Reconstruction of undersampled 3D non‐Cartesian image‐based navigators for coronary MRA using an unrolled deep learning model

Purpose To rapidly reconstruct undersampled 3D non‐Cartesian image‐based navigators (iNAVs) using an unrolled deep learning (DL) model, enabling nonrigid motion correction in coronary magnetic resonance angiography (CMRA). Methods An end‐to‐end unrolled network is trained to reconstruct beat‐to‐beat...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Magnetic resonance in medicine Ročník 84; číslo 2; s. 800 - 812
Hlavní autori:	Malavé, Mario O., Baron, Corey A., Koundinyan, Srivathsan P., Sandino, Christopher M., Ong, Frank, Cheng, Joseph Y., Nishimura, Dwight G.
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States Wiley Subscription Services, Inc 01.08.2020
Predmet:	3D cones trajectory Algorithms Angiography Artificial neural networks Cartesian coordinates Computer architecture Cones convolutional neural networks Coronary Angiography coronary MRA Deep Learning Heart Humans Image processing Image quality Image reconstruction Imaging, Three-Dimensional Machine learning Magnetic resonance Magnetic Resonance Angiography Model accuracy Navigators Neural networks non‐Cartesian Regularization Three dimensional models non-Cartesian 3D cones trajectory convolutional neural networks coronary MRA
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 rapidly reconstruct undersampled 3D non‐Cartesian image‐based navigators (iNAVs) using an unrolled deep learning (DL) model, enabling nonrigid motion correction in coronary magnetic resonance angiography (CMRA). Methods An end‐to‐end unrolled network is trained to reconstruct beat‐to‐beat 3D iNAVs acquired during a CMRA sequence. The unrolled model incorporates a nonuniform FFT operator in TensorFlow to perform the data‐consistency operation, and the regularization term is learned by a convolutional neural network (CNN) based on the proximal gradient descent algorithm. The training set includes 6,000 3D iNAVs acquired from 7 different subjects and 11 scans using a variable‐density (VD) cones trajectory. For testing, 3D iNAVs from 4 additional subjects are reconstructed using the unrolled model. To validate reconstruction accuracy, global and localized motion estimates from DL model‐based 3D iNAVs are compared with those extracted from 3D iNAVs reconstructed with l1‐ESPIRiT. Then, the high‐resolution coronary MRA images motion corrected with autofocusing using the l1‐ESPIRiT and DL model‐based 3D iNAVs are assessed for differences. Results 3D iNAVs reconstructed using the DL model‐based approach and conventional l1‐ESPIRiT generate similar global and localized motion estimates and provide equivalent coronary image quality. Reconstruction with the unrolled network completes in a fraction of the time compared to CPU and GPU implementations of l1‐ESPIRiT (20× and 3× speed increases, respectively). Conclusions We have developed a deep neural network architecture to reconstruct undersampled 3D non‐Cartesian VD cones iNAVs. Our approach decreases reconstruction time for 3D iNAVs, while preserving the accuracy of nonrigid motion information offered by them for correction.
AbstractList	PurposeTo rapidly reconstruct undersampled 3D non‐Cartesian image‐based navigators (iNAVs) using an unrolled deep learning (DL) model, enabling nonrigid motion correction in coronary magnetic resonance angiography (CMRA).MethodsAn end‐to‐end unrolled network is trained to reconstruct beat‐to‐beat 3D iNAVs acquired during a CMRA sequence. The unrolled model incorporates a nonuniform FFT operator in TensorFlow to perform the data‐consistency operation, and the regularization term is learned by a convolutional neural network (CNN) based on the proximal gradient descent algorithm. The training set includes 6,000 3D iNAVs acquired from 7 different subjects and 11 scans using a variable‐density (VD) cones trajectory. For testing, 3D iNAVs from 4 additional subjects are reconstructed using the unrolled model. To validate reconstruction accuracy, global and localized motion estimates from DL model‐based 3D iNAVs are compared with those extracted from 3D iNAVs reconstructed with l1‐ESPIRiT. Then, the high‐resolution coronary MRA images motion corrected with autofocusing using the l1‐ESPIRiT and DL model‐based 3D iNAVs are assessed for differences.Results3D iNAVs reconstructed using the DL model‐based approach and conventional l1‐ESPIRiT generate similar global and localized motion estimates and provide equivalent coronary image quality. Reconstruction with the unrolled network completes in a fraction of the time compared to CPU and GPU implementations of l1‐ESPIRiT (20× and 3× speed increases, respectively).ConclusionsWe have developed a deep neural network architecture to reconstruct undersampled 3D non‐Cartesian VD cones iNAVs. Our approach decreases reconstruction time for 3D iNAVs, while preserving the accuracy of nonrigid motion information offered by them for correction. Purpose To rapidly reconstruct undersampled 3D non‐Cartesian image‐based navigators (iNAVs) using an unrolled deep learning (DL) model, enabling nonrigid motion correction in coronary magnetic resonance angiography (CMRA). Methods An end‐to‐end unrolled network is trained to reconstruct beat‐to‐beat 3D iNAVs acquired during a CMRA sequence. The unrolled model incorporates a nonuniform FFT operator in TensorFlow to perform the data‐consistency operation, and the regularization term is learned by a convolutional neural network (CNN) based on the proximal gradient descent algorithm. The training set includes 6,000 3D iNAVs acquired from 7 different subjects and 11 scans using a variable‐density (VD) cones trajectory. For testing, 3D iNAVs from 4 additional subjects are reconstructed using the unrolled model. To validate reconstruction accuracy, global and localized motion estimates from DL model‐based 3D iNAVs are compared with those extracted from 3D iNAVs reconstructed with l1‐ESPIRiT. Then, the high‐resolution coronary MRA images motion corrected with autofocusing using the l1‐ESPIRiT and DL model‐based 3D iNAVs are assessed for differences. Results 3D iNAVs reconstructed using the DL model‐based approach and conventional l1‐ESPIRiT generate similar global and localized motion estimates and provide equivalent coronary image quality. Reconstruction with the unrolled network completes in a fraction of the time compared to CPU and GPU implementations of l1‐ESPIRiT (20× and 3× speed increases, respectively). Conclusions We have developed a deep neural network architecture to reconstruct undersampled 3D non‐Cartesian VD cones iNAVs. Our approach decreases reconstruction time for 3D iNAVs, while preserving the accuracy of nonrigid motion information offered by them for correction. To rapidly reconstruct undersampled 3D non-Cartesian image-based navigators (iNAVs) using an unrolled deep learning (DL) model, enabling nonrigid motion correction in coronary magnetic resonance angiography (CMRA). An end-to-end unrolled network is trained to reconstruct beat-to-beat 3D iNAVs acquired during a CMRA sequence. The unrolled model incorporates a nonuniform FFT operator in TensorFlow to perform the data-consistency operation, and the regularization term is learned by a convolutional neural network (CNN) based on the proximal gradient descent algorithm. The training set includes 6,000 3D iNAVs acquired from 7 different subjects and 11 scans using a variable-density (VD) cones trajectory. For testing, 3D iNAVs from 4 additional subjects are reconstructed using the unrolled model. To validate reconstruction accuracy, global and localized motion estimates from DL model-based 3D iNAVs are compared with those extracted from 3D iNAVs reconstructed with -ESPIRiT. Then, the high-resolution coronary MRA images motion corrected with autofocusing using the -ESPIRiT and DL model-based 3D iNAVs are assessed for differences. 3D iNAVs reconstructed using the DL model-based approach and conventional -ESPIRiT generate similar global and localized motion estimates and provide equivalent coronary image quality. Reconstruction with the unrolled network completes in a fraction of the time compared to CPU and GPU implementations of -ESPIRiT (20× and 3× speed increases, respectively). We have developed a deep neural network architecture to reconstruct undersampled 3D non-Cartesian VD cones iNAVs. Our approach decreases reconstruction time for 3D iNAVs, while preserving the accuracy of nonrigid motion information offered by them for correction. To rapidly reconstruct undersampled 3D non-Cartesian image-based navigators (iNAVs) using an unrolled deep learning (DL) model, enabling nonrigid motion correction in coronary magnetic resonance angiography (CMRA).PURPOSETo rapidly reconstruct undersampled 3D non-Cartesian image-based navigators (iNAVs) using an unrolled deep learning (DL) model, enabling nonrigid motion correction in coronary magnetic resonance angiography (CMRA).An end-to-end unrolled network is trained to reconstruct beat-to-beat 3D iNAVs acquired during a CMRA sequence. The unrolled model incorporates a nonuniform FFT operator in TensorFlow to perform the data-consistency operation, and the regularization term is learned by a convolutional neural network (CNN) based on the proximal gradient descent algorithm. The training set includes 6,000 3D iNAVs acquired from 7 different subjects and 11 scans using a variable-density (VD) cones trajectory. For testing, 3D iNAVs from 4 additional subjects are reconstructed using the unrolled model. To validate reconstruction accuracy, global and localized motion estimates from DL model-based 3D iNAVs are compared with those extracted from 3D iNAVs reconstructed with l1 -ESPIRiT. Then, the high-resolution coronary MRA images motion corrected with autofocusing using the l1 -ESPIRiT and DL model-based 3D iNAVs are assessed for differences.METHODSAn end-to-end unrolled network is trained to reconstruct beat-to-beat 3D iNAVs acquired during a CMRA sequence. The unrolled model incorporates a nonuniform FFT operator in TensorFlow to perform the data-consistency operation, and the regularization term is learned by a convolutional neural network (CNN) based on the proximal gradient descent algorithm. The training set includes 6,000 3D iNAVs acquired from 7 different subjects and 11 scans using a variable-density (VD) cones trajectory. For testing, 3D iNAVs from 4 additional subjects are reconstructed using the unrolled model. To validate reconstruction accuracy, global and localized motion estimates from DL model-based 3D iNAVs are compared with those extracted from 3D iNAVs reconstructed with l1 -ESPIRiT. Then, the high-resolution coronary MRA images motion corrected with autofocusing using the l1 -ESPIRiT and DL model-based 3D iNAVs are assessed for differences.3D iNAVs reconstructed using the DL model-based approach and conventional l1 -ESPIRiT generate similar global and localized motion estimates and provide equivalent coronary image quality. Reconstruction with the unrolled network completes in a fraction of the time compared to CPU and GPU implementations of l1 -ESPIRiT (20× and 3× speed increases, respectively).RESULTS3D iNAVs reconstructed using the DL model-based approach and conventional l1 -ESPIRiT generate similar global and localized motion estimates and provide equivalent coronary image quality. Reconstruction with the unrolled network completes in a fraction of the time compared to CPU and GPU implementations of l1 -ESPIRiT (20× and 3× speed increases, respectively).We have developed a deep neural network architecture to reconstruct undersampled 3D non-Cartesian VD cones iNAVs. Our approach decreases reconstruction time for 3D iNAVs, while preserving the accuracy of nonrigid motion information offered by them for correction.CONCLUSIONSWe have developed a deep neural network architecture to reconstruct undersampled 3D non-Cartesian VD cones iNAVs. Our approach decreases reconstruction time for 3D iNAVs, while preserving the accuracy of nonrigid motion information offered by them for correction.
Author	Ong, Frank Malavé, Mario O. Koundinyan, Srivathsan P. Sandino, Christopher M. Baron, Corey A. Cheng, Joseph Y. Nishimura, Dwight G.
AuthorAffiliation	2 Department of Medical Biophysics, Western University, London, ON, Canada 1 Magnetic Resonance Systems Research Laboratory, Department of Electrical Engineering, Stanford University, Stanford, CA 3 Department of Radiology, Stanford University, Stanford, CA
AuthorAffiliation_xml	– name: 2 Department of Medical Biophysics, Western University, London, ON, Canada – name: 1 Magnetic Resonance Systems Research Laboratory, Department of Electrical Engineering, Stanford University, Stanford, CA – name: 3 Department of Radiology, Stanford University, Stanford, CA
Author_xml	– sequence: 1 givenname: Mario O. orcidid: 0000-0003-0063-564X surname: Malavé fullname: Malavé, Mario O. email: momalave@gmail.com organization: Stanford University – sequence: 2 givenname: Corey A. orcidid: 0000-0001-7343-5580 surname: Baron fullname: Baron, Corey A. organization: Western University – sequence: 3 givenname: Srivathsan P. orcidid: 0000-0002-2977-6166 surname: Koundinyan fullname: Koundinyan, Srivathsan P. organization: Stanford University – sequence: 4 givenname: Christopher M. orcidid: 0000-0002-8360-0153 surname: Sandino fullname: Sandino, Christopher M. organization: Stanford University – sequence: 5 givenname: Frank surname: Ong fullname: Ong, Frank organization: Stanford University – sequence: 6 givenname: Joseph Y. surname: Cheng fullname: Cheng, Joseph Y. organization: Stanford University – sequence: 7 givenname: Dwight G. surname: Nishimura fullname: Nishimura, Dwight G. organization: Stanford University
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/32011021$$D View this record in MEDLINE/PubMed
BookMark	eNp9kc1uEzEUhS1URNPCghdAltjAYlr_TWa8QarCr9QIKYK1deOf4MpjB3umKDt4A56RJ8EhpYJKsLJ073eO79E5QUcxRYvQY0rOKCHsfMjDGetp191DM9oy1rBWiiM0I50gDadSHKOTUq4IIVJ24gE65oxQShidoW8rq1MsY5706FPEyeEpGpsLDNtgDeYvcf3sx9fvC8ijLR4i9gNsbJ2soVQgwrXfwJhywS5lrFNOEfIOL1cXeCo-bnCVTDGnsLcz1m5xsJDjfjMkY8NDdN9BKPbRzXuKPr5-9WHxtrl8_-bd4uKy0ULwrgFj5kLOpQHRaqJ7QY3sHTNrANpLDcL1c6cdtE4C9EIIRyiAlsK1wjJu-Cl6cfDdTuvBGm3jmCGoba558k4l8OrvTfSf1CZdq55zSjpSDZ7dGOT0ebJlVIMv2oYA0aapKMZbwrlsCavo0zvoVZpyrPEqJZkUnPKuUk_-vOj2lN_tVOD5AdA5lZKtu0UoUfvmVW1e_Wq-sud3WO1H2Hdaw_jwP8UXH-zu39ZquVoeFD8B-EfESg
CitedBy_id	crossref_primary_10_1111_1754_9485_13276 crossref_primary_10_1109_JBHI_2024_3357784 crossref_primary_10_1109_JPROC_2022_3141367 crossref_primary_10_1186_s12968_023_00962_9 crossref_primary_10_1002_mrm_30105 crossref_primary_10_1016_j_compbiomed_2023_107707 crossref_primary_10_1002_jmri_29295 crossref_primary_10_1007_s10334_024_01173_8 crossref_primary_10_1155_2022_5413473 crossref_primary_10_1002_mrm_29357 crossref_primary_10_1088_1361_6560_ad94c7 crossref_primary_10_1109_TBME_2024_3443635 crossref_primary_10_1002_mp_14809 crossref_primary_10_1155_2021_1197728 crossref_primary_10_3233_JCM_226712 crossref_primary_10_1007_s10278_022_00721_9 crossref_primary_10_1016_j_media_2022_102429 crossref_primary_10_1016_j_mri_2022_10_010 crossref_primary_10_3389_fcvm_2021_682924 crossref_primary_10_1007_s10334_024_01157_8 crossref_primary_10_1007_s12194_024_00875_x crossref_primary_10_1016_j_mri_2020_09_021 crossref_primary_10_1088_1361_6560_acc003 crossref_primary_10_1002_mrm_28659 crossref_primary_10_1002_mrm_28774 crossref_primary_10_1002_mrm_29666 crossref_primary_10_1109_TMI_2022_3144619 crossref_primary_10_1155_2021_5839391 crossref_primary_10_1038_s41598_020_70551_8 crossref_primary_10_1016_j_crad_2022_03_008
Cites_doi	10.1002/mrm.20790 10.1109/TMI.2005.848376 10.1016/j.compmedimag.2019.06.001 10.1109/ICIP.2017.8297024 10.1259/bjr.20170788 10.1109/TMI.2017.2760978 10.1109/TMI.2018.2865356 10.1109/TMI.2018.2858752 10.1109/CVPR.2016.90 10.1109/TMI.2018.2820120 10.1002/mrm.26273 10.1002/jmri.24602 10.1002/mrm.26928 10.1002/mrm.26269 10.1109/TMI.2003.815867 10.1002/jmri.24785 10.1002/mrm.24346 10.1561/2400000003 10.1109/TCI.2016.2644865 10.1002/cpa.20042 10.1002/mrm.25803 10.1109/CVPR.2016.55 10.1109/ISBI.2011.5872579 10.1002/cpa.20124 10.1002/jmri.22569 10.1002/mrm.20796 10.1109/TC.1987.1676943 10.1002/mrm.27480 10.1002/(SICI)1522-2594(199911)42:5<952::AID-MRM16>3.0.CO;2-S 10.1002/mrm.27355 10.1002/mrm.21391 10.1002/mrm.24751 10.1002/mrm.26977 10.1002/mrm.27706 10.1016/S0031-3203(98)00091-0 10.1109/TMI.2018.2863670 10.1002/mrm.24924 10.1002/mrm.27475
ContentType	Journal Article
Copyright	2020 International Society for Magnetic Resonance in Medicine 2020 International Society for Magnetic Resonance in Medicine.
Copyright_xml	– notice: 2020 International Society for Magnetic Resonance in Medicine – notice: 2020 International Society for Magnetic Resonance in Medicine.
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 8FD FR3 K9. M7Z P64 7X8 5PM
DOI	10.1002/mrm.28177
DatabaseName	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	Biochemistry Abstracts 1 MEDLINE MEDLINE - Academic
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Medicine Physics
EISSN	1522-2594
EndPage	812
ExternalDocumentID	PMC8331070 32011021 10_1002_mrm_28177 MRM28177
Genre	article Research Support, U.S. Gov't, Non-P.H.S Research Support, Non-U.S. Gov't Journal Article Research Support, N.I.H., Extramural
GrantInformation_xml	– fundername: NSF Graduate Research Fellowship Program funderid: NIH R01 HL127039; T32HL007846 – fundername: GE Healthcare – fundername: NHLBI NIH HHS grantid: R01 HL127039 – fundername: NHLBI NIH HHS grantid: T32 HL007846
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-c4437-add64969da45c0c841d98f2dbaa189ca4f86fcfa5f9aa8444f01aac94f54e23d3
IEDL.DBID	DRFUL
ISICitedReferencesCount	37
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000510500200001&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	Thu Aug 21 14:36:26 EDT 2025 Thu Jul 10 17:57:18 EDT 2025 Sat Nov 29 14:42:51 EST 2025 Mon Jul 21 05:59:28 EDT 2025 Sat Nov 29 02:37:49 EST 2025 Tue Nov 18 22:31:44 EST 2025 Wed Jan 22 16:34:01 EST 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	2
Keywords	non-Cartesian 3D cones trajectory convolutional neural networks coronary MRA
Language	English
License	2020 International Society for Magnetic Resonance in Medicine.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c4437-add64969da45c0c841d98f2dbaa189ca4f86fcfa5f9aa8444f01aac94f54e23d3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-8360-0153 0000-0003-0063-564X 0000-0001-7343-5580 0000-0002-2977-6166
OpenAccessLink	https://www.ncbi.nlm.nih.gov/pmc/articles/8331070
PMID	32011021
PQID	2392943137
PQPubID	1016391
PageCount	13
ParticipantIDs	pubmedcentral_primary_oai_pubmedcentral_nih_gov_8331070 proquest_miscellaneous_2350339502 proquest_journals_2392943137 pubmed_primary_32011021 crossref_primary_10_1002_mrm_28177 crossref_citationtrail_10_1002_mrm_28177 wiley_primary_10_1002_mrm_28177_MRM28177
PublicationCentury	2000
PublicationDate	August 2020
PublicationDateYYYYMMDD	2020-08-01
PublicationDate_xml	– month: 08 year: 2020 text: August 2020
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: Hoboken
PublicationTitle	Magnetic resonance in medicine
PublicationTitleAlternate	Magn Reson Med
PublicationYear	2020
Publisher	Wiley Subscription Services, Inc
Publisher_xml	– name: Wiley Subscription Services, Inc
References	1987; 36 2013; 69 2017; 25 2006; 55 2019; 76 2015; 74 2006; 59 2011; 33 1999; 42 2018; 26 2007; 58 2005; 24 2014; 1 2011; 2011 2015; 23 2019; 82 2019; 81 2014; 4 2016; 3 2017; 37 2017; 77 2015; 42 2015; 41 2004; 57 2018; 91 1999; 32 2017 2016 2014 2014; 72 2014; 71 2018; 38 2018; 37 2003; 22 2018; 79 e_1_2_6_51_1 Goodfellow I (e_1_2_6_44_1) 2014 e_1_2_6_32_1 Liu J (e_1_2_6_25_1) 2014; 4 e_1_2_6_19_1 He K (e_1_2_6_30_1) 2016 e_1_2_6_13_1 e_1_2_6_36_1 e_1_2_6_11_1 e_1_2_6_34_1 e_1_2_6_17_1 e_1_2_6_15_1 e_1_2_6_38_1 e_1_2_6_43_1 e_1_2_6_20_1 e_1_2_6_41_1 e_1_2_6_9_1 e_1_2_6_5_1 e_1_2_6_7_1 e_1_2_6_24_1 e_1_2_6_49_1 e_1_2_6_3_1 e_1_2_6_22_1 e_1_2_6_28_1 e_1_2_6_45_1 e_1_2_6_26_1 e_1_2_6_47_1 e_1_2_6_10_1 e_1_2_6_31_1 e_1_2_6_50_1 e_1_2_6_14_1 e_1_2_6_35_1 e_1_2_6_12_1 e_1_2_6_33_1 e_1_2_6_18_1 e_1_2_6_39_1 e_1_2_6_16_1 e_1_2_6_37_1 e_1_2_6_42_1 e_1_2_6_21_1 e_1_2_6_40_1 e_1_2_6_8_1 e_1_2_6_4_1 e_1_2_6_6_1 e_1_2_6_48_1 e_1_2_6_23_1 e_1_2_6_2_1 e_1_2_6_29_1 e_1_2_6_27_1 e_1_2_6_46_1
References_xml	– volume: 69 start-page: 1083 year: 2013 end-page: 1093 article-title: Free‐breathing multiphase whole‐heart coronary mr angiography using image‐based navigators and three‐dimensional cones imaging publication-title: Magn Reson Med – volume: 2011 start-page: 1039 year: 2011 end-page: 1043 – volume: 77 start-page: 1884 year: 2017 end-page: 1893 article-title: Nonrigid motion correction with 3D image‐based navigators for coronary MR angiography 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: 36 start-page: 581 year: 1987 end-page: 591 article-title: Parallelization and performance analysis of the Cooley‐Tukey FFT algorithm for shared‐memory architectures publication-title: IEEE Trans Comput – volume: 81 start-page: 1092 year: 2019 end-page: 1103 article-title: Whole‐heart coronary MR angiography using a 3D cones phyllotaxis trajectory publication-title: Magn Reson Med – volume: 38 start-page: 394 year: 2018 end-page: 405 article-title: Modl: Model‐based deep learning architecture for inverse problems publication-title: IEEE Trans Med Imaging – volume: 42 start-page: 952 year: 1999 end-page: 962 article-title: Sense: sensitivity encoding for fast MRI publication-title: Magn Reson Med – volume: 22 start-page: 986 year: 2003 end-page: 1004 article-title: Mutual‐information‐based registration of medical images: a survey publication-title: IEEE Trans Med Imaging – volume: 72 start-page: 347 year: 2014 end-page: 361 article-title: Nonrigid autofocus motion correction for coronary mr angiography with a 3D cones trajectory publication-title: Magn Reson Med – start-page: 770 year: 2016 end-page: 778 – start-page: 449 year: 2016 end-page: 458 – volume: 38 start-page: 167 year: 2018 end-page: 179 article-title: Deep generative adversarial neural networks for compressive sensing MRI publication-title: IEEE Trans Med Imaging – volume: 4 start-page: 57 year: 2014 end-page: 67 article-title: Accelerated MRI with circular cartesian undersampling (circus): a variable density cartesian sampling strategy for compressed sensing and parallel imaging publication-title: Quant Imaging Med Surgery – volume: 38 start-page: 280 year: 2018 end-page: 290 article-title: Convolutional recurrent neural networks for dynamic MR image reconstruction publication-title: IEEE Trans Med Imaging – volume: 32 start-page: 71 year: 1999 end-page: 86 article-title: An overlap invariant entropy measure of 3D medical image alignment publication-title: Pattern Recognition – volume: 42 start-page: 407 year: 2015 end-page: 420 article-title: Free‐breathing pediatric MRI with nonrigid motion correction and acceleration publication-title: J Magn Reson Imaging – volume: 79 start-page: 2685 year: 2018 end-page: 2692 article-title: Rapid compressed sensing reconstruction of 3D non‐cartesian MRI publication-title: Magn Reson Med – volume: 82 start-page: 485 year: 2019 end-page: 494 article-title: Dynamic MRI using model‐based deep learning and SToRM priors: MoDL‐SToRM publication-title: Magn Reson Med – volume: 58 start-page: 1182 year: 2007 end-page: 1195 article-title: Sparse MRI: The application of compressed sensing for rapid MR imaging publication-title: Magn Reson Med – volume: 55 start-page: 557 year: 2006 end-page: 565 article-title: Alternating repetition time balanced steady state free precession publication-title: Magn Reson Med – volume: 23 start-page: 2486 year: 2015 – volume: 24 start-page: 799 year: 2005 end-page: 808 article-title: Rapid gridding reconstruction with a minimal oversampling ratio publication-title: IEEE Trans Med Imaging – volume: 81 start-page: 1143 year: 2019 end-page: 1156 article-title: Real‐time cardiovascular MR with spatio‐temporal artifact suppression using deep learning‐proof of concept in congenital heart disease publication-title: Magn Reson Med – 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: 25 start-page: 3807 year: 2017 – volume: 55 start-page: 575 year: 2006 end-page: 582 article-title: Design and analysis of a practical 3D cones trajectory publication-title: Magn Reson Med – volume: 74 start-page: 614 year: 2015 end-page: 621 article-title: High‐resolution variable‐density 3D cones coronary MRA publication-title: Magn Reson Med – volume: 41 start-page: 738 year: 2015 end-page: 746 article-title: Highly efficient respiratory motion compensated free‐breathing coronary MRA using golden‐step cartesian acquisition publication-title: J Magn Reson Imaging – volume: 77 start-page: 1874 year: 2017 end-page: 1883 article-title: 3D image‐based navigators for coronary mr angiography publication-title: Magn Reson Med – volume: 26 start-page: 0920 year: 2018 – volume: 59 start-page: 1207 year: 2006 end-page: 1223 article-title: Stable signal recovery from incomplete and inaccurate measurements publication-title: Commun Pure Appl Math – volume: 37 start-page: 1488 year: 2018 end-page: 1497 article-title: Compressed sensing MRI reconstruction using a generative adversarial network with a cyclic loss publication-title: IEEE Trans Med Imaging – volume: 1 start-page: 127 year: 2014 end-page: 239 article-title: Proximal algorithms publication-title: Foundations Trends® Optim – volume: 23 start-page: 3639 year: 2015 – volume: 3 start-page: 47 year: 2016 end-page: 57 article-title: Loss functions for image restoration with neural networks publication-title: IEEE Trans Comput Imaging – volume: 57 start-page: 1413 year: 2004 end-page: 1457 article-title: An iterative thresholding algorithm for linear inverse problems with a sparsity constraint publication-title: Commun Pure Appl Math – start-page: 3953 year: 2017 end-page: 3957 – volume: 76 start-page: 101640 year: 2019 article-title: Motion estimation and correction in cardiac ct angiography images using convolutional neural networks publication-title: Comput Med Imaging Graphics – volume: 33 start-page: 1136 year: 2011 end-page: 1143 article-title: Loss of fine structure and edge sharpness in fast‐spin‐echo carotid wall imaging: measurements and comparison with multiple‐spin‐echo in normal and atherosclerotic subjects publication-title: J Magn Reson Imaging – volume: 91 start-page: 20170788 year: 2018 article-title: Respiratory motion correction for free‐breathing 3D abdominal MRI using CNN‐based image registration: a feasibility study publication-title: British J Radiol – start-page: 630 year: 2016 end-page: 645 article-title: Identity mappings in deep residual networks publication-title: European Conference on Computer Vision – 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: 2672 year: 2014 end-page: 2680 article-title: Generative adversarial nets publication-title: Adv Neural Infor Process Syst – volume: 37 start-page: 491 year: 2017 end-page: 503 article-title: A deep cascade of convolutional neural networks for dynamic MR image reconstruction publication-title: IEEE Trans Med Imaging – ident: e_1_2_6_4_1 doi: 10.1002/mrm.20790 – ident: e_1_2_6_34_1 doi: 10.1109/TMI.2005.848376 – ident: e_1_2_6_51_1 doi: 10.1016/j.compmedimag.2019.06.001 – ident: e_1_2_6_14_1 – ident: e_1_2_6_43_1 doi: 10.1109/ICIP.2017.8297024 – ident: e_1_2_6_49_1 doi: 10.1259/bjr.20170788 – ident: e_1_2_6_12_1 doi: 10.1109/TMI.2017.2760978 – ident: e_1_2_6_13_1 doi: 10.1109/TMI.2018.2865356 – ident: e_1_2_6_32_1 doi: 10.1109/TMI.2018.2858752 – ident: e_1_2_6_29_1 doi: 10.1109/CVPR.2016.90 – ident: e_1_2_6_47_1 doi: 10.1109/TMI.2018.2820120 – ident: e_1_2_6_6_1 doi: 10.1002/mrm.26273 – ident: e_1_2_6_26_1 doi: 10.1002/jmri.24602 – ident: e_1_2_6_41_1 doi: 10.1002/mrm.26928 – ident: e_1_2_6_2_1 doi: 10.1002/mrm.26269 – ident: e_1_2_6_39_1 doi: 10.1109/TMI.2003.815867 – ident: e_1_2_6_27_1 doi: 10.1002/jmri.24785 – ident: e_1_2_6_50_1 – ident: e_1_2_6_3_1 doi: 10.1002/mrm.24346 – ident: e_1_2_6_15_1 – ident: e_1_2_6_16_1 doi: 10.1561/2400000003 – ident: e_1_2_6_31_1 doi: 10.1109/TCI.2016.2644865 – ident: e_1_2_6_20_1 – ident: e_1_2_6_22_1 doi: 10.1002/cpa.20042 – ident: e_1_2_6_42_1 – ident: e_1_2_6_11_1 – ident: e_1_2_6_19_1 doi: 10.1002/mrm.25803 – ident: e_1_2_6_45_1 doi: 10.1109/CVPR.2016.55 – ident: e_1_2_6_24_1 doi: 10.1109/ISBI.2011.5872579 – ident: e_1_2_6_28_1 doi: 10.1002/cpa.20124 – ident: e_1_2_6_40_1 doi: 10.1002/jmri.22569 – ident: e_1_2_6_5_1 doi: 10.1002/mrm.20796 – ident: e_1_2_6_36_1 doi: 10.1109/TC.1987.1676943 – ident: e_1_2_6_17_1 doi: 10.1002/mrm.27480 – ident: e_1_2_6_33_1 – ident: e_1_2_6_21_1 doi: 10.1002/(SICI)1522-2594(199911)42:5<952::AID-MRM16>3.0.CO;2-S – ident: e_1_2_6_48_1 doi: 10.1002/mrm.27355 – ident: e_1_2_6_23_1 doi: 10.1002/mrm.21391 – ident: e_1_2_6_7_1 doi: 10.1002/mrm.24751 – ident: e_1_2_6_8_1 doi: 10.1002/mrm.26977 – ident: e_1_2_6_10_1 doi: 10.1002/mrm.27706 – ident: e_1_2_6_38_1 doi: 10.1016/S0031-3203(98)00091-0 – ident: e_1_2_6_9_1 doi: 10.1109/TMI.2018.2863670 – volume: 4 start-page: 57 year: 2014 ident: e_1_2_6_25_1 article-title: Accelerated MRI with circular cartesian undersampling (circus): a variable density cartesian sampling strategy for compressed sensing and parallel imaging publication-title: Quant Imaging Med Surgery – start-page: 630 year: 2016 ident: e_1_2_6_30_1 article-title: Identity mappings in deep residual networks publication-title: European Conference on Computer Vision – ident: e_1_2_6_37_1 doi: 10.1002/mrm.24924 – ident: e_1_2_6_46_1 – ident: e_1_2_6_18_1 doi: 10.1002/mrm.27475 – ident: e_1_2_6_35_1 – start-page: 2672 year: 2014 ident: e_1_2_6_44_1 article-title: Generative adversarial nets publication-title: Adv Neural Infor Process Syst
SSID	ssj0009974
Score	2.5197353
Snippet	Purpose To rapidly reconstruct undersampled 3D non‐Cartesian image‐based navigators (iNAVs) using an unrolled deep learning (DL) model, enabling nonrigid... To rapidly reconstruct undersampled 3D non-Cartesian image-based navigators (iNAVs) using an unrolled deep learning (DL) model, enabling nonrigid motion... PurposeTo rapidly reconstruct undersampled 3D non‐Cartesian image‐based navigators (iNAVs) using an unrolled deep learning (DL) model, enabling nonrigid motion...
SourceID	pubmedcentral proquest pubmed crossref wiley
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	800
SubjectTerms	3D cones trajectory Algorithms Angiography Artificial neural networks Cartesian coordinates Computer architecture Cones convolutional neural networks Coronary Angiography coronary MRA Deep Learning Heart Humans Image processing Image quality Image reconstruction Imaging, Three-Dimensional Machine learning Magnetic resonance Magnetic Resonance Angiography Model accuracy Navigators Neural networks non‐Cartesian Regularization Three dimensional models
Title	Reconstruction of undersampled 3D non‐Cartesian image‐based navigators for coronary MRA using an unrolled deep learning model
URI	https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmrm.28177 https://www.ncbi.nlm.nih.gov/pubmed/32011021 https://www.proquest.com/docview/2392943137 https://www.proquest.com/docview/2350339502 https://pubmed.ncbi.nlm.nih.gov/PMC8331070
Volume	84
WOSCitedRecordID	wos000510500200001&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 Free Content 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 – 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
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB71AYgLjwJloVQGceCSNnHstS1OVcsKJHaFVlTsLXL8KCt1s9Wm7Rn-Ab-RX4LHyWZZFSQkbkk8Thx7xv5sj78BeC2po9bpLJGlzRPGrUmULfuJ0NJpVwagxH0MNiFGIzmZqE8b8HZ5Fqbhh-gW3NAyYn-NBq7L-nBFGjpbzA6ozITYhG08VBVmXtsn48HpxxXnrmpImAXDrkaxJbFQSg-7zOvD0Q2MedNV8ncIG8egwf3_Kv0DuNdCT3LU6MpD2HDVDtwZtpvrO3A7eoOa-hF8x0npilqWzD25iodgNHIJW5KfkGpe_fz24xg9QvEYJpnOQscUnuCoaEmlr5G6Y76oSQDFxCBNQigrGY6PCHran5GQBf0Qz_F11rkL0oavOCMxNs9jOB28-3z8PmljNSSGsVwkoZvsM9VXVjNuUiNZZpX01JZaZ1IZzbzse-M190pryRjzaaa1Ucxz5mhu8yewFUrungKhilPnBPcy02E-xsvcem258NR5rqnpwZtlkxWmJTLHeBrnRUPBTItQuUWs3B686kQvGvaOPwntLdu9aA24LijixgCu8pD8sksOpof7Kbpy8yuUwT1gxVPag91GTbqv5BFY0awHYk2BOgGk9V5PqaZfI723zAPkFmn4zahAfy94MRwP48Wzfxd9DncprhhEF8Y92Aqa5F7ALXN9Oa0X-7ApJnK_taNw9-XD6BeETCf3
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1fb9MwED-NDgYv_BkDCgMM4oGXsMSxa1viZdqohmgqVG3S3iLXf0alNZ1atmf4BnxGPgk-J02pBhISb1F8SS72nf2zff4dwBtJHbVOZ4kc2zxh3JpE2XEvEVo67cYBKHEfk02I4VCenqrPG_B-eRam5odoF9zQM2J_jQ6OC9J7K9bQ6Xz6jspMiBuwyXq5kB3YPBz1TwYr0l1VszALhn2NYktmoZTutQ-vj0fXQOb1WMnfMWwchPr3_k_9-3C3AZ9kv7aWB7Dhqm3YKprt9W24FeNBzeIhfMdp6Ypclsw8uYzHYDSyCVuSH5JqVv389uMAY0LxICaZTEPXFO7guGhJpa-QvGM2X5AAi4lBooSgLClG-wRj7c9IeAQjEc_xdda5C9IksDgjMTvPDpz0PxwfHCVNtobEMJaLJHSUPaZ6ymrGTWoky6ySntqx1plURjMve954zb3SWjLGfJppbRTznDma2_wRdILm7gkQqjh1TnAvMx1mZHycW68tF546zzU1XXi7bLPSNFTmmFHjvKxJmGkZKreMlduF163oRc3f8Seh3WXDl40LL0qKyDHAqzwUv2qLg_Phjoqu3OwSZXAXWPGUduFxbSftV_IIrWjWBbFmQa0AEnuvl1STL5HgW-YBdIs0_Ga0oL8rXhajIl48_XfRl3D76LgYlIOPw0_P4A7F9YMY0LgLnWBV7jncNFdfJ4v5i8adfgEpbCnw
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB6VAhUXHuW1UMAgDlxCEz_WtsSlallRwa6qCkRvkeNHWambXe3SnuEf8Bv5JXicbJZVQULiFsWTZGLP2J_t8TcALxX11HlTZKpyLOPC2Uy7qp9Jo7zxVQRKIqRkE3I0Uicn-mgD3izPwjT8EN2CG3pG6q_Rwf3Mhd0Va-hkPnlNVSHlFbjKIw7HgK7Ph6MV5a5uOJglx55G8yWvUE53u0fXR6NLEPNypOTvCDYNQYNb_6f8bbjZQk-y19jKHdjw9TZsDdvN9W24nqJB7eIufMdJ6YpalkwDOU-HYAxyCTvCDkg9rX9--7GPEaF4DJOMJ7FjindwVHSkNhdI3TGdL0gExcQiTUJUlgyP9whG2p-S-AjGIZ7h65z3M9KmrzglKTfPPfg0ePtx_13W5mrILOdMZrGb7HPd185wYXOreOG0CtRVxhRKW8OD6gcbjAjaGMU5D3lhjNU8CO4pc-w-bEbN_UMgVAvqvRRBFSbOx0TFXDBOyEB9EIbaHrxatllpWyJzzKdxVjYUzLSMlVumyu3Bi0501rB3_EloZ9nwZevAi5IibozgisXi511xdD3cTzG1n56jDO4Ba5HTHjxo7KT7CkvAihY9kGsW1Akgrfd6ST3-kui9FYuQW-bxN5MF_V3xcng8TBeP_l30GWwdHQzKD4ej94_hBsXFgxTNuAOb0aj8E7hmL76OF_OnyZd-AfjvKEY
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=Reconstruction+of+undersampled+3D+non-Cartesian+image-based+navigators+for+coronary+MRA+using+an+unrolled+deep+learning+model&rft.jtitle=Magnetic+resonance+in+medicine&rft.au=Malav%C3%A9%2C+Mario+O&rft.au=Baron%2C+Corey+A&rft.au=Koundinyan%2C+Srivathsan+P&rft.au=Sandino%2C+Christopher+M&rft.date=2020-08-01&rft.eissn=1522-2594&rft.volume=84&rft.issue=2&rft.spage=800&rft_id=info:doi/10.1002%2Fmrm.28177&rft_id=info%3Apmid%2F32011021&rft.externalDocID=32011021
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