TMS-Net: A Segmentation Network Coupled With A Run-time Quality Control Method For Robust Cardiac Image Segmentation
Recently, deep networks have shown impressive performance for the segmentation of cardiac Magnetic Resonance Imaging (MRI) images. However, their achievement is proving slow to transition to widespread use in medical clinics because of robustness issues leading to low trust of clinicians to their re...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , |
Format | Paper Journal Article |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
21.12.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Recently, deep networks have shown impressive performance for the segmentation of cardiac Magnetic Resonance Imaging (MRI) images. However, their achievement is proving slow to transition to widespread use in medical clinics because of robustness issues leading to low trust of clinicians to their results. Predicting run-time quality of segmentation masks can be useful to warn clinicians against poor results. Despite its importance, there are few studies on this problem. To address this gap, we propose a quality control method based on the agreement across decoders of a multi-view network, TMS-Net, measured by the cosine similarity. The network takes three view inputs resliced from the same 3D image along different axes. Different from previous multi-view networks, TMS-Net has a single encoder and three decoders, leading to better noise robustness, segmentation performance and run-time quality estimation in our experiments on the segmentation of the left atrium on STACOM 2013 and STACOM 2018 challenge datasets. We also present a way to generate poor segmentation masks by using noisy images generated with engineered noise and Rician noise to simulate undertraining, high anisotropy and poor imaging settings problems. Our run-time quality estimation method show a good classification of poor and good quality segmentation masks with an AUC reaching to 0.97 on STACOM 2018. We believe that TMS-Net and our run-time quality estimation method has a high potential to increase the thrust of clinicians to automatic image analysis tools. |
---|---|
AbstractList | Computers in Biology and Medicine (2022): 106422 Recently, deep networks have shown impressive performance for the
segmentation of cardiac Magnetic Resonance Imaging (MRI) images. However, their
achievement is proving slow to transition to widespread use in medical clinics
because of robustness issues leading to low trust of clinicians to their
results. Predicting run-time quality of segmentation masks can be useful to
warn clinicians against poor results. Despite its importance, there are few
studies on this problem. To address this gap, we propose a quality control
method based on the agreement across decoders of a multi-view network, TMS-Net,
measured by the cosine similarity. The network takes three view inputs resliced
from the same 3D image along different axes. Different from previous multi-view
networks, TMS-Net has a single encoder and three decoders, leading to better
noise robustness, segmentation performance and run-time quality estimation in
our experiments on the segmentation of the left atrium on STACOM 2013 and
STACOM 2018 challenge datasets. We also present a way to generate poor
segmentation masks by using noisy images generated with engineered noise and
Rician noise to simulate undertraining, high anisotropy and poor imaging
settings problems. Our run-time quality estimation method show a good
classification of poor and good quality segmentation masks with an AUC reaching
to 0.97 on STACOM 2018. We believe that TMS-Net and our run-time quality
estimation method has a high potential to increase the thrust of clinicians to
automatic image analysis tools. Recently, deep networks have shown impressive performance for the segmentation of cardiac Magnetic Resonance Imaging (MRI) images. However, their achievement is proving slow to transition to widespread use in medical clinics because of robustness issues leading to low trust of clinicians to their results. Predicting run-time quality of segmentation masks can be useful to warn clinicians against poor results. Despite its importance, there are few studies on this problem. To address this gap, we propose a quality control method based on the agreement across decoders of a multi-view network, TMS-Net, measured by the cosine similarity. The network takes three view inputs resliced from the same 3D image along different axes. Different from previous multi-view networks, TMS-Net has a single encoder and three decoders, leading to better noise robustness, segmentation performance and run-time quality estimation in our experiments on the segmentation of the left atrium on STACOM 2013 and STACOM 2018 challenge datasets. We also present a way to generate poor segmentation masks by using noisy images generated with engineered noise and Rician noise to simulate undertraining, high anisotropy and poor imaging settings problems. Our run-time quality estimation method show a good classification of poor and good quality segmentation masks with an AUC reaching to 0.97 on STACOM 2018. We believe that TMS-Net and our run-time quality estimation method has a high potential to increase the thrust of clinicians to automatic image analysis tools. |
Author | Bharath, Anil A Uslu, Fatmatulzehra |
Author_xml | – sequence: 1 givenname: Fatmatulzehra surname: Uslu fullname: Uslu, Fatmatulzehra – sequence: 2 givenname: Anil surname: Bharath middlename: A fullname: Bharath, Anil A |
BackLink | https://doi.org/10.1016/j.compbiomed.2022.106422$$DView published paper (Access to full text may be restricted) https://doi.org/10.48550/arXiv.2212.10877$$DView paper in arXiv |
BookMark | eNpVkF1PwjAUhhujiYj8AK9s4vWwH3Qt3pFFlAQ0AomXy2FrYbi12HUo_94J3pic5CTnffLm5LlC59ZZjdANJf2BEoLcg_8u9n3GKOtToqQ8Qx3GOY3UgLFL1KvrLSGExZIJwTsoLGeL6EWHBzzCC72utA0QCmdxe_ty_gMnrtmVOsfvRdi0zLyxUSgqjd8aKItwaHMbvCvxTIeNy_HYeTx3q6YOOAGfF5DhSQVr_a_8Gl0YKGvd-9tdtBw_LpPnaPr6NElG0wgEG0ZUcRCZMYwwDYbGktBc0hWTKo-pMLGQOpNAjaBaAvAcJBkYNVRZxjkRQHgX3Z5qj0rSnS8q8If0V016VNMSdydi591no-uQbl3jbftTyqSIlWxnyH8AHN9oIg |
ContentType | Paper Journal Article |
Copyright | 2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
Copyright_xml | – notice: 2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS AKY GOX |
DOI | 10.48550/arxiv.2212.10877 |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Database (Proquest) ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection arXiv Computer Science arXiv.org |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: GOX name: arXiv.org url: http://arxiv.org/find sourceTypes: Open Access Repository – sequence: 2 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
ExternalDocumentID | 2212_10877 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS AKY GOX |
ID | FETCH-LOGICAL-a529-183a5cff202eaf16701d71b278d615f657ec7a1f51e7aa3da704f898cc3305a03 |
IEDL.DBID | 8FG |
IngestDate | Mon Jan 08 05:42:46 EST 2024 Fri Sep 13 06:44:28 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-a529-183a5cff202eaf16701d71b278d615f657ec7a1f51e7aa3da704f898cc3305a03 |
OpenAccessLink | https://www.proquest.com/docview/2756876879/abstract/?pq-origsite=%requestingapplication% |
PQID | 2756876879 |
PQPubID | 2050157 |
ParticipantIDs | arxiv_primary_2212_10877 proquest_journals_2756876879 |
PublicationCentury | 2000 |
PublicationDate | 20221221 2022-12-21 |
PublicationDateYYYYMMDD | 2022-12-21 |
PublicationDate_xml | – month: 12 year: 2022 text: 20221221 day: 21 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2022 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 1.8617116 |
SecondaryResourceType | preprint |
Snippet | Recently, deep networks have shown impressive performance for the segmentation of cardiac Magnetic Resonance Imaging (MRI) images. However, their achievement... Computers in Biology and Medicine (2022): 106422 Recently, deep networks have shown impressive performance for the segmentation of cardiac Magnetic Resonance... |
SourceID | arxiv proquest |
SourceType | Open Access Repository Aggregation Database |
SubjectTerms | Anisotropy Atria Coders Computer Science - Computer Vision and Pattern Recognition Control methods Decoders Image analysis Image quality Image segmentation Magnetic resonance imaging Masks Medical imaging Quality control Robust control |
SummonAdditionalLinks | – databaseName: arXiv.org dbid: GOX link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwdV3fS8MwEA7bnnwRRWXTKffga7BJfyT1bRTrFDZhm7i3kraJDlw7tlb0vzdJO0TEtxAuebjL3X2Qu-8QuuZSg3yVelhDBYE95npYcBVgrnJXA2wleGganCfTYPzsPS79ZQfBvhdGbD9XHw0_cLq7oTqwmio4xrqoS6kp2bp_Wjafk5aKq5X_kdMY0279Ca02X8RH6LAFejBqLHOMOrI4QdViMsdTWd3CCObydd02_hQwbaqxISrrzbvM4WVVvWmZWV1gM_0dGqqLL4iaynKY2MHPEJdbmJVpvasgsqbO4GGtI8Svy0_RIr5bRGPczj3Awqch1k4m_Ewp6lApFAmYQ3JGUsp4ruGHCnwmMyaI8olkQri5YI6neMizzNXOKxz3DPWKspB9BKlgmXSpw81nqadTj-NIX3GPpEFg1gPUt9pKNg21RWIUmVhFDtBwr8Ckfda7xHDF6_DJWXj-_8kLdEBNjwChmJIh6lXbWl7qzF2lV9Z834Pjl7Y priority: 102 providerName: Cornell University |
Title | TMS-Net: A Segmentation Network Coupled With A Run-time Quality Control Method For Robust Cardiac Image Segmentation |
URI | https://www.proquest.com/docview/2756876879/abstract/ https://arxiv.org/abs/2212.10877 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dT8IwEG8QYuKbn0FF0gdfK2v30eKLUcKHJiABjLwtXdcqiWwIm9EX_3bbDjTGxJelW5c9XHe_u9zd7w6Acya1k68iD2lXgSOPuh7iTAWIqdjVDrbirGkIzv1B0Hvw7qb-tAR6Gy6MKavcYKIF6jgVJkbeMG3KteYy2mzwyEQBRNa4WrwiMz_K5FnXwzS2QAWbnniGM97pfkdbSEC17-wWaU3bxKvBl--ztwuiodvU2VFtnir20R9QtpamswsqQ76Qyz1Qksk-2LYFmmJ1ALJJf4wGMruE13Asn-ZrylACB0UdN2yl-eJFxvBxlj3rd0Z5gszceFg0yfiAraImHfbtyGjYSZdwlEb5KoMt-5MIeDvX2PLr44dg0mlPWj20npiAuE-aSKsn94VSxCGSKxxQB8cUR4SyWDsuKvCpFJRj5WNJOXdjTh1PsSYTwtVqzx33CJSTNJFVACNOhXSJw0ya1dNGy3Gkr5iHoyAw62NQtdIKF0VTjNAIMrSCPAa1jQDDtUKswp_jO_l_-xTsEMMwwAQRXAPlbJnLM233s6huj7QOKjftwXCk77r3U33tf7a_APkcsBw |
link.rule.ids | 228,230,786,790,891,12792,21416,27958,33408,33779,43635,43840 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1bT4MwFG50i9E3r3E6tQ--1kG5tPPFmMW56SBmm3FvpECrSxwgA6P_3rYwjTHxjQDh4ZTzfSfn9gFwTrkM8kVoIxkqMGQTy0aMChdREVsywBaMdtWAs-e7g0f7bubM6oTbsm6rXGGiBuo4jVSOvKPWlEvPpaR7lb0hpRqlqqu1hMY6aNqWpE41Kd6__c6xYJfIiNmqipl6dVeH5R_z9wssAVt11xFJSk196w8Ua37pb4PmA8t4vgPWeLILNnRbZrTcA8XUmyCfF5fwGk7486IeFEqgX3Vvw15aZq88hk_z4kW-My4TpNTiYbUa4xP2qk506GmhaNhPczhOw3JZwJ7-NSI4XEhE-fXxfTDt30x7A1TrJCDm4C6STsmcSAhsYM6E6RLDjIkZYkJjGa4I1yE8IswUjskJY1bMiGEL2qVRZElnZ4Z1ABpJmvBDAENGIm5hg6riqi2pyjC4I6hthq6rrlvgUFsryKpVGIEyZKAN2QLtlQGD2g2Wwc-hHf3_-AxsDqbeKBgN_ftjsIXVjIGJETbboFHkJT-RzF-Ep_p4vwD0Dqtw |
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=TMS-Net%3A+A+Segmentation+Network+Coupled+With+A+Run-time+Quality+Control+Method+For+Robust+Cardiac+Image+Segmentation&rft.jtitle=arXiv.org&rft.au=Uslu%2C+Fatmatulzehra&rft.au=Bharath%2C+Anil+A&rft.date=2022-12-21&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422&rft_id=info:doi/10.48550%2Farxiv.2212.10877 |