DoDNet: Learning to Segment Multi-Organ and Tumors from Multiple Partially Labeled Datasets

Due to the intensive cost of labor and expertise in annotating 3D medical images at a voxel level, most benchmark datasets are equipped with the annotations of only one type of organs and/or tumors, resulting in the so-called partially labeling issue. To address this issue, we propose a dynamic on-d...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 1195 - 1204
Hlavní autoři: Zhang, Jianpeng, Xie, Yutong, Xia, Yong, Shen, Chunhua
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2021
Témata:
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Due to the intensive cost of labor and expertise in annotating 3D medical images at a voxel level, most benchmark datasets are equipped with the annotations of only one type of organs and/or tumors, resulting in the so-called partially labeling issue. To address this issue, we propose a dynamic on-demand network (DoDNet) that learns to segment multiple organs and tumors on partially labeled datasets. DoD-Net consists of a shared encoder-decoder architecture, a task encoding module, a controller for dynamic filter generation, and a single but dynamic segmentation head. The information of current segmentation task is encoded as a task-aware prior to tell the model what the task is expected to achieve. Different from existing approaches which fix kernels after training, the kernels in dynamic head are generated adaptively by the controller, conditioned on both input image and assigned task. Thus, DoDNet is able to segment multiple organs and tumors, as done by multiple networks or a multi-head network, in a much efficient and flexible manner. We created a large-scale partially labeled dataset called MOTS and demonstrated the superior performance of our DoDNet over other competitors on seven organ and tumor segmentation tasks. We also transferred the weights pre-trained on MOTS to a downstream multi-organ segmentation task and achieved state-of-the-art performance. This study provides a general 3D medical image segmentation model that has been pre-trained on a large-scale partially labeled dataset and can be extended (after fine-tuning) to downstream volumetric medical data segmentation tasks. Code and models are available at: https://git.io/DoDNet
AbstractList Due to the intensive cost of labor and expertise in annotating 3D medical images at a voxel level, most benchmark datasets are equipped with the annotations of only one type of organs and/or tumors, resulting in the so-called partially labeling issue. To address this issue, we propose a dynamic on-demand network (DoDNet) that learns to segment multiple organs and tumors on partially labeled datasets. DoD-Net consists of a shared encoder-decoder architecture, a task encoding module, a controller for dynamic filter generation, and a single but dynamic segmentation head. The information of current segmentation task is encoded as a task-aware prior to tell the model what the task is expected to achieve. Different from existing approaches which fix kernels after training, the kernels in dynamic head are generated adaptively by the controller, conditioned on both input image and assigned task. Thus, DoDNet is able to segment multiple organs and tumors, as done by multiple networks or a multi-head network, in a much efficient and flexible manner. We created a large-scale partially labeled dataset called MOTS and demonstrated the superior performance of our DoDNet over other competitors on seven organ and tumor segmentation tasks. We also transferred the weights pre-trained on MOTS to a downstream multi-organ segmentation task and achieved state-of-the-art performance. This study provides a general 3D medical image segmentation model that has been pre-trained on a large-scale partially labeled dataset and can be extended (after fine-tuning) to downstream volumetric medical data segmentation tasks. Code and models are available at: https://git.io/DoDNet
Author Shen, Chunhua
Xia, Yong
Zhang, Jianpeng
Xie, Yutong
Author_xml – sequence: 1
  givenname: Jianpeng
  surname: Zhang
  fullname: Zhang, Jianpeng
  email: james.zhang@mail.nwpu.edu.cn
  organization: Northwestern Polytechnical University,School of Computer Science and Engineering,China
– sequence: 2
  givenname: Yutong
  surname: Xie
  fullname: Xie, Yutong
  email: xuyongxie@mail.nwpu.edu.cn
  organization: Northwestern Polytechnical University,School of Computer Science and Engineering,China
– sequence: 3
  givenname: Yong
  surname: Xia
  fullname: Xia, Yong
  email: yxia@nwpu.edu.cn
  organization: Northwestern Polytechnical University,School of Computer Science and Engineering,China
– sequence: 4
  givenname: Chunhua
  surname: Shen
  fullname: Shen, Chunhua
  email: chhshen@gmail.com
  organization: The University of Adelaide,Australia
BookMark eNotj8tOwkAUQEejiYB8gS7mB4p3Hp123BnAR1KFKLpxQW6nd0hNOyXtsODvNcHVWZzkJGfMLkIXiLFbATMhwN7Nv9bv2miVzSRIMQMQMj1jY2FMqnUKVp6zkQCjEmOFvWLTYfgBACWFMDYfse9Ft3ijeM8Lwj7UYcdjxz9o11KI_PXQxDpZ9TsMHEPFN4e26wfu-649uX1DfI19rLFpjrzAkhqq-AIjDhSHa3bpsRlo-s8J-3xcbubPSbF6epk_FEktQcXEK4vaOZNmzjkvtRfaElAJFo02mcm0w78Rb6wzZQmoJLrSSlkhlT4XlZqwm1O3JqLtvq9b7I9bm2Z5ZnL1C9f8Vf0
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR46437.2021.00125
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 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 Applied Sciences
EISBN 1665445092
9781665445092
EISSN 1063-6919
EndPage 1204
ExternalDocumentID 9578768
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i203t-f39a4cc657cccf24f149e0eb09a6467674ca509f69c6bb0a32acb922daebf81d3
IEDL.DBID RIE
ISICitedReferencesCount 144
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000739917301039&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 02:28:29 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-f39a4cc657cccf24f149e0eb09a6467674ca509f69c6bb0a32acb922daebf81d3
PageCount 10
ParticipantIDs ieee_primary_9578768
PublicationCentury 2000
PublicationDate 2021-June
PublicationDateYYYYMMDD 2021-06-01
PublicationDate_xml – month: 06
  year: 2021
  text: 2021-June
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.5807395
Snippet Due to the intensive cost of labor and expertise in annotating 3D medical images at a voxel level, most benchmark datasets are equipped with the annotations of...
SourceID ieee
SourceType Publisher
StartPage 1195
SubjectTerms Annotations
Encoding
Head
Image segmentation
Labeling
Task analysis
Three-dimensional displays
Title DoDNet: Learning to Segment Multi-Organ and Tumors from Multiple Partially Labeled Datasets
URI https://ieeexplore.ieee.org/document/9578768
WOSCitedRecordID wos000739917301039&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/eLvHCXMwlV3PS8MwFA7b8OBp6ib-JgePxnVpljZeN4eHMYZOGXgYSfo6BrMdayv435vXlunBi7eQQAJ5Ce_78vK9R8gtaBlrYYE5NGKY4HbATD_0mFDCGMyL65vS0pNgOg0XCzVrkLu9FgYAys9ncI_NMpYfpbbAp7KewuMlwyZpBoGstFr79xTfMRmpwlod1_dUb_g2exYYl3IskPcx5ID1sH_VUCldyLj9v8WPSPdHi0dney9zTBqQnJB2DR5pfTWzDnkfpaMp5A-0zpi6onlKX2CFs9JSZstK3SXVSUTnxUe6yyhqS6qx7catgqdIbzZfdKKN80YRHencObk865LX8eN8-MTqyglszT0_Z7GvnAGsHATW2piL2PEg8MB4SkuBKdoEVkJQsVRWGuNpn2trFOeRBhM7BOufklaSJnBGKDgIrh2M1BzJlAq1xEhmFCGTAeHbc9LBvVpuq-QYy3qbLv7uviSHaIzqr9UVaeW7Aq7Jgf3M19nuprToN750omI
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4QTfSECsbf9uDRyujKWL2CBONciKIh8UDa7o2QICNsmPjf27ct6MGLt6ZN2qSvzfu-vn7vEXINyouVMMAsGtFMcNNmuuU7TEihNebFdXVu6aAThv54LIcVcrPRwgBA_vkMbrGZx_KjxKzxqawp8Xh5_hbZbgvBnUKttXlRcS2X8aRf6uNajmx234bPAiNTlgfyFgYdsCL2ryoquRPp1_63_D5p_Kjx6HDjZw5IBRaHpFbCR1pezrRO3ntJL4TsjpY5U6c0S-gLTHFWmgttWa68pGoR0dH6I1mlFNUlxdhyblfBc6Tm8y8aKG39UUR7KrNuLksb5LV_P-oOWFk7gc2442YsdqU1gfHaHWNMzEVsmRA4oB2pPIFJ2gTWQpCxJ42ntaNcroyWnEcKdGwxrHtEqotkAceEggXhygJJxZFOSV95GMuMIuQyIFxzQuq4V5NlkR5jUm7T6d_dV2R3MHoKJsFD-HhG9tAwxc-rc1LNVmu4IDvmM5ulq8vcut9fMaWp
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+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=DoDNet%3A+Learning+to+Segment+Multi-Organ+and+Tumors+from+Multiple+Partially+Labeled+Datasets&rft.au=Zhang%2C+Jianpeng&rft.au=Xie%2C+Yutong&rft.au=Xia%2C+Yong&rft.au=Shen%2C+Chunhua&rft.date=2021-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=1195&rft.epage=1204&rft_id=info:doi/10.1109%2FCVPR46437.2021.00125&rft.externalDocID=9578768