Learning Shape Priors by Pairwise Comparison for Robust Semantic Segmentation

Semantic segmentation is important in medical image analysis. Inspired by the strong ability of traditional image analysis techniques in capturing shape priors and inter-subject similarity, many deep learning (DL) models have been recently proposed to exploit such prior information and achieved robu...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (International Symposium on Biomedical Imaging) s. 38 - 41
Hlavní autoři: Xie, Cong, Liu, Hualuo, Cao, Shilei, Wei, Dong, Ma, Kai, Wang, Liansheng, Zheng, Yefeng
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 13.04.2021
Témata:
ISSN:1945-8452
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Semantic segmentation is important in medical image analysis. Inspired by the strong ability of traditional image analysis techniques in capturing shape priors and inter-subject similarity, many deep learning (DL) models have been recently proposed to exploit such prior information and achieved robust performance. However, these two types of important prior information are usually studied separately in existing models. In this paper, we propose a novel DL model to model both type of priors within a single framework. Specifically, we introduce an extra encoder into the classic encoder-decoder structure to form a Siamese structure for the encoders, where one of them takes a target image as input (the image-encoder), and the other concatenates a template image and its foreground regions as input (the template-encoder). The template-encoder encodes the shape priors and appearance characteristics of each foreground class in the template image. A cosine similarity based attention module is proposed to fuse the information from both encoders, to utilize both types of prior information encoded by the template-encoder and model the inter-subject similarity for each foreground class. Extensive experiments on two public datasets demonstrate that our proposed method can produce superior performance to competing methods.
AbstractList Semantic segmentation is important in medical image analysis. Inspired by the strong ability of traditional image analysis techniques in capturing shape priors and inter-subject similarity, many deep learning (DL) models have been recently proposed to exploit such prior information and achieved robust performance. However, these two types of important prior information are usually studied separately in existing models. In this paper, we propose a novel DL model to model both type of priors within a single framework. Specifically, we introduce an extra encoder into the classic encoder-decoder structure to form a Siamese structure for the encoders, where one of them takes a target image as input (the image-encoder), and the other concatenates a template image and its foreground regions as input (the template-encoder). The template-encoder encodes the shape priors and appearance characteristics of each foreground class in the template image. A cosine similarity based attention module is proposed to fuse the information from both encoders, to utilize both types of prior information encoded by the template-encoder and model the inter-subject similarity for each foreground class. Extensive experiments on two public datasets demonstrate that our proposed method can produce superior performance to competing methods.
Author Xie, Cong
Cao, Shilei
Wang, Liansheng
Ma, Kai
Wei, Dong
Zheng, Yefeng
Liu, Hualuo
Author_xml – sequence: 1
  givenname: Cong
  surname: Xie
  fullname: Xie, Cong
  organization: Xiamen University
– sequence: 2
  givenname: Hualuo
  surname: Liu
  fullname: Liu, Hualuo
  organization: Tencent Jarvis Lab
– sequence: 3
  givenname: Shilei
  surname: Cao
  fullname: Cao, Shilei
  organization: Tencent Jarvis Lab
– sequence: 4
  givenname: Dong
  surname: Wei
  fullname: Wei, Dong
  organization: Tencent Jarvis Lab
– sequence: 5
  givenname: Kai
  surname: Ma
  fullname: Ma, Kai
  organization: Tencent Jarvis Lab
– sequence: 6
  givenname: Liansheng
  surname: Wang
  fullname: Wang, Liansheng
  email: lswang@xmu.edu.cn
  organization: Xiamen University
– sequence: 7
  givenname: Yefeng
  surname: Zheng
  fullname: Zheng, Yefeng
  organization: Tencent Jarvis Lab
BookMark eNotj81KAzEURqMo2NY-gSB5gan5uZNMllqsFioWq-tyZ-ZOjThJSUakb2_BfptzVge-MbsIMRBjt1LMpBTubrl5WEKlpJwpoeTMgdZOmzM2lsaUIBUYec5G0kFZVFCqKzbN-UscZwG0gBF7WRGm4MOObz5xT3ydfEyZ1we-Rp9-fSY-j_0ek88x8C4m_hbrnzzwDfUYBt8cZddTGHDwMVyzyw6_M01PnLCPxeP7_LlYvT4t5_erwiuhh6I1ZWsciMYAYEOgO6xMQ2UH1jqLJVQCVaOtqIWsK2ctkGsbI0nXqNrW6gm7-e96Itruk-8xHban9_oPbQpRHw
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ISBI48211.2021.9433936
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 1665412461
9781665412469
EISSN 1945-8452
EndPage 41
ExternalDocumentID 9433936
Genre orig-research
GrantInformation_xml – fundername: Fundamental Research Funds for the Central Universities
  funderid: 10.13039/501100012226
GroupedDBID 23N
6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i203t-d65d6940c644ace43fa86ce5f47797a5480a2c370b01b89774e9dc61e3ba2dd73
IEDL.DBID RIE
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000786144100009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:27:47 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-d65d6940c644ace43fa86ce5f47797a5480a2c370b01b89774e9dc61e3ba2dd73
PageCount 4
ParticipantIDs ieee_primary_9433936
PublicationCentury 2000
PublicationDate 2021-April-13
PublicationDateYYYYMMDD 2021-04-13
PublicationDate_xml – month: 04
  year: 2021
  text: 2021-April-13
  day: 13
PublicationDecade 2020
PublicationTitle Proceedings (International Symposium on Biomedical Imaging)
PublicationTitleAbbrev ISBI
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000744304
Score 2.1626618
Snippet Semantic segmentation is important in medical image analysis. Inspired by the strong ability of traditional image analysis techniques in capturing shape priors...
SourceID ieee
SourceType Publisher
StartPage 38
SubjectTerms Analytical models
Biological system modeling
Deep learning
Fuses
Image analysis
Image segmentation
Inter-subject similarity
Semantic segmentation
Shape
Shape priors
Title Learning Shape Priors by Pairwise Comparison for Robust Semantic Segmentation
URI https://ieeexplore.ieee.org/document/9433936
WOSCitedRecordID wos000786144100009&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFH9sw4Ne_NjEb3LwaLe2yZrk6nA40DGcwm4jX5092I62U_zvTbpSFbx4CyEh8EJ4v_defr8HcB3rofVbFHsh84lHuB97Atv3KBUTKqgEzyt1_Qc6nbLFgs9acNNwYYwx1ecz03fDqpavM7VxqbIBJxhzHLWhTSndcrWafIp1hcSG5jUJOPD5YDK_nRBmAxwbBYZBv978q4tK5UTG-_87_gB632w8NGv8zCG0THoEez-EBLvwWMukrtD8Vazd8iTLCyQ_0Uwk-UdSGDRqGg4ii1PRUyY3RYnm5s2aNlF2sHqraUhpD17Gd8-je69ulOAloY9LT0dDHXHiKwtuhDIEx4JFygxjQimnwkm6iVBh6pKekjnEZ7hWUWCwFKHWFB9DJ81ScwKIxBYvMSwCIyQxhDIlsFZ-ZGGMDCSPT6HrDLNcb7UwlrVNzv6ePoddZ3tXfQnwBXTKfGMuYUe9l0mRX1UX-AWHuJwJ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4QTdSLP8D42x48OljXbm2vEglEIEQw4UbarsMd2AgbGv9727FMTbx4a5o2aV7TvO-91-97ANxHoW_8FsWOx1ziEO5GjsDmPUrFhEKF4Hmhrj-goxGbzfi4Bh4qLozWuvh8plt2WNTyw1RtbKqszQnGHAc7YNcnxENbtlaVUTHOkJjgvKQBI5e3-5PHPmEmxDFxoIda5fZffVQKN9I9-t8BjkHzm48Hx5WnOQE1nZyCwx9Sgg0wLIVSF3DyJlZ2eZyuMyg_4VjE648407BTtRyEBqnCl1RushxO9NIYN1ZmsFiWRKSkCV67T9NOzylbJTix5-LcCQM_DDhxlYE3QmmCI8ECpf2IUMqpsKJuwlOY2rSnZBbzaR6qAGkshReGFJ-BepIm-hxAEhnExLBAWkiiCWVK4FC5gQEyEkkeXYCGNcx8tVXDmJc2ufx7-g7s96bDwXzQHz1fgQN7D7YWg_A1qOfrjb4Be-o9j7P1bXGZX9Sdn1A
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=proceeding&rft.title=Proceedings+%28International+Symposium+on+Biomedical+Imaging%29&rft.atitle=Learning+Shape+Priors+by+Pairwise+Comparison+for+Robust+Semantic+Segmentation&rft.au=Xie%2C+Cong&rft.au=Liu%2C+Hualuo&rft.au=Cao%2C+Shilei&rft.au=Wei%2C+Dong&rft.date=2021-04-13&rft.pub=IEEE&rft.eissn=1945-8452&rft.spage=38&rft.epage=41&rft_id=info:doi/10.1109%2FISBI48211.2021.9433936&rft.externalDocID=9433936