CLAIRE: A DISTRIBUTED-MEMORY SOLVER FOR CONSTRAINED LARGE DEFORMATION DIFFEOMORPHIC IMAGE REGISTRATION

With this work we release CLAIRE, a distributed-memory implementation of an effective solver for constrained large deformation diifeomorphic image registration problems in three dimensions. We consider an optimal control formulation. We invert for a stationary velocity field that parameterizes the d...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:SIAM journal on scientific computing Ročník 41; číslo 5; s. C548
Hlavní autoři: Mang, Andreas, Gholami, Amir, Davatzikos, Christos, Biros, George
Médium: Journal Article
Jazyk:angličtina
Vydáno: 01.01.2019
ISSN:1064-8275
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract With this work we release CLAIRE, a distributed-memory implementation of an effective solver for constrained large deformation diifeomorphic image registration problems in three dimensions. We consider an optimal control formulation. We invert for a stationary velocity field that parameterizes the deformation map. Our solver is based on a globalized, preconditioned, inexact reduced space Gauss‒Newton‒Krylov scheme. We exploit state-of-the-art techniques in scientific computing to develop an eifective solver that scales to thousands of distributed memory nodes on high-end clusters. We present the formulation, discuss algorithmic features, describe the software package, and introduce an improved preconditioner for the reduced space Hessian to speed up the convergence of our solver. We test registration performance on synthetic and real data. We Demonstrate registration accuracy on several neuroimaging datasets. We compare the performance of our scheme against diiferent flavors of the Demons algorithm for diifeomorphic image registration. We study convergence of our preconditioner and our overall algorithm. We report scalability results on state-of-the-art supercomputing platforms. We Demonstrate that we can solve registration problems for clinically relevant data sizes in two to four minutes on a standard compute node with 20 cores, attaining excellent data fidelity. With the present work we achieve a speedup of (on average) 5× with a peak performance of up to 17× compared to our former work.With this work we release CLAIRE, a distributed-memory implementation of an effective solver for constrained large deformation diifeomorphic image registration problems in three dimensions. We consider an optimal control formulation. We invert for a stationary velocity field that parameterizes the deformation map. Our solver is based on a globalized, preconditioned, inexact reduced space Gauss‒Newton‒Krylov scheme. We exploit state-of-the-art techniques in scientific computing to develop an eifective solver that scales to thousands of distributed memory nodes on high-end clusters. We present the formulation, discuss algorithmic features, describe the software package, and introduce an improved preconditioner for the reduced space Hessian to speed up the convergence of our solver. We test registration performance on synthetic and real data. We Demonstrate registration accuracy on several neuroimaging datasets. We compare the performance of our scheme against diiferent flavors of the Demons algorithm for diifeomorphic image registration. We study convergence of our preconditioner and our overall algorithm. We report scalability results on state-of-the-art supercomputing platforms. We Demonstrate that we can solve registration problems for clinically relevant data sizes in two to four minutes on a standard compute node with 20 cores, attaining excellent data fidelity. With the present work we achieve a speedup of (on average) 5× with a peak performance of up to 17× compared to our former work.
AbstractList With this work we release CLAIRE, a distributed-memory implementation of an effective solver for constrained large deformation diifeomorphic image registration problems in three dimensions. We consider an optimal control formulation. We invert for a stationary velocity field that parameterizes the deformation map. Our solver is based on a globalized, preconditioned, inexact reduced space Gauss‒Newton‒Krylov scheme. We exploit state-of-the-art techniques in scientific computing to develop an eifective solver that scales to thousands of distributed memory nodes on high-end clusters. We present the formulation, discuss algorithmic features, describe the software package, and introduce an improved preconditioner for the reduced space Hessian to speed up the convergence of our solver. We test registration performance on synthetic and real data. We Demonstrate registration accuracy on several neuroimaging datasets. We compare the performance of our scheme against diiferent flavors of the Demons algorithm for diifeomorphic image registration. We study convergence of our preconditioner and our overall algorithm. We report scalability results on state-of-the-art supercomputing platforms. We Demonstrate that we can solve registration problems for clinically relevant data sizes in two to four minutes on a standard compute node with 20 cores, attaining excellent data fidelity. With the present work we achieve a speedup of (on average) 5× with a peak performance of up to 17× compared to our former work.With this work we release CLAIRE, a distributed-memory implementation of an effective solver for constrained large deformation diifeomorphic image registration problems in three dimensions. We consider an optimal control formulation. We invert for a stationary velocity field that parameterizes the deformation map. Our solver is based on a globalized, preconditioned, inexact reduced space Gauss‒Newton‒Krylov scheme. We exploit state-of-the-art techniques in scientific computing to develop an eifective solver that scales to thousands of distributed memory nodes on high-end clusters. We present the formulation, discuss algorithmic features, describe the software package, and introduce an improved preconditioner for the reduced space Hessian to speed up the convergence of our solver. We test registration performance on synthetic and real data. We Demonstrate registration accuracy on several neuroimaging datasets. We compare the performance of our scheme against diiferent flavors of the Demons algorithm for diifeomorphic image registration. We study convergence of our preconditioner and our overall algorithm. We report scalability results on state-of-the-art supercomputing platforms. We Demonstrate that we can solve registration problems for clinically relevant data sizes in two to four minutes on a standard compute node with 20 cores, attaining excellent data fidelity. With the present work we achieve a speedup of (on average) 5× with a peak performance of up to 17× compared to our former work.
Author Davatzikos, Christos
Mang, Andreas
Biros, George
Gholami, Amir
Author_xml – sequence: 1
  givenname: Andreas
  surname: Mang
  fullname: Mang, Andreas
– sequence: 2
  givenname: Amir
  surname: Gholami
  fullname: Gholami, Amir
– sequence: 3
  givenname: Christos
  surname: Davatzikos
  fullname: Davatzikos, Christos
– sequence: 4
  givenname: George
  surname: Biros
  fullname: Biros, George
BookMark eNotjMtOwzAURL0oEm1hwxd4ySbgexMnDjuTOKmlpEZuisSqShxXAvUBpP3_hsdqpJk5Z0Ymh-PBE3IH7AEgTB5B7AFZIkBMyBRYHAUCE35NZsPwwRjEUYpTss0qqa16opLmetVY_bxuVB7Uqjb2ja5M9aosLYylmVmOs9RLldNK2lLRXI19LRttliNbFMqMzMtCZ1TXctytKn-Mv4cbcrVtd4O__c85WReqyRZBZUqdySpwYRSfgtbzqI866CIfIjCPLN2mCM6JjsfAQWCPXR_ymDF0LhEcXNx5aEWPfRsKwDm5__N-fh-_zn44bfbvg_O7XXvwx_OwQS5QsCRMU7wAnURP4A
CitedBy_id crossref_primary_10_1016_j_jcp_2023_112463
crossref_primary_10_1137_19M1275280
crossref_primary_10_1137_23M1570727
crossref_primary_10_3390_s22103735
crossref_primary_10_1109_TMI_2020_3024264
crossref_primary_10_1146_annurev_bioeng_062117_121105
crossref_primary_10_1016_j_media_2023_102917
crossref_primary_10_1109_TPDS_2022_3218898
crossref_primary_10_1016_j_jpdc_2020_11_006
crossref_primary_10_1016_j_media_2025_103577
crossref_primary_10_3390_math13172807
crossref_primary_10_1007_s10851_024_01211_z
crossref_primary_10_1016_j_media_2025_103757
crossref_primary_10_1007_s10851_021_01016_4
crossref_primary_10_3390_jimaging8090251
crossref_primary_10_3390_mca27020022
crossref_primary_10_1007_s10957_020_01789_5
crossref_primary_10_1111_str_12412
ContentType Journal Article
DBID 7X8
DOI 10.1137/18m1207818
DatabaseName MEDLINE - Academic
DatabaseTitle MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
Database_xml – sequence: 1
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Applied Sciences
Mathematics
GroupedDBID -~X
.4S
123
4.4
7X8
AALVN
ABKAD
ABMZU
ACBEA
ACGFO
ACGOD
ACIWK
ACPRK
AENEX
AFFNX
AFRAH
ALMA_UNASSIGNED_HOLDINGS
ANXRF
CS3
D0L
DU5
EBS
EDO
EJD
EST
F5P
H13
H~9
P1Q
RJG
RSI
TAE
TN5
YNT
ID FETCH-LOGICAL-c346t-ae54d4b1b4e3210e209f921cc8b5615182d2bd356002cc7851c6be1a8d2da3812
IEDL.DBID 7X8
ISICitedReferencesCount 18
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000493897100045&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1064-8275
IngestDate Sun Nov 09 09:45:19 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 5
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c346t-ae54d4b1b4e3210e209f921cc8b5615182d2bd356002cc7851c6be1a8d2da3812
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PQID 2582807399
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2582807399
PublicationCentury 2000
PublicationDate 20190101
PublicationDateYYYYMMDD 2019-01-01
PublicationDate_xml – month: 01
  year: 2019
  text: 20190101
  day: 01
PublicationDecade 2010
PublicationTitle SIAM journal on scientific computing
PublicationYear 2019
SSID ssj0016492
Score 2.4164646
Snippet With this work we release CLAIRE, a distributed-memory implementation of an effective solver for constrained large deformation diifeomorphic image registration...
SourceID proquest
SourceType Aggregation Database
StartPage C548
Title CLAIRE: A DISTRIBUTED-MEMORY SOLVER FOR CONSTRAINED LARGE DEFORMATION DIFFEOMORPHIC IMAGE REGISTRATION
URI https://www.proquest.com/docview/2582807399
Volume 41
WOSCitedRecordID wos000493897100045&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV05T8MwFLaAMsBAoYC4ZSTWqNhxLhYUUqeNlKNKW1SmKrEdiYEWSOH3Y6eGDixIrPGhyHnH997nvAfADbYqQTDhhipmbhBWSJVStyxkvIxL6dEcVDTV9WMnTd3p1BvqhFutr1V-28TGUPMFUznyLlb8jqKVvPvXN0N1jVLsqm6hsQlapoQySqqd6ZpFsIm3YjttYrjYsXR5UmQ6XeS-IKwK3bi_jHDjWcL2f99pH-xpTAn9lRAcgA0x74C2xpdQa2_dAbvJT43W-hBUQexHOb2DPuxFo3EePUykFTMSmmT5Exxl8SPNoYwRYZClqrNylNIejP28T2GPyudJk92Sa8OQZnLNcBAFMEp8OZ7TvtqxmXAEJiEdBwNDd10wmEnspVEIi3BSopII9X-PwLde5WHEmFtaCv64mOOSmwopYcYcidiYXQpUuBzzQvp_fAy25ou5OAFQEO5WDiorVHnElF-jCTe5zUklFNI5Bdff5zqTUq2oimIuFh_1bH2yZ3-Ycw52JI7xVpmRC9CqpOaKS7DNPpfP9ftVIxRf3EC3EA
linkProvider ProQuest
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=CLAIRE%3A+A+DISTRIBUTED-MEMORY+SOLVER+FOR+CONSTRAINED+LARGE+DEFORMATION+DIFFEOMORPHIC+IMAGE+REGISTRATION&rft.jtitle=SIAM+journal+on+scientific+computing&rft.au=Mang%2C+Andreas&rft.au=Gholami%2C+Amir&rft.au=Davatzikos%2C+Christos&rft.au=Biros%2C+George&rft.date=2019-01-01&rft.issn=1064-8275&rft.volume=41&rft.issue=5&rft.spage=C548&rft_id=info:doi/10.1137%2F18m1207818&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1064-8275&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1064-8275&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1064-8275&client=summon