Learning a preconditioner to accelerate compressed sensing reconstructions in MRI

Purpose To learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions. Methods A convolutional neural network (CNN) with residual connections was used to train a preconditioning operator. Training and validation data were simulated using 50% brain image...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Magnetic resonance in medicine Ročník 87; číslo 4; s. 2063 - 2073
Hlavní autori: Koolstra, Kirsten, Remis, Rob
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States Wiley Subscription Services, Inc 01.04.2022
John Wiley and Sons Inc
Predmet:
ISSN:0740-3194, 1522-2594, 1522-2594
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Purpose To learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions. Methods A convolutional neural network (CNN) with residual connections was used to train a preconditioning operator. Training and validation data were simulated using 50% brain images and 50% white Gaussian noise images. Each multichannel training example contains a simulated sampling mask, complex coil sensitivity maps, and two regularization parameter maps. The trained model was integrated in the preconditioned conjugate gradient (PCG) method as part of the split Bregman CS method. The acceleration performance was compared with that of a circulant PI‐CS preconditioner for varying undersampling factors, number of coil elements and anatomies. Results The learned preconditioner reduces the number of PCG iterations by a factor of 4, yielding a similar acceleration as an efficient circulant preconditioner. The method generalizes well to different sampling schemes, coil configurations and anatomies. Conclusion It is possible to learn adaptable preconditioners for PI and CS reconstructions that meet the performance of state‐of‐the‐art preconditioners. Further acceleration could be achieved by optimizing the network architecture and the training set. Such a preconditioner could also be integrated in fully learned reconstruction methods to accelerate the training process of unrolled networks.
AbstractList Purpose To learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions. Methods A convolutional neural network (CNN) with residual connections was used to train a preconditioning operator. Training and validation data were simulated using 50% brain images and 50% white Gaussian noise images. Each multichannel training example contains a simulated sampling mask, complex coil sensitivity maps, and two regularization parameter maps. The trained model was integrated in the preconditioned conjugate gradient (PCG) method as part of the split Bregman CS method. The acceleration performance was compared with that of a circulant PI‐CS preconditioner for varying undersampling factors, number of coil elements and anatomies. Results The learned preconditioner reduces the number of PCG iterations by a factor of 4, yielding a similar acceleration as an efficient circulant preconditioner. The method generalizes well to different sampling schemes, coil configurations and anatomies. Conclusion It is possible to learn adaptable preconditioners for PI and CS reconstructions that meet the performance of state‐of‐the‐art preconditioners. Further acceleration could be achieved by optimizing the network architecture and the training set. Such a preconditioner could also be integrated in fully learned reconstruction methods to accelerate the training process of unrolled networks.
To learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions.PURPOSETo learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions.A convolutional neural network (CNN) with residual connections was used to train a preconditioning operator. Training and validation data were simulated using 50% brain images and 50% white Gaussian noise images. Each multichannel training example contains a simulated sampling mask, complex coil sensitivity maps, and two regularization parameter maps. The trained model was integrated in the preconditioned conjugate gradient (PCG) method as part of the split Bregman CS method. The acceleration performance was compared with that of a circulant PI-CS preconditioner for varying undersampling factors, number of coil elements and anatomies.METHODSA convolutional neural network (CNN) with residual connections was used to train a preconditioning operator. Training and validation data were simulated using 50% brain images and 50% white Gaussian noise images. Each multichannel training example contains a simulated sampling mask, complex coil sensitivity maps, and two regularization parameter maps. The trained model was integrated in the preconditioned conjugate gradient (PCG) method as part of the split Bregman CS method. The acceleration performance was compared with that of a circulant PI-CS preconditioner for varying undersampling factors, number of coil elements and anatomies.The learned preconditioner reduces the number of PCG iterations by a factor of 4, yielding a similar acceleration as an efficient circulant preconditioner. The method generalizes well to different sampling schemes, coil configurations and anatomies.RESULTSThe learned preconditioner reduces the number of PCG iterations by a factor of 4, yielding a similar acceleration as an efficient circulant preconditioner. The method generalizes well to different sampling schemes, coil configurations and anatomies.It is possible to learn adaptable preconditioners for PI and CS reconstructions that meet the performance of state-of-the-art preconditioners. Further acceleration could be achieved by optimizing the network architecture and the training set. Such a preconditioner could also be integrated in fully learned reconstruction methods to accelerate the training process of unrolled networks.CONCLUSIONIt is possible to learn adaptable preconditioners for PI and CS reconstructions that meet the performance of state-of-the-art preconditioners. Further acceleration could be achieved by optimizing the network architecture and the training set. Such a preconditioner could also be integrated in fully learned reconstruction methods to accelerate the training process of unrolled networks.
PurposeTo learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions.MethodsA convolutional neural network (CNN) with residual connections was used to train a preconditioning operator. Training and validation data were simulated using 50% brain images and 50% white Gaussian noise images. Each multichannel training example contains a simulated sampling mask, complex coil sensitivity maps, and two regularization parameter maps. The trained model was integrated in the preconditioned conjugate gradient (PCG) method as part of the split Bregman CS method. The acceleration performance was compared with that of a circulant PI‐CS preconditioner for varying undersampling factors, number of coil elements and anatomies.ResultsThe learned preconditioner reduces the number of PCG iterations by a factor of 4, yielding a similar acceleration as an efficient circulant preconditioner. The method generalizes well to different sampling schemes, coil configurations and anatomies.ConclusionIt is possible to learn adaptable preconditioners for PI and CS reconstructions that meet the performance of state‐of‐the‐art preconditioners. Further acceleration could be achieved by optimizing the network architecture and the training set. Such a preconditioner could also be integrated in fully learned reconstruction methods to accelerate the training process of unrolled networks.
To learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions. A convolutional neural network (CNN) with residual connections was used to train a preconditioning operator. Training and validation data were simulated using 50% brain images and 50% white Gaussian noise images. Each multichannel training example contains a simulated sampling mask, complex coil sensitivity maps, and two regularization parameter maps. The trained model was integrated in the preconditioned conjugate gradient (PCG) method as part of the split Bregman CS method. The acceleration performance was compared with that of a circulant PI-CS preconditioner for varying undersampling factors, number of coil elements and anatomies. The learned preconditioner reduces the number of PCG iterations by a factor of 4, yielding a similar acceleration as an efficient circulant preconditioner. The method generalizes well to different sampling schemes, coil configurations and anatomies. It is possible to learn adaptable preconditioners for PI and CS reconstructions that meet the performance of state-of-the-art preconditioners. Further acceleration could be achieved by optimizing the network architecture and the training set. Such a preconditioner could also be integrated in fully learned reconstruction methods to accelerate the training process of unrolled networks.
Author Remis, Rob
Koolstra, Kirsten
AuthorAffiliation 1 Division of Image Processing Department of Radiology Leiden University Medical Center Leiden The Netherlands
2 Circuits & Systems Group Electrical Engineering Mathematics and Computer Science Faculty Delft University of Technology Delft The Netherlands
AuthorAffiliation_xml – name: 2 Circuits & Systems Group Electrical Engineering Mathematics and Computer Science Faculty Delft University of Technology Delft The Netherlands
– name: 1 Division of Image Processing Department of Radiology Leiden University Medical Center Leiden The Netherlands
Author_xml – sequence: 1
  givenname: Kirsten
  orcidid: 0000-0002-7873-1511
  surname: Koolstra
  fullname: Koolstra, Kirsten
  email: K.Koolstra@lumc.nl
  organization: Leiden University Medical Center
– sequence: 2
  givenname: Rob
  surname: Remis
  fullname: Remis, Rob
  organization: Delft University of Technology
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34752655$$D View this record in MEDLINE/PubMed
BookMark eNp1kc1v1DAQxS1URLeFA_8AisSlHNKOvxL7goQqPirtClHB2fI6k-IqsRc7oep_j7e7RVC1pznM7z3NvHdEDkIMSMhrCqcUgJ2NaTxlGlr-jCyoZKxmUosDsoBWQM2pFofkKOdrANC6FS_IIRetZI2UC_JtiTYFH64qW20Suhg6P_lin6opVtY5HDDZCSsXx7LPGbsqY8hbxR2epzS7rSJXPlSry4uX5Hlvh4yv9vOY_Pj08fv5l3r59fPF-Ydl7YTgvO4a7JQTUvM1alSu0UK1zopWIVeUaaeYttjbTlDLFUJPKdo1g3UrVQ_Q82Pyfue7mdcjdg7DlOxgNsmPNt2aaL35fxP8T3MVfxvNtAbGi8HJ3iDFXzPmyYw-l38HGzDO2ZQQG6BSCijo2wfodZxTKO8Z1jDeQAFVod78e9HfU-7TLsDZDnAp5pywN85PdhteOdAPhoLZ9mlKn-auz6J490Bxb_oYu3e_8QPePg2a1eVqp_gDWbywZA
CitedBy_id crossref_primary_10_1155_2022_9222958
Cites_doi 10.1109/TBME.2018.2821699
10.1016/j.neuroimage.2013.05.041
10.1002/mrm.27371
10.1002/mrm.27813
10.1109/ISBI.2017.7950457
10.1007/978-3-030-32248-9_3
10.1137/080725891
10.1109/TMI.2018.2833635
10.1109/TMI.2019.2954121
10.1002/mrm.27825
10.1038/nature25988
10.1002/mrm.26977
10.1002/mrm.27355
10.1109/ISBI.2011.5872579
10.1017/CBO9780511804441
10.1002/mrm.25222
10.1002/mrm.24751
10.1073/pnas.1907377117
10.1097/RLI.0b013e318271869c
10.1007/978-3-319-10404-1_18
10.1109/ISBI.2016.7493320
10.1109/EMBC.2019.8857141
10.1002/mrm.21236
10.1109/TMI.2012.2188039
10.1002/mrm.22161
10.1007/s12021-017-9354-9
10.1109/ACCESS.2020.3034287
ContentType Journal Article
Copyright 2021 The Authors. published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.
2021 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.
2021. This article is published under http://creativecommons.org/licenses/by-nc/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2021 The Authors. published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.
– notice: 2021 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.
– notice: 2021. This article is published under http://creativecommons.org/licenses/by-nc/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID 24P
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
8FD
FR3
K9.
M7Z
P64
7X8
5PM
DOI 10.1002/mrm.29073
DatabaseName Wiley Online Library Open Access
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Technology Research Database
Engineering Research Database
ProQuest Health & Medical Complete (Alumni)
Biochemistry Abstracts 1
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Biochemistry Abstracts 1
ProQuest Health & Medical Complete (Alumni)
Engineering Research Database
Technology Research Database
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
Biochemistry Abstracts 1
MEDLINE
Database_xml – sequence: 1
  dbid: 24P
  name: Wiley Online Library Open Access
  url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  sourceTypes: Publisher
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Physics
DocumentTitleAlternate KOOLSTRA et al
EISSN 1522-2594
EndPage 2073
ExternalDocumentID PMC9299023
34752655
10_1002_mrm_29073
MRM29073
Genre technicalNote
Research Support, Non-U.S. Gov't
Journal Article
GrantInformation_xml – fundername: Nederlandse Organisatie voor Wetenschappelijk Onderzoek
  funderid: HTSM 17104
– fundername: ;
  grantid: HTSM 17104
GroupedDBID ---
-DZ
.3N
.55
.GA
.Y3
05W
0R~
10A
1L6
1OB
1OC
1ZS
24P
31~
33P
3O-
3SF
3WU
4.4
4ZD
50Y
50Z
51W
51X
52M
52N
52O
52P
52R
52S
52T
52U
52V
52W
52X
53G
5GY
5RE
5VS
66C
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
930
A01
A03
AAESR
AAEVG
AAHHS
AAHQN
AAIPD
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDPE
ABEML
ABIJN
ABJNI
ABLJU
ABPVW
ABQWH
ABXGK
ACAHQ
ACBWZ
ACCFJ
ACCZN
ACFBH
ACGFO
ACGFS
ACGOF
ACIWK
ACMXC
ACPOU
ACPRK
ACRPL
ACSCC
ACXBN
ACXQS
ACYXJ
ADBBV
ADBTR
ADEOM
ADIZJ
ADKYN
ADMGS
ADNMO
ADOZA
ADXAS
ADZMN
AEEZP
AEGXH
AEIGN
AEIMD
AENEX
AEQDE
AEUQT
AEUYR
AFBPY
AFFNX
AFFPM
AFGKR
AFPWT
AFRAH
AFWVQ
AFZJQ
AHBTC
AHMBA
AIACR
AIAGR
AITYG
AIURR
AIWBW
AJBDE
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ASPBG
ATUGU
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMXJE
BROTX
BRXPI
BY8
C45
CS3
D-6
D-7
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRMAN
DRSTM
DU5
EBD
EBS
EJD
EMOBN
F00
F01
F04
FEDTE
FUBAC
G-S
G.N
GNP
GODZA
H.X
HBH
HDBZQ
HF~
HGLYW
HHY
HHZ
HVGLF
HZ~
I-F
IX1
J0M
JPC
KBYEO
KQQ
LATKE
LAW
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
M65
MEWTI
MK4
MRFUL
MRMAN
MRSTM
MSFUL
MSMAN
MSSTM
MXFUL
MXMAN
MXSTM
N04
N05
N9A
NF~
NNB
O66
O9-
OIG
OVD
P2P
P2W
P2X
P2Z
P4B
P4D
PALCI
PQQKQ
Q.N
Q11
QB0
QRW
R.K
RGB
RIWAO
RJQFR
ROL
RWI
RX1
RYL
SAMSI
SUPJJ
SV3
TEORI
TUS
TWZ
UB1
V2E
V8K
W8V
W99
WBKPD
WHWMO
WIB
WIH
WIJ
WIK
WIN
WJL
WOHZO
WQJ
WRC
WUP
WVDHM
WXI
WXSBR
X7M
XG1
XPP
XV2
ZGI
ZXP
ZZTAW
~IA
~WT
AAMMB
AAYXX
AEFGJ
AEYWJ
AGHNM
AGQPQ
AGXDD
AGYGG
AIDQK
AIDYY
AIQQE
CITATION
O8X
CGR
CUY
CVF
ECM
EIF
NPM
8FD
FR3
K9.
M7Z
P64
7X8
5PM
ID FETCH-LOGICAL-c4433-d6ed8c4593be9e8c69487ca478e38129c829aefad41a38e0f11eab20b758f00f3
IEDL.DBID 24P
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000716037000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0740-3194
1522-2594
IngestDate Tue Nov 04 01:48:05 EST 2025
Sun Nov 09 14:15:41 EST 2025
Sat Nov 29 14:38:54 EST 2025
Wed Feb 19 02:25:51 EST 2025
Sat Nov 29 06:34:33 EST 2025
Tue Nov 18 22:32:16 EST 2025
Wed Jan 22 16:26:11 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords split Bregman
deep learning
parallel imaging
compressed sensing
MR image reconstruction
preconditioning
Language English
License Attribution-NonCommercial
2021 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.
This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc/4.0/ License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c4433-d6ed8c4593be9e8c69487ca478e38129c829aefad41a38e0f11eab20b758f00f3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-7873-1511
OpenAccessLink https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmrm.29073
PMID 34752655
PQID 2623606018
PQPubID 1016391
PageCount 10
ParticipantIDs pubmedcentral_primary_oai_pubmedcentral_nih_gov_9299023
proquest_miscellaneous_2596015540
proquest_journals_2623606018
pubmed_primary_34752655
crossref_citationtrail_10_1002_mrm_29073
crossref_primary_10_1002_mrm_29073
wiley_primary_10_1002_mrm_29073_MRM29073
PublicationCentury 2000
PublicationDate April 2022
PublicationDateYYYYMMDD 2022-04-01
PublicationDate_xml – month: 04
  year: 2022
  text: April 2022
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Hoboken
PublicationTitle Magnetic resonance in medicine
PublicationTitleAlternate Magn Reson Med
PublicationYear 2022
Publisher Wiley Subscription Services, Inc
John Wiley and Sons Inc
Publisher_xml – name: Wiley Subscription Services, Inc
– name: John Wiley and Sons Inc
References 2013; 48
2009; 62
2011
2015; 73
2020; 39
2004
2018; 65
2007; 57
2012; 31
2020; 8
2019; 82
2019; 81
2018; 555
2013; 80
2019
2020; 117
2017
2016
2014; 17
2016; 29
2009; 2
2014; 71
2018; 16
2018; 37
2018; 79
e_1_2_6_10_1
e_1_2_6_19_1
e_1_2_6_13_1
e_1_2_6_14_1
e_1_2_6_11_1
e_1_2_6_12_1
e_1_2_6_17_1
e_1_2_6_18_1
e_1_2_6_15_1
e_1_2_6_16_1
e_1_2_6_21_1
e_1_2_6_20_1
e_1_2_6_9_1
e_1_2_6_8_1
Yang Y (e_1_2_6_29_1) 2016; 29
e_1_2_6_5_1
e_1_2_6_4_1
e_1_2_6_7_1
e_1_2_6_6_1
e_1_2_6_25_1
e_1_2_6_24_1
e_1_2_6_3_1
e_1_2_6_23_1
e_1_2_6_2_1
e_1_2_6_22_1
e_1_2_6_28_1
e_1_2_6_27_1
e_1_2_6_26_1
References_xml – volume: 2
  start-page: 323
  year: 2009
  end-page: 343
  article-title: The split Bregman method for L1‐regularized problems
  publication-title: SIAM J Imaging Sci
– volume: 62
  start-page: 1574
  year: 2009
  end-page: 1584
  article-title: Accelerating SENSE using compressed sensing
  publication-title: Magn Reson Med
– volume: 57
  start-page: 1086
  year: 2007
  end-page: 1098
  article-title: Undersampled radial MRI with multiple coils. Iterative image reconstruction using a total variation constraint
  publication-title: Magn Reson Med
– volume: 79
  start-page: 3055
  year: 2018
  end-page: 3071
  article-title: Learning a variational network for reconstruction of accelerated MRI data
  publication-title: Magn Reson Med
– volume: 31
  start-page: 1250
  year: 2012
  end-page: 1262
  article-title: Fast l1‐SPIRiT compressed sensing parallel imaging MRI: scalable parallel implementation and clinically feasible runtime
  publication-title: IEEE Trans Med Imaging
– volume: 73
  start-page: 1034
  year: 2015
  end-page: 1040
  article-title: Fast reconstruction for multichannel compressed sensing using a hierarchically semiseparable solver
  publication-title: Magn Reson Med
– volume: 71
  start-page: 990
  year: 2014
  end-page: 1001
  article-title: ESPIRiT‐an eigenvalue approach to autocalibrating parallel MRI: where SENSE meets GRAPPA
  publication-title: Magn Reson Med
– start-page: 1039
  year: 2011
  end-page: 1043
– volume: 8
  start-page: 204825
  year: 2020
  end-page: 204838
  article-title: An adaptive intelligence algorithm for undersampled knee MRI reconstruction
  publication-title: IEEE Access
– start-page: 21
  year: 2019
  end-page: 29
– volume: 48
  start-page: 10
  year: 2013
  end-page: 16
  article-title: Free‐breathing contrast‐enhanced multiphase MRI of the liver using a combination of compressed sensing, parallel imaging, and golden‐angle radial sampling
  publication-title: Invest Radiol
– volume: 82
  start-page: 1398
  year: 2019
  end-page: 1411
  article-title: Deep residual network for off‐resonance artifact correction with application to pediatric body MRA with 3D cones
  publication-title: Magn Reson Med
– volume: 39
  start-page: 1646
  year: 2020
  end-page: 1654
  article-title: Accelerating non‐cartesian MRI reconstruction convergence using k‐space preconditioning
  publication-title: IEEE Trans Med Imaging
– volume: 82
  start-page: 1343
  year: 2019
  end-page: 1358
  article-title: Highly accelerated multishot echo planar imaging through synergistic machine learning and joint reconstruction
  publication-title: Magn Reson Med
– volume: 65
  start-page: 1985
  year: 2018
  end-page: 1995
  article-title: Deep residual learning for accelerated MRI using magnitude and phase networks
  publication-title: IEEE Trans Biomed Eng
– volume: 81
  start-page: 116
  year: 2019
  end-page: 128
  article-title: Assessment of the generalization of learned image reconstruction and the potential for transfer learning
  publication-title: Magn Reson Med
– volume: 555
  start-page: 487
  year: 2018
  end-page: 492
  article-title: Image reconstruction by domain‐transform manifold learning
  publication-title: Nature
– volume: 117
  start-page: 30088
  year: 2020
  end-page: 300950095
  article-title: On instabilities of deep learning in image reconstruction and the potential costs of AI
  publication-title: Proc Nat Acad Sci
– volume: 17
  start-page: 138
  year: 2014
  end-page: 145
– start-page: 6818
  year: 2019
  end-page: 6821
– year: 2004
– volume: 81
  start-page: 670
  year: 2019
  end-page: 685
  article-title: Accelerating compressed sensing in parallel imaging reconstructions using an efficient circulant preconditioner for cartesian trajectories
  publication-title: Magn Reson Med
– volume: 29
  start-page: 10
  year: 2016
  end-page: 18
  article-title: Deep ADMM‐Net for compressive sensing MRI
  publication-title: Proc 30th Int Neural Inf Process Syst
– volume: 37
  start-page: 1289
  year: 2018
  end-page: 1296
  article-title: Image reconstruction is a new frontier of machine learning
  publication-title: IEEE Trans Med Imaging
– start-page: 514
  year: 2016
  end-page: 517
– volume: 16
  start-page: 425
  year: 2018
  end-page: 430
  article-title: PRIM: an efficient preconditioning iterative reweighted least squares method for parallel brain MRI reconstruction
  publication-title: Neuroinformatics
– volume: 80
  start-page: 62
  year: 2013
  end-page: 79
  article-title: The WU‐Minn human connectome project: an overview
  publication-title: NeuroImage
– start-page: 15
  year: 2017
  end-page: 18
– ident: e_1_2_6_17_1
  doi: 10.1109/TBME.2018.2821699
– ident: e_1_2_6_26_1
  doi: 10.1016/j.neuroimage.2013.05.041
– ident: e_1_2_6_9_1
  doi: 10.1002/mrm.27371
– ident: e_1_2_6_24_1
  doi: 10.1002/mrm.27813
– ident: e_1_2_6_14_1
  doi: 10.1109/ISBI.2017.7950457
– ident: e_1_2_6_23_1
  doi: 10.1007/978-3-030-32248-9_3
– ident: e_1_2_6_25_1
  doi: 10.1137/080725891
– volume: 29
  start-page: 10
  year: 2016
  ident: e_1_2_6_29_1
  article-title: Deep ADMM‐Net for compressive sensing MRI
  publication-title: Proc 30th Int Neural Inf Process Syst
– ident: e_1_2_6_15_1
  doi: 10.1109/TMI.2018.2833635
– ident: e_1_2_6_10_1
  doi: 10.1109/TMI.2019.2954121
– ident: e_1_2_6_27_1
  doi: 10.1002/mrm.27825
– ident: e_1_2_6_16_1
  doi: 10.1038/nature25988
– ident: e_1_2_6_18_1
  doi: 10.1002/mrm.26977
– ident: e_1_2_6_20_1
  doi: 10.1002/mrm.27355
– ident: e_1_2_6_5_1
  doi: 10.1109/ISBI.2011.5872579
– ident: e_1_2_6_11_1
  doi: 10.1017/CBO9780511804441
– ident: e_1_2_6_12_1
  doi: 10.1002/mrm.25222
– ident: e_1_2_6_28_1
  doi: 10.1002/mrm.24751
– ident: e_1_2_6_21_1
  doi: 10.1073/pnas.1907377117
– ident: e_1_2_6_3_1
  doi: 10.1097/RLI.0b013e318271869c
– ident: e_1_2_6_7_1
  doi: 10.1007/978-3-319-10404-1_18
– ident: e_1_2_6_13_1
  doi: 10.1109/ISBI.2016.7493320
– ident: e_1_2_6_22_1
  doi: 10.1109/EMBC.2019.8857141
– ident: e_1_2_6_4_1
  doi: 10.1002/mrm.21236
– ident: e_1_2_6_6_1
  doi: 10.1109/TMI.2012.2188039
– ident: e_1_2_6_2_1
  doi: 10.1002/mrm.22161
– ident: e_1_2_6_8_1
  doi: 10.1007/s12021-017-9354-9
– ident: e_1_2_6_19_1
  doi: 10.1109/ACCESS.2020.3034287
SSID ssj0009974
Score 2.4129205
Snippet Purpose To learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions. Methods A convolutional neural network...
To learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions. A convolutional neural network (CNN) with...
PurposeTo learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions.MethodsA convolutional neural network (CNN)...
To learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions.PURPOSETo learn a preconditioner that accelerates...
SourceID pubmedcentral
proquest
pubmed
crossref
wiley
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 2063
SubjectTerms Acceleration
Algorithms
Artificial neural networks
Brain - diagnostic imaging
compressed sensing
Computer architecture
Conditioned stimulus
deep learning
Image Processing, Computer-Assisted - methods
Image reconstruction
Magnetic resonance imaging
Magnetic Resonance Imaging - methods
Medical imaging
MR image reconstruction
Neural networks
Neural Networks, Computer
Neuroimaging
parallel imaging
Parameter sensitivity
Preconditioning
Random noise
Regularization
Sampling
split Bregman
Technical Note
Technical Notes—Computer Processing and Modeling
Training
Title Learning a preconditioner to accelerate compressed sensing reconstructions in MRI
URI https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmrm.29073
https://www.ncbi.nlm.nih.gov/pubmed/34752655
https://www.proquest.com/docview/2623606018
https://www.proquest.com/docview/2596015540
https://pubmed.ncbi.nlm.nih.gov/PMC9299023
Volume 87
WOSCitedRecordID wos000716037000001&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: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1522-2594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0009974
  issn: 0740-3194
  databaseCode: DRFUL
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
– providerCode: PRVWIB
  databaseName: Wiley Online Library Open Access
  customDbUrl:
  eissn: 1522-2594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0009974
  issn: 0740-3194
  databaseCode: WIN
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3db9MwED_tAyZeBgwGhW4yaA97CYs_UtvaE2JUm0SrUW2ib5HtuFslllbL4O_n7KQZVZmEtJcokc_KyXeXu4vPvwM4kNRlToo0sY7ZREjvEkVTm2hhBLUUc7nUxGYTcjhU47E-X4PjxVmYGh-i_eEWLCN-r4OBG1sd3YOG3tzefGKY2vF12KSUy6DSTJzfI-7qGoI5MIJ6JhawQik7aqcuO6OVCHO1UPLvADZ6oP7zR_H-ArabwJN8rjXlJaz5cge2Bs3W-g48jbWgrnoF3xvM1StiyDwmzEUDaETuZsQ4h54qAEyQUI4esccLUoU6eJwRyVtM2opMSzIYnb2Gy_7Xiy-nSdN5IXFCcJ4UPV8oJzLNrddeuZ7GvMYZIZVHD8-0U0wbPzGFoIYrn04o9QbFajH7mKTphO_CRol8vQUihCio9ZwiXTgHq9Fj6kxg1uMdUzbrwOFCBLlrYMlDd4yfeQ2ozHJcrDwuVgc-tqTzGovjX0TdhRzzxhyrnGGQ1wvIM6oDH9phNKSwO2JKP_uFNBkmcyG6SjvwphZ7-xYuZGgjgMzKJYVoCQJI9_JIOb2OYN06-HuGbB1GhXiY8XwwGsSbd_9P-h6esXAcI1YSdWEDxev34In7fTetbvejPeBVjtU-bJ6M-pff8OnH2fAPUL0RwQ
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpZ3dT9swEMBPXdmAF8Y3BTa8iYe-ZMSO09jSXiagAq2ptqqV-hY5jjsqQUAE-Ps5O2mggklIvEXKRTnl7nJ3yflngMOI6lBH3PdSzVKPR0Z7gvqpJ7niNKXYy_nKbTYR9ftiPJZ_GvBztham5EPUH9xsZLj3tQ1w-0H66IkaenV79YNhbxd8gAWObhQ2YeFk0B31nqC7sqQwW13Q1fiMLOSzo_ri-Xz0osh8OSv5vIZ1Saj7-X3qr8JKVXySX6W3rEHD5OuwGFe_19fhk5sH1cUG_K24q_-IIjeuac4qqBG5uyZKa8xWFjJB7Ei6449npLCz8HiFE6-5tAWZ5iQenG_CqHs6PD7zqt0XPM15EHhZx2RC81AGqZFG6I7E3kYrHgmDWZ5JLZhUZqIyTlUgjD-h1Cg0bYodyMT3J8EWNHPUawcI5zyjqQkoytm1sBKzpgw5dj5GM5GGLWjPbJDoCk1ud8i4TEqoMkvwYSXuYbXgey16U_I4XhPanxkyqUKySBgWeh1LnxEt-FafxmCyf0hUbq7vUSbEhs5WWH4Ltku713cJeGS3EkBlozmPqAUsqHv-TD69cMBuaXM-Q7XaziP-r3gSD2J3sPt20QNYOhvGvaR33v-9B8vMLs9wk0X70ERTmy_wUT_cTYvbr1V4PAIJJBOn
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpZ3dT9swEMBPwDbEy8bYgG58GMQDL6Gxc2lsaS_TtgrEWhUEEm-R4zijEqRVw_b37-ykYRWbNIm3SDkrp5wvdxeffwY4SriJTYJhkBmRBZhYE0geZoFCjTzjVMuF2h82kQyH8uZGjZbg03wvTM2HaH-4Oc_w32vn4HaaF91Hauj97P5EUG0XLcMLjOkb67jOOHpE7qqawew0oYmGc65QKLrt0MVo9CTFfNop-WcG60NQ_83zlF-H103qyT7Xc-UtLNlyA1YHzeL6Brzy3aCmegcXDXX1B9Ns6kvmvEEasYcJ08ZQrHKICeYa0j19PGeV64SnEV68pdJWbFyyweXZe7juf7v6cho0Zy8EBjGKgrxnc2kwVlFmlZWmp6iyMRoTaSnGC2WkUNoWOkeuI2nDgnOrybAZ1R9FGBbRJqyUpNc2METMeWYjTnJuJ6yimKlipLrHGiGzuAPHcxukpgGTu_Mx7tIaqSxSelmpf1kdOGxFpzWN429CO3NDpo1DVqmgNK_n2DOyAwftbXIltz6iSzv5STIxlXMuvwo7sFXbvX1KhIk7SICUTRZmRCvgMN2Ld8rxrcd1KxfxBal17GfEvxVPB5cDf_Hh_0X3YXX0tZ9-Pxuef4Q14fZm-LaiHVghS9tdeGl-PYyr2Z73jd-a3BGQ
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=Learning+a+preconditioner+to+accelerate+compressed+sensing+reconstructions+in+MRI&rft.jtitle=Magnetic+resonance+in+medicine&rft.au=Koolstra%2C+Kirsten&rft.au=Remis%2C+Rob&rft.date=2022-04-01&rft.issn=0740-3194&rft.eissn=1522-2594&rft.volume=87&rft.issue=4&rft.spage=2063&rft.epage=2073&rft_id=info:doi/10.1002%2Fmrm.29073&rft.externalDBID=10.1002%252Fmrm.29073&rft.externalDocID=MRM29073
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0740-3194&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0740-3194&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0740-3194&client=summon