Deep-learning-based image reconstruction with limited data: generating synthetic raw data using deep learning

Object Deep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw data is not always available in sufficient quantities. This study investigates synthetic data generation to complement small datasets and impr...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Magma (New York, N.Y.) Ročník 37; číslo 6; s. 1059 - 1076
Hlavní autoři:	Zijlstra, Frank, While, Peter Thomas
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Cham Springer International Publishing 01.12.2024
Témata:	Algorithms Basic Science - Reconstruction algorithms and artificial intelligence Biomedical Engineering and Bioengineering Brain - diagnostic imaging Computer Appl. in Life Sciences Deep Learning Health Informatics Humans Image Processing, Computer-Assisted - methods Imaging Magnetic Resonance Imaging - methods Medicine Medicine & Public Health Neural Networks, Computer Radiology Research Article Solid State Physics Deep learning Accelerated MRI Image reconstruction Synthetic data
ISSN:	1352-8661, 0968-5243, 1352-8661
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Object Deep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw data is not always available in sufficient quantities. This study investigates synthetic data generation to complement small datasets and improve reconstruction quality. Materials and methods An adversarial auto-encoder was trained to generate phase and coil sensitivity maps from magnitude images, which were combined into synthetic raw data. On a fourfold accelerated MR reconstruction task, deep-learning-based reconstruction networks were trained with varying amounts of training data (20 to 160 scans). Test set performance was compared between baseline experiments and experiments that incorporated synthetic training data. Results Training with synthetic raw data showed decreasing reconstruction errors with increasing amounts of training data, but importantly this was magnitude-only data, rather than real raw data. For small training sets, training with synthetic data decreased the mean absolute error (MAE) by up to 7.5%, whereas for larger training sets the MAE increased by up to 2.6%. Discussion Synthetic raw data generation improved reconstruction quality in scenarios with limited training data. A major advantage of synthetic data generation is that it allows for the reuse of magnitude-only datasets, which are more readily available than raw datasets.
AbstractList	Deep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw data is not always available in sufficient quantities. This study investigates synthetic data generation to complement small datasets and improve reconstruction quality. An adversarial auto-encoder was trained to generate phase and coil sensitivity maps from magnitude images, which were combined into synthetic raw data. On a fourfold accelerated MR reconstruction task, deep-learning-based reconstruction networks were trained with varying amounts of training data (20 to 160 scans). Test set performance was compared between baseline experiments and experiments that incorporated synthetic training data. Training with synthetic raw data showed decreasing reconstruction errors with increasing amounts of training data, but importantly this was magnitude-only data, rather than real raw data. For small training sets, training with synthetic data decreased the mean absolute error (MAE) by up to 7.5%, whereas for larger training sets the MAE increased by up to 2.6%. Synthetic raw data generation improved reconstruction quality in scenarios with limited training data. A major advantage of synthetic data generation is that it allows for the reuse of magnitude-only datasets, which are more readily available than raw datasets. Deep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw data is not always available in sufficient quantities. This study investigates synthetic data generation to complement small datasets and improve reconstruction quality.OBJECTDeep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw data is not always available in sufficient quantities. This study investigates synthetic data generation to complement small datasets and improve reconstruction quality.An adversarial auto-encoder was trained to generate phase and coil sensitivity maps from magnitude images, which were combined into synthetic raw data. On a fourfold accelerated MR reconstruction task, deep-learning-based reconstruction networks were trained with varying amounts of training data (20 to 160 scans). Test set performance was compared between baseline experiments and experiments that incorporated synthetic training data.MATERIALS AND METHODSAn adversarial auto-encoder was trained to generate phase and coil sensitivity maps from magnitude images, which were combined into synthetic raw data. On a fourfold accelerated MR reconstruction task, deep-learning-based reconstruction networks were trained with varying amounts of training data (20 to 160 scans). Test set performance was compared between baseline experiments and experiments that incorporated synthetic training data.Training with synthetic raw data showed decreasing reconstruction errors with increasing amounts of training data, but importantly this was magnitude-only data, rather than real raw data. For small training sets, training with synthetic data decreased the mean absolute error (MAE) by up to 7.5%, whereas for larger training sets the MAE increased by up to 2.6%.RESULTSTraining with synthetic raw data showed decreasing reconstruction errors with increasing amounts of training data, but importantly this was magnitude-only data, rather than real raw data. For small training sets, training with synthetic data decreased the mean absolute error (MAE) by up to 7.5%, whereas for larger training sets the MAE increased by up to 2.6%.Synthetic raw data generation improved reconstruction quality in scenarios with limited training data. A major advantage of synthetic data generation is that it allows for the reuse of magnitude-only datasets, which are more readily available than raw datasets.DISCUSSIONSynthetic raw data generation improved reconstruction quality in scenarios with limited training data. A major advantage of synthetic data generation is that it allows for the reuse of magnitude-only datasets, which are more readily available than raw datasets. Object Deep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw data is not always available in sufficient quantities. This study investigates synthetic data generation to complement small datasets and improve reconstruction quality. Materials and methods An adversarial auto-encoder was trained to generate phase and coil sensitivity maps from magnitude images, which were combined into synthetic raw data. On a fourfold accelerated MR reconstruction task, deep-learning-based reconstruction networks were trained with varying amounts of training data (20 to 160 scans). Test set performance was compared between baseline experiments and experiments that incorporated synthetic training data. Results Training with synthetic raw data showed decreasing reconstruction errors with increasing amounts of training data, but importantly this was magnitude-only data, rather than real raw data. For small training sets, training with synthetic data decreased the mean absolute error (MAE) by up to 7.5%, whereas for larger training sets the MAE increased by up to 2.6%. Discussion Synthetic raw data generation improved reconstruction quality in scenarios with limited training data. A major advantage of synthetic data generation is that it allows for the reuse of magnitude-only datasets, which are more readily available than raw datasets.
Author	Zijlstra, Frank While, Peter Thomas
Author_xml	– sequence: 1 givenname: Frank orcidid: 0000-0002-9184-7666 surname: Zijlstra fullname: Zijlstra, Frank email: Frank.Zijlstra@stolav.no organization: Department of Radiology and Nuclear Medicine, St Olav’s University Hospital, Department of Circulation and Medical Imaging, NTNU–Norwegian University of Science and Technology – sequence: 2 givenname: Peter Thomas surname: While fullname: While, Peter Thomas organization: Department of Radiology and Nuclear Medicine, St Olav’s University Hospital, Department of Circulation and Medical Imaging, NTNU–Norwegian University of Science and Technology
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/39207581$$D View this record in MEDLINE/PubMed
BookMark	eNp9UctO3DAUtSoQr_IDXVResgn1K3HcTYVoS5FGYkPXluPcyRgl9tR2QPx9PQyMgAULy_Y9j2vfc4z2fPCA0BdKzikh8luihHNREVYWpYpX4hM6orxmVds0dO_V-RAdp3RHCKM14QfokCtGZN3SIzT9BFhXI5jonR-qziTosZvMADiCDT7lONvsgscPLq_w6CaXC6M32XzHA3iIJhchTo8-ryA7i6N5eILxnDZAX_zxi_9ntL80Y4LT5_0E_f396_byT7W4ubq-vFhUVgiZKyFBLTvFu7blS9Z3lvG6KxWgrSyVnpBaMCuNYEoCa4gwrWXQlGtDRd90_AT92Pqu526C3oLP0Yx6HcvP4qMOxum3iHcrPYR7TWndMlY3xeHs2SGGfzOkrCeXLIyj8RDmpDlRSirJuCrUr6-b7bq8DLkQ2JZgY0gpwnJHoURvktTbJHVJUj8lqUURte9E1mWzSaI82I0fS_lWmkofP0DUd2GOvgz8I9V_zSu0eA
CitedBy_id	crossref_primary_10_1007_s11053_025_10543_5 crossref_primary_10_1016_j_cmpb_2025_108814
Cites_doi	10.1109/5.726791 10.1038/nature25988 10.1148/radiol.204097 10.1002/mrm.10171 10.1109/TMI.2023.3290149 10.1002/mrm.28148 10.1016/j.mri.2012.09.009 10.1016/j.media.2022.102479 10.1186/s40537-019-0197-0 10.1109/TMI.2022.3147426 10.1002/jemt.23694 10.1002/mrm.27106 10.1186/s40537-016-0043-6 10.1109/TMI.2022.3179981 10.1097/RLI.0000000000000928 10.48550/arXiv.1710.10196 10.1002/mrm.27355 10.1109/MSP.2019.2950433 10.1002/mrm.28827 10.1109/TMI.2021.3075856 10.1214/aoms/1177704014 10.1109/TIP.2003.819861 10.1002/mrm.21391 10.1002/mrm.28338 10.1109/TMI.2018.2865356 10.1002/(SICI)1522-2594(199911)42:5<952::AID-MRM16>3.0.CO;2-S 10.1148/radiol.220425 10.1016/j.tics.2021.11.008 10.1117/1.JMI.10.5.054503 10.3390/bioengineering10030358 10.3390/diagnostics11101935 10.48550/arXiv.2004.06688 10.48550/arXiv.2307.13220 10.48550/arXiv.2312.10271 10.48550/arXiv.1909.11512 10.48550/arXiv.1511.05644 10.48550/arXiv.2106.13199 10.48550/arXiv.2112.10752 10.1109/CVPR42600.2020.00872 10.1109/ICCV.2019.00460 10.48550/arXiv.2006.11239 10.1109/CVPRW.2018.00143 10.1007/978-3-031-26438-2_12 10.1109/CVPR.2017.632 10.48550/arXiv.2111.05826 10.1109/CVPR.2019.00020 10.48550/arXiv.1910.07113 10.48550/arXiv.1911.08716 10.48550/arXiv.1811.08839 10.48550/arXiv.2109.08237 10.48550/arXiv.2204.06125
ContentType	Journal Article
Copyright	The Author(s) 2024 2024. The Author(s). The Author(s) 2024 2024
Copyright_xml	– notice: The Author(s) 2024 – notice: 2024. The Author(s). – notice: The Author(s) 2024 2024
DBID	C6C AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 5PM
DOI	10.1007/s10334-024-01193-4
DatabaseName	Open Access资源_Springer Nature OA Free Journals CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic PubMed Central (Full Participant titles)
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic
DatabaseTitleList	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
EISSN	1352-8661
EndPage	1076
ExternalDocumentID	PMC11582256 39207581 10_1007_s10334_024_01193_4
Genre	Journal Article
GrantInformation_xml	– fundername: Norges Forskningsråd grantid: 302624 funderid: http://dx.doi.org/10.13039/501100005416 – fundername: NTNU Norwegian University of Science and Technology (incl St. Olavs Hospital - Trondheim University Hospital) – fundername: Norges Forskningsråd grantid: 302624
GroupedDBID	--- --K -53 -5E -5G -BR -EM -Y2 -~C .86 .VR 06C 06D 0R~ 0VY 1B1 1N0 1SB 203 28- 29M 29~ 2J2 2JN 2JY 2KG 2LR 2P1 2VQ 2~H 30V 3SX 3V. 4.4 406 408 409 40D 40E 53G 5GY 5QI 5VS 67Z 6NX 7X7 88E 88I 8FE 8FG 8FH 8FI 8FJ 8FW 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAEDT AAHNG AAIAL AAJBT AAJKR AALRI AANXM AANZL AAQFI AAQXK AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAXUO AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA ABDZT ABECU ABFTV ABHLI ABHQN ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABPLI ABQBU ABQSL ABSXP ABTEG ABTKH ABTMW ABULA ABUWG ABWNU ABWVN ABXPI ACAOD ACBXY ACDTI ACGFS ACGOD ACHSB ACHXU ACIUM ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACRPL ACSNA ACUDM ACZOJ ADBBV ADHHG ADHIR ADINQ ADKNI ADKPE ADMUD ADNMO ADPHR ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFIE AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AETLH AEUYN AEVLU AEXYK AFBBN AFEXP AFKRA AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHMBA AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ AKMHD AKRWK ALIPV ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARAPS ARMRJ ASPBG AVWKF AXYYD AZFZN AZQEC B-. BA0 BBWZM BDATZ BENPR BGLVJ BGNMA BHPHI BKSAR BPHCQ BSONS BVXVI C6C CAG CCPQU COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 DWQXO EBLON EBS EIOEI EJD EMOBN EN4 EPAXT ESBYG F5P FDB FEDTE FERAY FFXSO FGOYB FIGPU FINBP FNLPD FRRFC FSGXE FWDCC FYUFA G-Y G-Z GGCAI GGRSB GJIRD GNUQQ GNWQR GQ6 GQ7 GQ8 GRRUI GXS H13 HCIFZ HF~ HG5 HG6 HMCUK HMJXF HQYDN HRMNR HVGLF HZ~ I09 IHE IJ- IKXTQ IWAJR IXC IXD IXE IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ KDC KOV KOW KPH LAK LK5 LLZTM M1P M2P M41 M4Y M7R MA- N2Q NB0 NDZJH NPVJJ NQ- NQJWS NU0 O9- O93 O9G O9I O9J OAM P19 P2P P62 P9S PCBAR PF0 PQQKQ PROAC PSQYO PT4 PT5 Q2X QOK QOR QOS R2- R4E R89 R9I RHV RIG RNI RNS ROL RPX RPZ RRX RSV RZK S16 S1Z S26 S27 S28 S37 S3B SAP SCLPG SDE SDH SEW SHX SISQX SJYHP SMD SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW SSXJD SSZ STPWE SV3 SZ9 SZN T13 T16 TSG TSK TSV TT1 TUC U2A U9L UG4 UHS UKHRP UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WJK WK6 WK8 YLTOR Z45 Z7X Z82 Z83 Z88 Z8R Z8V Z8W ZMTXR ZOVNA ~EX AAPKM AAYXX ABBRH ABDBE ABFSG ABRTQ ACSTC AEZWR AFDZB AFHIU AFOHR AHPBZ AHWEU AIXLP ATHPR AYFIA CITATION ADHKG AEUPX AFPUW AGQPQ CGR CUY CVF ECM EIF NPM PHGZM PHGZT PJZUB PPXIY PQGLB 7X8 5PM
ID	FETCH-LOGICAL-c447t-47e9fb93b883f2dbc235b9fbe18783fd00542c7a4297e2604a8c2e6429614d6b3
IEDL.DBID	RSV
ISICitedReferencesCount	2
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001302322900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1352-8661 0968-5243
IngestDate	Tue Nov 04 02:04:53 EST 2025 Thu Sep 04 16:25:10 EDT 2025 Mon Jul 21 06:03:32 EDT 2025 Sat Nov 29 03:00:50 EST 2025 Tue Nov 18 21:49:59 EST 2025 Fri Feb 21 02:39:31 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	6
Keywords	Deep learning Accelerated MRI Image reconstruction Synthetic data
Language	English
License	2024. The Author(s). Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c447t-47e9fb93b883f2dbc235b9fbe18783fd00542c7a4297e2604a8c2e6429614d6b3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0002-9184-7666
OpenAccessLink	https://link.springer.com/10.1007/s10334-024-01193-4
PMID	39207581
PQID	3099797239
PQPubID	23479
PageCount	18
ParticipantIDs	pubmedcentral_primary_oai_pubmedcentral_nih_gov_11582256 proquest_miscellaneous_3099797239 pubmed_primary_39207581 crossref_primary_10_1007_s10334_024_01193_4 crossref_citationtrail_10_1007_s10334_024_01193_4 springer_journals_10_1007_s10334_024_01193_4
PublicationCentury	2000
PublicationDate	2024-12-01
PublicationDateYYYYMMDD	2024-12-01
PublicationDate_xml	– month: 12 year: 2024 text: 2024-12-01 day: 01
PublicationDecade	2020
PublicationPlace	Cham
PublicationPlace_xml	– name: Cham – name: Germany
PublicationSubtitle	Official Journal of the European Society for Magnetic Resonance in Medicine and Biology
PublicationTitle	Magma (New York, N.Y.)
PublicationTitleAbbrev	Magn Reson Mater Phy
PublicationTitleAlternate	MAGMA
PublicationYear	2024
Publisher	Springer International Publishing
Publisher_xml	– name: Springer International Publishing
References	Shorten, Khoshgoftaar (CR18) 2019; 6 Shin, Tenenholtz, Rogers, Schwarz, Senjem, Gunter, Andriole, Michalski, Gooya, Goksel, Oguz, Burgos (CR33) 2018 CR39 Chung, Ye (CR55) 2022; 80 CR38 CR36 Pruessmann, Weiger, Scheidegger, Boesiger (CR1) 1999; 42 CR34 Özbey, Dalmaz, Dar, Bedel, Özturk, Güngör, Çukur (CR56) 2023; 42 CR30 Muckley, Riemenschneider, Radmanesh, Kim, Jeong, Ko, Jun, Shin, Hwang, Mostapha, Arberet, Nickel, Ramzi, Ciuciu, Starck, Teuwen, Karkalousos, Zhang, Sriram, Huang, Yakubova, Lui, Knoll (CR9) 2021; 40 Lee, Mustafaev, Nishikawa (CR40) 2023; 10 Dar, Özbey, Çatlı, Çukur (CR21) 2020; 84 Han, Yoo, Kim, Shin, Sung, Ye (CR20) 2018; 80 Knoll, Hammernik, Kobler, Pock, Recht, Sodickson (CR6) 2019; 81 Zhu, Liu, Cauley, Rosen, Rosen (CR4) 2018; 555 Lin, Walter, Fritz (CR12) 2023; 58 Korkmaz, Dar, Yurt, Özbey, Çukur (CR22) 2022; 41 Tudosiu, Pinaya, Graham, Borges, Fernandez, Yang, Appleyard, Novati, Mehra, Vella, Nachev, Ourselin, Cardoso, Zhao, Svoboda, Wolterink, Escobar (CR37) 2022 Knoll, Murrell, Sriram, Yakubova, Zbontar, Rabbat, Defazio, Muckley, Sodickson, Zitnick, Recht (CR7) 2020; 84 CR48 CR47 CR44 CR43 CR42 CR41 Lecun, Bottou, Bengio, Haffner (CR58) 1998; 86 Deveshwar, Rajagopal, Sahin, Shimron, Larson (CR25) 2023; 10 Ronneberger, Fischer, Brox (CR59) 2015 de Melo, Torralba, Guibas, DiCarlo, Chellappa, Hodgins (CR32) 2022; 26 Khan, Khan, Harouni, Abbasi, Iqbal, Mehmood (CR31) 2021; 84 Lustig, Donoho, Pauly (CR3) 2007; 58 Hammernik, Schlemper, Qin, Duan, Summers, Rueckert (CR15) 2021; 86 Miao, Huang, Narayan, Wilson (CR46) 2013; 31 CR17 CR16 Ueda, Ohno, Yamamoto, Murayama, Ikedo, Yui, Hanamatsu, Tanaka, Obama, Ikeda, Toyama (CR10) 2022; 303 CR13 CR57 Griswold, Jakob, Heidemann, Nittka, Jellus, Wang, Kiefer, Haase (CR2) 2002; 47 CR54 CR53 Good (CR61) 1963; 34 CR52 Wang, Bovik, Sheikh, Simoncelli (CR45) 2004; 13 CR51 Weiss, Khoshgoftaar, Wang (CR19) 2016; 3 CR50 Sandino, Cheng, Chen, Mardani, Pauly, Vasanawala (CR8) 2020; 37 Yang, Lin, Wang, Bao, Wang, Ma, Zhou, Yang, Cai, He, Cai, Dong, Cheng, Chen, Zhong (CR35) 2022; 41 Karras, Aila, Laine, Lehtinen (CR60) 2018 CR29 Johnson, Muckley, Bruno, Kobler, Hammernik, Pock, Knoll, Knoll, Maier, Rueckert, Ye (CR14) 2019 CR28 Aggarwal, Mani, Jacob (CR5) 2019; 38 CR27 CR26 CR24 CR62 Johnson, Lin, Zbontar, Zitnick, Sriram, Muckley, Babb, Kline, Ciavarra, Alaia, Samim, Walter, Calderon, Pock, Sodickson, Recht, Knoll (CR11) 2023; 307 Wang, Zhang, Dai, Chen, Wang, Wang (CR23) 2021; 11 Larsen, Sønderby, Larochelle, Winther, Larsen (CR49) 2016 1193_CR24 T Karras (1193_CR60) 2018 Y Lecun (1193_CR58) 1998; 86 C Shorten (1193_CR18) 2019; 6 1193_CR62 1193_CR29 1193_CR28 1193_CR27 HK Aggarwal (1193_CR5) 2019; 38 N Deveshwar (1193_CR25) 2023; 10 1193_CR26 K Weiss (1193_CR19) 2016; 3 Z Wang (1193_CR45) 2004; 13 T Ueda (1193_CR10) 2022; 303 KP Pruessmann (1193_CR1) 1999; 42 1193_CR36 H-C Shin (1193_CR33) 2018 1193_CR34 H Chung (1193_CR55) 2022; 80 1193_CR30 IJ Good (1193_CR61) 1963; 34 B Zhu (1193_CR4) 2018; 555 1193_CR39 1193_CR38 Y Han (1193_CR20) 2018; 80 F Knoll (1193_CR6) 2019; 81 M Lustig (1193_CR3) 2007; 58 PM Johnson (1193_CR14) 2019 Y Korkmaz (1193_CR22) 2022; 41 ABL Larsen (1193_CR49) 2016 CM Sandino (1193_CR8) 2020; 37 PM Johnson (1193_CR11) 2023; 307 F Wang (1193_CR23) 2021; 11 Q Yang (1193_CR35) 2022; 41 1193_CR47 1193_CR44 1193_CR43 MJ Muckley (1193_CR9) 2021; 40 1193_CR42 1193_CR41 M Özbey (1193_CR56) 2023; 42 F Knoll (1193_CR7) 2020; 84 1193_CR48 MA Griswold (1193_CR2) 2002; 47 SUH Dar (1193_CR21) 2020; 84 1193_CR13 1193_CR57 K Hammernik (1193_CR15) 2021; 86 AR Khan (1193_CR31) 2021; 84 1193_CR54 1193_CR53 O Ronneberger (1193_CR59) 2015 1193_CR52 1193_CR51 CM de Melo (1193_CR32) 2022; 26 1193_CR17 1193_CR16 P-D Tudosiu (1193_CR37) 2022 J Miao (1193_CR46) 2013; 31 1193_CR50 DJ Lin (1193_CR12) 2023; 58 J Lee (1193_CR40) 2023; 10
References_xml	– volume: 86 start-page: 2278 year: 1998 end-page: 2324 ident: CR58 article-title: Gradient-based learning applied to document recognition publication-title: Proc IEEE doi: 10.1109/5.726791 – volume: 555 start-page: 487 year: 2018 end-page: 492 ident: CR4 article-title: Image reconstruction by domain-transform manifold learning publication-title: Nature doi: 10.1038/nature25988 – volume: 303 start-page: 373 year: 2022 end-page: 381 ident: CR10 article-title: Deep learning reconstruction of diffusion-weighted MRI improves image quality for prostatic imaging publication-title: Radiology doi: 10.1148/radiol.204097 – start-page: 1 year: 2018 end-page: 11 ident: CR33 article-title: Medical Image Synthesis for Data Augmentation and Anonymization Using Generative Adversarial Networks publication-title: Simul – ident: CR39 – ident: CR16 – ident: CR51 – volume: 47 start-page: 1202 year: 2002 end-page: 1210 ident: CR2 article-title: Generalized autocalibrating partially parallel acquisitions (GRAPPA) publication-title: Magn Reson Med doi: 10.1002/mrm.10171 – volume: 42 start-page: 3524 year: 2023 end-page: 3539 ident: CR56 article-title: Unsupervised medical image translation with adversarial diffusion models publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2023.3290149 – volume: 84 start-page: 663 year: 2020 end-page: 685 ident: CR21 article-title: A Transfer-learning approach for accelerated mri using deep neural networks publication-title: Magn Reson Med doi: 10.1002/mrm.28148 – ident: CR29 – ident: CR54 – volume: 31 start-page: 596 year: 2013 end-page: 603 ident: CR46 article-title: A new perceptual difference model for diagnostically relevant quantitative image quality evaluation: A preliminary study publication-title: Magn Reson Imaging doi: 10.1016/j.mri.2012.09.009 – volume: 80 year: 2022 ident: CR55 article-title: Score-based diffusion models for accelerated MRI publication-title: Med Image Anal doi: 10.1016/j.media.2022.102479 – ident: CR42 – volume: 6 start-page: 60 year: 2019 ident: CR18 article-title: A survey on image data augmentation for deep learning publication-title: J Big Data doi: 10.1186/s40537-019-0197-0 – volume: 41 start-page: 1747 year: 2022 end-page: 1763 ident: CR22 article-title: Unsupervised MRI reconstruction via zero-shot learned adversarial transformers publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2022.3147426 – volume: 84 start-page: 1389 year: 2021 end-page: 1399 ident: CR31 article-title: Brain tumor segmentation using K-means clustering and deep learning with synthetic data augmentation for classification publication-title: Microsc Res Tech doi: 10.1002/jemt.23694 – volume: 80 start-page: 1189 year: 2018 end-page: 1205 ident: CR20 article-title: Deep learning with domain adaptation for accelerated projection-reconstruction MR publication-title: Magn Reson Med doi: 10.1002/mrm.27106 – ident: CR50 – volume: 3 start-page: 9 year: 2016 ident: CR19 article-title: A survey of transfer learning publication-title: J Big Data doi: 10.1186/s40537-016-0043-6 – volume: 41 start-page: 3167 year: 2022 end-page: 3181 ident: CR35 article-title: MOdel-based synthetic data-driven learning (MOST-DL): application in single-shot T2 mapping with severe head motion using overlapping-echo acquisition publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2022.3179981 – volume: 58 start-page: 28 year: 2023 end-page: 42 ident: CR12 article-title: Artificial intelligence-driven ultra-fast superresolution MRI : 10-fold accelerated musculoskeletal turbo spin echo MRI within reach publication-title: Invest Radiol doi: 10.1097/RLI.0000000000000928 – ident: CR57 – ident: CR36 – year: 2018 ident: CR60 article-title: Progressive growing of GANs for improved Quality, Stability, and Variation publication-title: [cs.NE] doi: 10.48550/arXiv.1710.10196 – ident: CR26 – volume: 81 start-page: 116 year: 2019 end-page: 128 ident: CR6 article-title: Assessment of the generalization of learned image reconstruction and the potential for transfer learning publication-title: Magn Reson Med doi: 10.1002/mrm.27355 – volume: 37 start-page: 117 year: 2020 end-page: 127 ident: CR8 article-title: Compressed sensing: from research to clinical practice with deep neural networks: shortening scan times for magnetic resonance imaging publication-title: IEEE Signal Process Mag doi: 10.1109/MSP.2019.2950433 – ident: CR43 – ident: CR47 – year: 2015 ident: CR59 publication-title: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th international conference, Munich, Germany, October 5–9, 2015, proceedings, part III 18 – start-page: 66 year: 2022 end-page: 78 ident: CR37 article-title: Morphology-Preserving Autoregressive 3D Generative Modelling of the Brain publication-title: Simul – volume: 86 start-page: 1859 year: 2021 end-page: 1872 ident: CR15 article-title: Systematic evaluation of iterative deep neural networks for fast parallel MRI reconstruction with sensitivity-weighted coil combination publication-title: Magn Reson Med doi: 10.1002/mrm.28827 – ident: CR53 – ident: CR30 – volume: 40 start-page: 2306 year: 2021 end-page: 2317 ident: CR9 article-title: Results of the 2020 fastMRI challenge for machine learning MR image reconstruction publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2021.3075856 – volume: 34 start-page: 911 year: 1963 end-page: 934 ident: CR61 article-title: Maximum Entropy for hypothesis formulation, especially for multidimensional contingency tables publication-title: Ann Math Stat doi: 10.1214/aoms/1177704014 – volume: 13 start-page: 600 year: 2004 end-page: 612 ident: CR45 article-title: Image quality assessment: from error visibility to structural similarity publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2003.819861 – volume: 58 start-page: 1182 year: 2007 end-page: 1195 ident: CR3 article-title: Sparse MRI: the application of compressed sensing for rapid MR imaging publication-title: Magn Reson Med doi: 10.1002/mrm.21391 – ident: CR27 – start-page: 71 year: 2019 end-page: 79 ident: CR14 article-title: Joint Multi-anatomy Training of a Variational Network for Reconstruction of Accelerated Magnetic Resonance Image Acquisitions publication-title: Mach – volume: 84 start-page: 3054 year: 2020 end-page: 3070 ident: CR7 article-title: Advancing machine learning for MR image reconstruction with an open competition: overview of the 2019 fastMRI challenge publication-title: Magn Reson Med doi: 10.1002/mrm.28338 – year: 2016 ident: CR49 article-title: Autoencoding beyond pixels using a learned similarity metric publication-title: International conference on machine learning – ident: CR44 – volume: 38 start-page: 394 year: 2019 end-page: 405 ident: CR5 article-title: MoDL: model-based deep learning architecture for inverse problems publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2018.2865356 – ident: CR48 – volume: 42 start-page: 952 year: 1999 end-page: 962 ident: CR1 article-title: SENSE: sensitivity encoding for fast MRI publication-title: Magn Reson Med doi: 10.1002/(SICI)1522-2594(199911)42:5<952::AID-MRM16>3.0.CO;2-S – volume: 307 start-page: e220425 year: 2023 ident: CR11 article-title: Deep learning reconstruction enables prospectively accelerated clinical knee MRI publication-title: Radiology doi: 10.1148/radiol.220425 – volume: 26 start-page: 174 year: 2022 end-page: 187 ident: CR32 article-title: Next-generation deep learning based on simulators and synthetic data publication-title: Trends Cogn Sci doi: 10.1016/j.tics.2021.11.008 – ident: CR38 – ident: CR52 – ident: CR17 – volume: 10 year: 2023 ident: CR40 article-title: Impact of GAN artifacts for simulating mammograms on identifying mammographically occult cancer publication-title: J Med Imaging doi: 10.1117/1.JMI.10.5.054503 – ident: CR13 – ident: CR34 – volume: 10 start-page: 358 year: 2023 ident: CR25 article-title: Synthesizing complex-valued multicoil MRI data from magnitude-only images publication-title: Bioengineering doi: 10.3390/bioengineering10030358 – ident: CR28 – ident: CR41 – ident: CR62 – ident: CR24 – volume: 11 start-page: 1935 year: 2021 ident: CR23 article-title: MAGnitude-image-to-complex K-space (MAGIC-K) net: a data augmentation network for image reconstruction publication-title: Diagnostics doi: 10.3390/diagnostics11101935 – volume: 6 start-page: 60 year: 2019 ident: 1193_CR18 publication-title: J Big Data doi: 10.1186/s40537-019-0197-0 – volume: 37 start-page: 117 year: 2020 ident: 1193_CR8 publication-title: IEEE Signal Process Mag doi: 10.1109/MSP.2019.2950433 – ident: 1193_CR44 doi: 10.48550/arXiv.2004.06688 – volume-title: International conference on machine learning year: 2016 ident: 1193_CR49 – volume: 13 start-page: 600 year: 2004 ident: 1193_CR45 publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2003.819861 – ident: 1193_CR24 doi: 10.48550/arXiv.2307.13220 – volume: 42 start-page: 952 year: 1999 ident: 1193_CR1 publication-title: Magn Reson Med doi: 10.1002/(SICI)1522-2594(199911)42:5<952::AID-MRM16>3.0.CO;2-S – volume: 80 start-page: 1189 year: 2018 ident: 1193_CR20 publication-title: Magn Reson Med doi: 10.1002/mrm.27106 – volume: 26 start-page: 174 year: 2022 ident: 1193_CR32 publication-title: Trends Cogn Sci doi: 10.1016/j.tics.2021.11.008 – volume-title: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th international conference, Munich, Germany, October 5–9, 2015, proceedings, part III 18 year: 2015 ident: 1193_CR59 – volume: 86 start-page: 1859 year: 2021 ident: 1193_CR15 publication-title: Magn Reson Med doi: 10.1002/mrm.28827 – volume: 84 start-page: 663 year: 2020 ident: 1193_CR21 publication-title: Magn Reson Med doi: 10.1002/mrm.28148 – volume: 40 start-page: 2306 year: 2021 ident: 1193_CR9 publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2021.3075856 – ident: 1193_CR48 – volume: 84 start-page: 3054 year: 2020 ident: 1193_CR7 publication-title: Magn Reson Med doi: 10.1002/mrm.28338 – ident: 1193_CR16 doi: 10.48550/arXiv.2312.10271 – ident: 1193_CR30 doi: 10.48550/arXiv.1909.11512 – ident: 1193_CR42 doi: 10.48550/arXiv.1511.05644 – volume: 42 start-page: 3524 year: 2023 ident: 1193_CR56 publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2023.3290149 – volume: 47 start-page: 1202 year: 2002 ident: 1193_CR2 publication-title: Magn Reson Med doi: 10.1002/mrm.10171 – volume: 81 start-page: 116 year: 2019 ident: 1193_CR6 publication-title: Magn Reson Med doi: 10.1002/mrm.27355 – ident: 1193_CR17 – year: 2018 ident: 1193_CR60 publication-title: [cs.NE] doi: 10.48550/arXiv.1710.10196 – volume: 58 start-page: 28 year: 2023 ident: 1193_CR12 publication-title: Invest Radiol doi: 10.1097/RLI.0000000000000928 – volume: 31 start-page: 596 year: 2013 ident: 1193_CR46 publication-title: Magn Reson Imaging doi: 10.1016/j.mri.2012.09.009 – volume: 34 start-page: 911 year: 1963 ident: 1193_CR61 publication-title: Ann Math Stat doi: 10.1214/aoms/1177704014 – ident: 1193_CR62 – volume: 555 start-page: 487 year: 2018 ident: 1193_CR4 publication-title: Nature doi: 10.1038/nature25988 – ident: 1193_CR36 doi: 10.48550/arXiv.2106.13199 – ident: 1193_CR38 – ident: 1193_CR52 doi: 10.48550/arXiv.2112.10752 – start-page: 66 volume-title: Simul year: 2022 ident: 1193_CR37 – ident: 1193_CR39 doi: 10.1109/CVPR42600.2020.00872 – start-page: 71 volume-title: Mach year: 2019 ident: 1193_CR14 – ident: 1193_CR57 doi: 10.1109/ICCV.2019.00460 – volume: 41 start-page: 3167 year: 2022 ident: 1193_CR35 publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2022.3179981 – ident: 1193_CR50 doi: 10.48550/arXiv.2006.11239 – start-page: 1 volume-title: Simul year: 2018 ident: 1193_CR33 – ident: 1193_CR27 doi: 10.1109/CVPRW.2018.00143 – ident: 1193_CR34 doi: 10.1007/978-3-031-26438-2_12 – ident: 1193_CR41 doi: 10.1109/CVPR.2017.632 – volume: 38 start-page: 394 year: 2019 ident: 1193_CR5 publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2018.2865356 – ident: 1193_CR53 doi: 10.48550/arXiv.2111.05826 – volume: 10 year: 2023 ident: 1193_CR40 publication-title: J Med Imaging doi: 10.1117/1.JMI.10.5.054503 – ident: 1193_CR47 doi: 10.1109/CVPR.2019.00020 – ident: 1193_CR28 doi: 10.48550/arXiv.1910.07113 – volume: 307 start-page: e220425 year: 2023 ident: 1193_CR11 publication-title: Radiology doi: 10.1148/radiol.220425 – volume: 3 start-page: 9 year: 2016 ident: 1193_CR19 publication-title: J Big Data doi: 10.1186/s40537-016-0043-6 – volume: 84 start-page: 1389 year: 2021 ident: 1193_CR31 publication-title: Microsc Res Tech doi: 10.1002/jemt.23694 – volume: 58 start-page: 1182 year: 2007 ident: 1193_CR3 publication-title: Magn Reson Med doi: 10.1002/mrm.21391 – ident: 1193_CR29 doi: 10.48550/arXiv.1911.08716 – volume: 86 start-page: 2278 year: 1998 ident: 1193_CR58 publication-title: Proc IEEE doi: 10.1109/5.726791 – volume: 11 start-page: 1935 year: 2021 ident: 1193_CR23 publication-title: Diagnostics doi: 10.3390/diagnostics11101935 – ident: 1193_CR54 – volume: 303 start-page: 373 year: 2022 ident: 1193_CR10 publication-title: Radiology doi: 10.1148/radiol.204097 – volume: 41 start-page: 1747 year: 2022 ident: 1193_CR22 publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2022.3147426 – ident: 1193_CR13 doi: 10.48550/arXiv.1811.08839 – volume: 10 start-page: 358 year: 2023 ident: 1193_CR25 publication-title: Bioengineering doi: 10.3390/bioengineering10030358 – ident: 1193_CR43 – ident: 1193_CR26 doi: 10.48550/arXiv.2109.08237 – ident: 1193_CR51 doi: 10.48550/arXiv.2204.06125 – volume: 80 year: 2022 ident: 1193_CR55 publication-title: Med Image Anal doi: 10.1016/j.media.2022.102479
SSID	ssj0021503
Score	2.3915968
Snippet	Object Deep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw... Deep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw data is...
SourceID	pubmedcentral proquest pubmed crossref springer
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	1059
SubjectTerms	Algorithms Basic Science - Reconstruction algorithms and artificial intelligence Biomedical Engineering and Bioengineering Brain - diagnostic imaging Computer Appl. in Life Sciences Deep Learning Health Informatics Humans Image Processing, Computer-Assisted - methods Imaging Magnetic Resonance Imaging - methods Medicine Medicine & Public Health Neural Networks, Computer Radiology Research Article Solid State Physics
Title	Deep-learning-based image reconstruction with limited data: generating synthetic raw data using deep learning
URI	https://link.springer.com/article/10.1007/s10334-024-01193-4 https://www.ncbi.nlm.nih.gov/pubmed/39207581 https://www.proquest.com/docview/3099797239 https://pubmed.ncbi.nlm.nih.gov/PMC11582256
Volume	37
WOSCitedRecordID	wos001302322900001&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: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 1352-8661 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0021503 issn: 1352-8661 databaseCode: RSV dateStart: 19970101 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1ZT9wwEB5xVIgXoAcQLrlS31pLTZzENm8IWPEACPVY7VuUOM6yEptFhEP8e2aco90uWqm8-opljz2fMzPfAHyxRkdRHvhcFbgNRHHOiWaMx3Gk_ULHRexyHfbP5eWlGgz0VRMUVrXe7q1J0t3UfwW7CRFy1CmceMoEDxdhGdWdooQNP372u2cWQhzRhMe83m9aBc3gyln3yH9spE719NbfNukNWGugJjuqZeM9LNjyA6xcNMb0jzA-sfaWN2kjhpz0Wc5GY7xgmHsmd9SyjH7Wsps6FIqRT-khGzq6avKZZtVziSgSP8Lu0idXzcibfshyHJ-143-C373TX8dnvMm-wE0YynseSquLTItMKVEEeWYCEWVYYn0lsSQnsBcYmaJCkxZfRWGqTGDxOaNR4-dxJjZhqZyUdhuYn0vEpUrjgUf49T1IM1MUfm4pBXmgjfTAbzckMQ01OWXIuEn-kCrTOia4jolbxyT04GvX57Ym5pjb-nO7zwmeHzKKpKWdPFSJoNBhSr2mPdiq970bD7EjIirle6CmJKJrQNzc0zXl6NpxdCPQRugVxR58awUjaW6Has48d_6v-S6sBiRbzr1mD5ZQLuw-vDOP96Pq7gAW5UAduMPxAjNuCQc
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT9wwEB6VbQVcKJRXoAUj9QaWSJyHzQ3RIiqWFWoBcbMSx1lWgrAiPMS_Z8abBLZUSOXqVyx77PmcmfkG4Ls1KorywOeywG0ginNONGM8jiPlFyouYpfr8Kyb9Hry_Fwd10FhVePt3pgk3U39IthNiJCjTuHEUyZ4OAEfQ9RYxJj_-89Z-8xCiCPq8Jh_9xtXQa9w5Wv3yL9spE717H9-36RnYaaGmmx3JBtz8MGWX2DyqDamz8PVD2uHvE4b0eekz3I2uMILhrlncksty-hnLbschUIx8indYX1HV00-06x6LBFF4kfYTfrgqhl50_dZjuOzZvwFON3_ebJ3wOvsC9yEYXLLw8SqIlMik1IUQZ6ZQEQZllhfJliSE9gLTJKiQkssvorCVJrA4nNGocbP40wsQqe8Lu0yMD9PEJdKhQce4dd2kGamKPzcUgryQJnEA7_ZEG1qanLKkHGpn0mVaR01rqN266hDDzbbPsMRMcebrTeafdZ4fsgokpb2-q7SgkKHKfWa8mBptO_teIgdEVFJ3wM5JhFtA-LmHq8pBxeOoxuBNkKvKPZgqxEMXd8O1RvzXPm_5uswdXBy1NXdX73DVZgOSM6cq81X6KCM2G_wydzfDqqbNXdEngBobgsD
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT9wwEB61FCEulFJa0hYwEjdq0cR52L1VpSsQsELiIW5WYjvblSCs2AXUf98Z51EWEBLq1a8k9tjzTTzzDcCmMypJbBRyWeIyEMU5J5oxnqaJCkuVlqnPdXh2kPX78vxcHd2L4vfe7u2VZB3TQCxN1WR7ZMvte4FvQsQc9QsnzjLB49fwJiZHerLXj886kwvhjmhCZZ7uN62OHmHMx66SD-5LvRrqvf3_D1iEhQaCsh-1zLyDV65agrnD5pL9PVzuODfiTTqJASc9Z9nwEg8e5s3njnKW0U9cdlGHSDHyNf3OBp7Gmnyp2fhPhegSH8Ku8ztfzcjLfsAsjs_a8ZfhtPfr5Ocub7IycBPH2YTHmVNloUQhpSgjW5hIJAWWuFBmWGIJBEYmy1HRZQ6tpTiXJnJo5ihEAjYtxAeYqa4qtwIstBniVanwIEBY9i3KC1OWoXWUmjxSJgsgbBdHm4aynDJnXOh_ZMs0jxrnUft51HEAW12fUU3Y8WzrjXbNNe4ruizJK3d1M9aCQoopJZsK4GMtA914iCkRackwADklHV0D4uyerqmGvz13NwJwhGRJGsDXVkh0c2qMn3nPTy9rvg5zRzs9fbDX3_8M8xGJmffA-QIzKCJuFWbN7WQ4vl7zu-UvGC0T5w
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=Deep-learning-based+image+reconstruction+with+limited+data%3A+generating+synthetic+raw+data+using+deep+learning&rft.jtitle=Magma+%28New+York%2C+N.Y.%29&rft.au=Zijlstra%2C+Frank&rft.au=While%2C+Peter+Thomas&rft.date=2024-12-01&rft.eissn=1352-8661&rft.volume=37&rft.issue=6&rft.spage=1059&rft_id=info:doi/10.1007%2Fs10334-024-01193-4&rft_id=info%3Apmid%2F39207581&rft.externalDocID=39207581
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1352-8661&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1352-8661&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1352-8661&client=summon