRKKWfgJQD1xSvN3acG1BBQarEBc6W6zjIKLUjJ1WVv8dRC0fmsLsazb7mmsx88JaQW6AroJLeMxASQOCKUcZWDDjnZXVB5hOfA5Qw-6sFXpFl33_TBCkECj4nm6dw8LWOY66POtqssXo4pKx9nXXR1s4MLvgs2sZ5u7d-yJoQsy60Y5f19mti9KS4IZeNbnu7POcF-Xx5_li_5tv3zdv6cZsb5DjkDC1yqQUVoFlT7LQQlqKltUiA2qTIJeO7skJpKa8SYZpaA5OFQZQSF4Sf5poY-j6dpbro9ul-BVRNhqhfQ9RkiDobkvruTn3eOWXcFEGWWAnAgkmkWBVS0iR7OMmcT3_u9THEtlaDHtsQm6i9cb3C_zf9AHeHctA
Cites_doi 10.1007/s11548-013-0926-3
10.1007/s11263-021-01453-z
10.1109/CVPR42600.2020.00487
10.1016/j.media.2022.102418
10.1155/2017/4037190
10.1007/978-3-030-87193-2_66
10.1109/ACCESS.2021.3116265
10.1109/ICCV.2017.487
10.1007/978-3-030-37734-2_37
10.1007/s41095-022-0274-8
10.1109/TIP.2003.819861
10.1109/CVPR.2014.39
10.1016/j.neucom.2019.12.036
10.1007/978-3-319-24574-4_28
10.1007/978-3-030-87193-2_2
10.1109/ISM46123.2019.00049
10.1109/TPAMI.2019.2938758
10.1007/978-3-030-00889-5_1
10.1109/LGRS.2018.2802944
10.1007/978-3-030-01234-2_49
10.1007/978-3-030-32239-7_34
10.1109/CVPR42600.2020.00389
10.1016/j.patcog.2012.03.002
10.1016/j.dld.2016.06.025
10.1145/3474085.3475375
10.1007/978-3-030-59725-2_26
10.1109/CVPR.2017.667
10.1007/978-3-030-87193-2_20
10.1109/ICCV.2019.00140
10.1016/j.compmedimag.2015.02.007
10.1109/CVPR.2018.00745
ContentType Journal Article
Copyright 2022 Informa UK Limited, trading as Taylor & Francis Group 2022
Copyright_xml – notice: 2022 Informa UK Limited, trading as Taylor & Francis Group 2022
DBID RYH
AAYXX
CITATION
DOI 10.1080/21681163.2022.2155579
DatabaseName CiNii Complete
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2168-1171
EndPage 1196
ExternalDocumentID 10_1080_21681163_2022_2155579
2155579
Genre Research Article
GroupedDBID 0BK
30N
4.4
AAGDL
AAJMT
AALDU
AAMIU
AAPUL
AAQRR
ABLIJ
ABPAQ
ABXUL
ABXYU
ACGFS
ADCVX
ADGTB
ADMLS
AEISY
AFRVT
AGDLA
AHDZW
AIJEM
AIYEW
AKBVH
AKOOK
ALMA_UNASSIGNED_HOLDINGS
ALQZU
AQTUD
ARCSS
BLEHA
CCCUG
EBS
EUPTU
GTTXZ
H13
HZ~
KYCEM
LJTGL
M4Z
O9-
RIG
RNANH
ROSJB
RTWRZ
SNACF
SOJIQ
TBQAZ
TDBHL
TEN
TFL
TFT
TFW
TTHFI
TUROJ
RYH
AAYXX
CITATION
ID FETCH-LOGICAL-c353t-23e358a6061a2f4ba66e03e0d66661dc6665825b7938e059c66cfda1284c33883
IEDL.DBID TFW
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000901947800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2168-1163
IngestDate Sat Nov 29 06:34:11 EST 2025
Mon Nov 10 09:17:35 EST 2025
Mon Oct 20 23:49:00 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Language English
Japanese
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c353t-23e358a6061a2f4ba66e03e0d66661dc6665825b7938e059c66cfda1284c33883
ORCID 0000-0001-7714-422X
0000-0002-0100-4797
OpenAccessLink https://cir.nii.ac.jp/crid/1873961342830394880
PageCount 10
ParticipantIDs nii_cinii_1873961342830394880
informaworld_taylorfrancis_310_1080_21681163_2022_2155579
crossref_primary_10_1080_21681163_2022_2155579
PublicationCentury 2000
PublicationDate 2023-07-04
PublicationDateYYYYMMDD 2023-07-04
PublicationDate_xml – month: 07
  year: 2023
  text: 2023-07-04
  day: 04
PublicationDecade 2020
PublicationTitle Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
PublicationYear 2023
Publisher Taylor & Francis
Informa UK Limited
Publisher_xml – name: Taylor & Francis
– name: Informa UK Limited
References cit0011
cit0033
cit0012
cit0034
Kervadec H (cit0016) 2019
cit0031
cit0010
cit0032
Loshchilov I (cit0019) 2018
cit0030
cit0017
cit0018
cit0015
cit0013
cit0035
cit0014
cit0036
cit0022
cit0001
cit0020
cit0021
Dong B (cit0006) 2021
cit0008
cit0009
cit0028
cit0007
cit0029
cit0004
cit0026
cit0005
cit0027
cit0002
cit0024
cit0003
Roy AG (cit0023) 2018
cit0025
References_xml – ident: cit0024
  doi: 10.1007/s11548-013-0926-3
– ident: cit0011
  doi: 10.1007/s11263-021-01453-z
– ident: cit0018
  doi: 10.1109/CVPR42600.2020.00487
– ident: cit0032
  doi: 10.1016/j.media.2022.102418
– ident: cit0025
  doi: 10.1155/2017/4037190
– ident: cit0031
  doi: 10.1007/978-3-030-87193-2_66
– ident: cit0001
  doi: 10.1109/ACCESS.2021.3116265
– ident: cit0007
  doi: 10.1109/ICCV.2017.487
– ident: cit0014
  doi: 10.1007/978-3-030-37734-2_37
– ident: cit0029
  doi: 10.1007/s41095-022-0274-8
– ident: cit0026
  doi: 10.1109/TIP.2003.819861
– ident: cit0020
  doi: 10.1109/CVPR.2014.39
– ident: cit0035
  doi: 10.1016/j.neucom.2019.12.036
– volume-title: International Conference on Learning Representations
  year: 2018
  ident: cit0019
– ident: cit0022
  doi: 10.1007/978-3-319-24574-4_28
– ident: cit0033
  doi: 10.1007/978-3-030-87193-2_2
– ident: cit0015
  doi: 10.1109/ISM46123.2019.00049
– ident: cit0010
  doi: 10.1109/TPAMI.2019.2938758
– ident: cit0036
  doi: 10.1007/978-3-030-00889-5_1
– ident: cit0034
  doi: 10.1109/LGRS.2018.2802944
– ident: cit0005
  doi: 10.1007/978-3-030-01234-2_49
– ident: cit0008
  doi: 10.1007/978-3-030-32239-7_34
– ident: cit0027
  doi: 10.1109/CVPR42600.2020.00389
– start-page: 421
  volume-title: International conference on medical image computing and computer-assisted intervention
  year: 2018
  ident: cit0023
– ident: cit0003
  doi: 10.1016/j.patcog.2012.03.002
– ident: cit0021
  doi: 10.1016/j.dld.2016.06.025
– ident: cit0017
  doi: 10.1145/3474085.3475375
– ident: cit0009
  doi: 10.1007/978-3-030-59725-2_26
– ident: cit0004
  doi: 10.1109/CVPR.2017.667
– ident: cit0028
  doi: 10.1007/978-3-030-87193-2_20
– ident: cit0030
  doi: 10.1007/s41095-022-0274-8
– ident: cit0012
  doi: 10.1109/ICCV.2019.00140
– year: 2021
  ident: cit0006
  publication-title: This is a technical report rather than a journal paper
– ident: cit0002
  doi: 10.1016/j.compmedimag.2015.02.007
– start-page: 285
  volume-title: International conference on medical imaging with deep learning
  year: 2019
  ident: cit0016
– ident: cit0013
  doi: 10.1109/CVPR.2018.00745
SSID ssj0000866365
ssib044168314
ssib039557987
ssib024195514
Score 2.240919
Snippet Polyp segmentation from colonoscopy videos is an essential task in medical image processing for detecting early cancer. However, segmenting a precise boundary...
SourceID crossref
nii
informaworld
SourceType Index Database
Publisher
StartPage 1187
SubjectTerms boundary-aware
consistency learning
Polyp segmentation
Title Boundary-aware feature and prediction refinement for polyp segmentation
URI https://www.tandfonline.com/doi/abs/10.1080/21681163.2022.2155579
https://cir.nii.ac.jp/crid/1873961342830394880
Volume 11
WOSCitedRecordID wos000901947800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAWR
  databaseName: Taylor & Francis Online Journals
  customDbUrl:
  eissn: 2168-1171
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000866365
  issn: 2168-1163
  databaseCode: TFW
  dateStart: 20130301
  isFulltext: true
  titleUrlDefault: https://www.tandfonline.com
  providerName: Taylor & Francis
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZQxQADb0SBIg-sKUlsx84IiMKAKoYiukVuYqNKEKIkgPrvuXMS1A6IARYPkc6xzo_vzr77jpDzjAOsamZgf1vr8YwrT0sReZmxEiwEbpjvEoXv5XisptP4oY0mrNqwSvShbUMU4c5q3Nx6VnURcRdhEKkA7Ajw7sJwCJglhMQUPoB-rGEwGT1937KAwR4xV08ShTyU6tJ4fupoBaBW6EsBfvL5fAl-Rtv_MPAdstXanvSyWSy7ZM3ke2RziZFwn9xeuTJL5cLTn7o01BpH_Enhl7Qo8VEHJ5LCqEEGLxYpDJwWby-Lglbm-bXNZMoPyOPoZnJ957W1FryUCVZ7ITNMKA3uTKBDy2c6iozPjJ-BexMFWQqtAGdyBttZGTDJ4ENqM43oloKXq9gh6eVvuTkiVCpARQyfYpJzobXiLDUBk1bHQliR9cmwU3BSNJQaSdAylXYaSlBDSauhPomXpyGp3V2GbQqPJOwX2QHMWZLOsQ2UZDHYL0gy57MYz67jP_R9Qjaw-LwL3uWnpFeX72ZA1tOPel6VZ24hfgH8utUn
linkProvider Taylor & Francis
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELagIAEDb0SBggfWQBPbiTMCohRROhXRLXITG0WCNEoDqP-euzxQOiAGWDJEOsc6P767y913hJxHHGBVMQ3n2xiLR1xayhOuFWnjgYXANesWhcIDbziU47HfrIXBtEr0oU1JFFHc1Xi4MRhdp8RdOrYrbTAkwL1znAsALSE8f5msCMBa3OWj3vN3nAVMdpcVHSVRykKxupDnp5EWIGqBwBQAKInjBgD1tv5j6ttkszI_6VW5X3bIkk52yUaDlHCP3F0XnZayuaU-Vaap0QX3J4Vv0jTD_zq4lhSmDTIYW6Qwc5pOX-cpnemXt6qYKdknT73b0U3fqtotWCETLLccppmQCjwaWzmGT5Tr6i7T3Qg8HNeOQngK8CcncKKlBqsMXoQmUghwITi6kh2QVjJN9CGhngRgxAwq5nEulJKchdpmnlG-EEZEbXJRazhIS1aNwK7ISmsNBaihoNJQm_jNdQjyIpxhyt4jAftFtgOLFoQxPm3pMR9MGOSZ6zIfr6-jP4x9Rtb6o8dBMLgfPhyTdexFX-Ty8hPSyrN33SGr4Ucez7LTYld-AaS22VI
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELagIAQDb0SBggfWlCS2Y2fkFUBUVYciukVuYqNIkEZpAPXfc84DtQNigCVDpHOs8-P7zjl_h9B5TAFWJVGwvrW2aEyFJTnzrFhpDgyBKmKXF4V7vN8Xo5E_qLMJp3VapYmhdSUUUe7VZnFnsW4y4i5cxxMO8AiI7ly3C5jFGPeX0QpQZ8_EX8Pg-fuYBRi7R8qCksbKMmbNPZ6fWlpAqAX9UsCfNEnm8CfY-oeeb6PNmnziy2q27KAlle6ijTlJwj10d1XWWcpnlvyUucJalcqfGD6Js9z81TEjiaHXYGNOFjF0HGeT11mGp-rlrb7KlO6jp-B2eH1v1cUWrIgwUlguUYQJCfGMI11Nx9LzlE2UHUN84zlxBE8G0eQY1rNQwMngRaRjaeAtgjBXkAPUSiepOkSYC4BFkz9FOKVMSkFJpBzCtfQZ0yxuo27j4DCrNDVCp5YqbTwUGg-FtYfayJ8fhrAoDzN0VXkkJL_YdmDMwigxT0dw4gOBMSpzNvHN5nX0h7bP0NrgJgh7D_3HY7RuCtGXibz0BLWK_F110Gr0USTT_LSck18hMtgD
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Boundary-aware+feature+and+prediction+refinement+for+polyp+segmentation&rft.jtitle=Computer+methods+in+biomechanics+and+biomedical+engineering.&rft.au=Qiu%2C+Jie&rft.au=Hayashi%2C+Yuichiro&rft.au=Oda%2C+Masahiro&rft.au=Kitasaka%2C+Takayuki&rft.date=2023-07-04&rft.pub=Taylor+%26+Francis&rft.issn=2168-1163&rft.eissn=2168-1171&rft.volume=11&rft.issue=4&rft.spage=1187&rft.epage=1196&rft_id=info:doi/10.1080%2F21681163.2022.2155579&rft.externalDocID=2155579
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2168-1163&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2168-1163&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2168-1163&client=summon