Learning to deep learning: statistics and a paradigm test in selecting a UNet architecture to enhance MRI

Objective This study aims to assess the statistical significance of training parameters in 240 dense UNets (DUNets) used for enhancing low Signal-to-Noise Ratio (SNR) and undersampled MRI in various acquisition protocols. The objective is to determine the validity of differences between different DU...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Magma (New York, N.Y.) Jg. 37; H. 3; S. 507 - 528
Hauptverfasser:	Sharma, Rishabh, Tsiamyrtzis, Panagiotis, Webb, Andrew G., Leiss, Ernst L., Tsekos, Nikolaos V.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Cham Springer International Publishing 01.07.2024
Schlagworte:	Algorithms Analysis of Variance 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 Enhancement - methods Image Processing, Computer-Assisted - methods Imaging Magnetic Resonance Imaging - methods Medicine Medicine & Public Health Neural Networks, Computer Radiology Reproducibility of Results Research Article Signal-To-Noise Ratio Solid State Physics Deep learning Statistical significance Mixed effects modeling Enhance UNet Undersampled
ISSN:	1352-8661, 1352-8661
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Objective This study aims to assess the statistical significance of training parameters in 240 dense UNets (DUNets) used for enhancing low Signal-to-Noise Ratio (SNR) and undersampled MRI in various acquisition protocols. The objective is to determine the validity of differences between different DUNet configurations and their impact on image quality metrics. Materials and Methods To achieve this, we trained all DUNets using the same learning rate and number of epochs, with variations in 5 acquisition protocols, 24 loss function weightings, and 2 ground truths. We calculated evaluation metrics for two metric regions of interest (ROI). We employed both Analysis of Variance (ANOVA) and Mixed Effects Model (MEM) to assess the statistical significance of the independent parameters, aiming to compare their efficacy in revealing differences and interactions among fixed parameters. Results ANOVA analysis showed that, except for the acquisition protocol, fixed variables were statistically insignificant. In contrast, MEM analysis revealed that all fixed parameters and their interactions held statistical significance. This emphasizes the need for advanced statistical analysis in comparative studies, where MEM can uncover finer distinctions often overlooked by ANOVA. Discussion These findings highlight the importance of utilizing appropriate statistical analysis when comparing different deep learning models. Additionally, the surprising effectiveness of the UNet architecture in enhancing various acquisition protocols underscores the potential for developing improved methods for characterizing and training deep learning models. This study serves as a stepping stone toward enhancing the transparency and comparability of deep learning techniques for medical imaging applications.
AbstractList	Objective This study aims to assess the statistical significance of training parameters in 240 dense UNets (DUNets) used for enhancing low Signal-to-Noise Ratio (SNR) and undersampled MRI in various acquisition protocols. The objective is to determine the validity of differences between different DUNet configurations and their impact on image quality metrics. Materials and Methods To achieve this, we trained all DUNets using the same learning rate and number of epochs, with variations in 5 acquisition protocols, 24 loss function weightings, and 2 ground truths. We calculated evaluation metrics for two metric regions of interest (ROI). We employed both Analysis of Variance (ANOVA) and Mixed Effects Model (MEM) to assess the statistical significance of the independent parameters, aiming to compare their efficacy in revealing differences and interactions among fixed parameters. Results ANOVA analysis showed that, except for the acquisition protocol, fixed variables were statistically insignificant. In contrast, MEM analysis revealed that all fixed parameters and their interactions held statistical significance. This emphasizes the need for advanced statistical analysis in comparative studies, where MEM can uncover finer distinctions often overlooked by ANOVA. Discussion These findings highlight the importance of utilizing appropriate statistical analysis when comparing different deep learning models. Additionally, the surprising effectiveness of the UNet architecture in enhancing various acquisition protocols underscores the potential for developing improved methods for characterizing and training deep learning models. This study serves as a stepping stone toward enhancing the transparency and comparability of deep learning techniques for medical imaging applications. This study aims to assess the statistical significance of training parameters in 240 dense UNets (DUNets) used for enhancing low Signal-to-Noise Ratio (SNR) and undersampled MRI in various acquisition protocols. The objective is to determine the validity of differences between different DUNet configurations and their impact on image quality metrics.OBJECTIVEThis study aims to assess the statistical significance of training parameters in 240 dense UNets (DUNets) used for enhancing low Signal-to-Noise Ratio (SNR) and undersampled MRI in various acquisition protocols. The objective is to determine the validity of differences between different DUNet configurations and their impact on image quality metrics.To achieve this, we trained all DUNets using the same learning rate and number of epochs, with variations in 5 acquisition protocols, 24 loss function weightings, and 2 ground truths. We calculated evaluation metrics for two metric regions of interest (ROI). We employed both Analysis of Variance (ANOVA) and Mixed Effects Model (MEM) to assess the statistical significance of the independent parameters, aiming to compare their efficacy in revealing differences and interactions among fixed parameters.MATERIALS AND METHODSTo achieve this, we trained all DUNets using the same learning rate and number of epochs, with variations in 5 acquisition protocols, 24 loss function weightings, and 2 ground truths. We calculated evaluation metrics for two metric regions of interest (ROI). We employed both Analysis of Variance (ANOVA) and Mixed Effects Model (MEM) to assess the statistical significance of the independent parameters, aiming to compare their efficacy in revealing differences and interactions among fixed parameters.ANOVA analysis showed that, except for the acquisition protocol, fixed variables were statistically insignificant. In contrast, MEM analysis revealed that all fixed parameters and their interactions held statistical significance. This emphasizes the need for advanced statistical analysis in comparative studies, where MEM can uncover finer distinctions often overlooked by ANOVA.RESULTSANOVA analysis showed that, except for the acquisition protocol, fixed variables were statistically insignificant. In contrast, MEM analysis revealed that all fixed parameters and their interactions held statistical significance. This emphasizes the need for advanced statistical analysis in comparative studies, where MEM can uncover finer distinctions often overlooked by ANOVA.These findings highlight the importance of utilizing appropriate statistical analysis when comparing different deep learning models. Additionally, the surprising effectiveness of the UNet architecture in enhancing various acquisition protocols underscores the potential for developing improved methods for characterizing and training deep learning models. This study serves as a stepping stone toward enhancing the transparency and comparability of deep learning techniques for medical imaging applications.DISCUSSIONThese findings highlight the importance of utilizing appropriate statistical analysis when comparing different deep learning models. Additionally, the surprising effectiveness of the UNet architecture in enhancing various acquisition protocols underscores the potential for developing improved methods for characterizing and training deep learning models. This study serves as a stepping stone toward enhancing the transparency and comparability of deep learning techniques for medical imaging applications. This study aims to assess the statistical significance of training parameters in 240 dense UNets (DUNets) used for enhancing low Signal-to-Noise Ratio (SNR) and undersampled MRI in various acquisition protocols. The objective is to determine the validity of differences between different DUNet configurations and their impact on image quality metrics. To achieve this, we trained all DUNets using the same learning rate and number of epochs, with variations in 5 acquisition protocols, 24 loss function weightings, and 2 ground truths. We calculated evaluation metrics for two metric regions of interest (ROI). We employed both Analysis of Variance (ANOVA) and Mixed Effects Model (MEM) to assess the statistical significance of the independent parameters, aiming to compare their efficacy in revealing differences and interactions among fixed parameters. ANOVA analysis showed that, except for the acquisition protocol, fixed variables were statistically insignificant. In contrast, MEM analysis revealed that all fixed parameters and their interactions held statistical significance. This emphasizes the need for advanced statistical analysis in comparative studies, where MEM can uncover finer distinctions often overlooked by ANOVA. These findings highlight the importance of utilizing appropriate statistical analysis when comparing different deep learning models. Additionally, the surprising effectiveness of the UNet architecture in enhancing various acquisition protocols underscores the potential for developing improved methods for characterizing and training deep learning models. This study serves as a stepping stone toward enhancing the transparency and comparability of deep learning techniques for medical imaging applications.
Author	Sharma, Rishabh Leiss, Ernst L. Tsekos, Nikolaos V. Tsiamyrtzis, Panagiotis Webb, Andrew G.
Author_xml	– sequence: 1 givenname: Rishabh surname: Sharma fullname: Sharma, Rishabh organization: Medical Robotics and Imaging Lab, Department of Computer Science, 501, Philip G. Hoffman Hall, University of Houston – sequence: 2 givenname: Panagiotis surname: Tsiamyrtzis fullname: Tsiamyrtzis, Panagiotis organization: Department of Mechanical Engineering, Politecnico Di Milano, Department of Statistics, Athens University of Economics and Business – sequence: 3 givenname: Andrew G. surname: Webb fullname: Webb, Andrew G. organization: C.J. Gorter Center for High Field MRI, Department of Radiology, Leiden University Medical Center – sequence: 4 givenname: Ernst L. surname: Leiss fullname: Leiss, Ernst L. organization: Department of Computer Science, University of Houston – sequence: 5 givenname: Nikolaos V. surname: Tsekos fullname: Tsekos, Nikolaos V. email: nvtsekos@central.uh.edu organization: Medical Robotics and Imaging Lab, Department of Computer Science, 501, Philip G. Hoffman Hall, University of Houston
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/37989921$$D View this record in MEDLINE/PubMed
BookMark	eNp9kctOxCAUhonReH8BF4almyqXQqk7Y7xMMmpinDWh9HTEdOgIdOHbyzijMS5cQU6-70D-_wBt-8EDQieUnFNCqotICedlQRgvCKWsKuQW2qdcsEJJSbd_3ffQQYxvhDAqCN9Fe7yqVV0zuo_cFEzwzs9xGnALsMT9ZnCJYzLJxeRsxMa32OClCaZ18wVOEBN2HkfowaaVbfDsERI2wb66lGdjgNVG8K_GW8APz5MjtNOZPsLx5jxEs9ubl-v7Yvp0N7m-mhaW1zQV1hohGKVGdaqsWhBl13LGhFXQtLWVTJCuapuaNKqSpbSZEY1UklpFm7Ir-SE6W-9dhuF9zB_VCxct9L3xMIxRM1UzKZRkKqOnG3RsFtDqZXALEz70dzwZYGvAhiHGAN0PQoledaDXHejcgf7qQMssqT-SdaskB5-Ccf3_Kl-rMb_j5xD02zAGn-P6z_oEL_qadw
CitedBy_id	crossref_primary_10_1007_s10334_024_01179_2 crossref_primary_10_1088_1361_6560_ad94c7 crossref_primary_10_1007_s44352_025_00012_3 crossref_primary_10_1007_s10278_024_01205_8
Cites_doi	10.1109/TMI.2014.2377694 10.1016/j.compmedimag.2018.10.005 10.3389/fcvm.2020.00017 10.1109/JBHI.2019.2912935 10.1016/j.patcog.2019.107038 10.1002/mp.12600 10.1109/TIP.2003.819861 10.1002/mrm.28117 10.21037/qims.2019.08.10 10.1109/TMI.2019.2927101 10.1002/mrm.28733 10.3389/fonc.2019.01010 10.1038/nature14539 10.1162/jocn.2007.19.9.1498 10.1109/TIP.2019.2895768 10.1016/j.cviu.2021.103329 10.1016/j.media.2023.102872 10.21037/qims-19-1090 10.1002/jmri.26534 10.1109/TBME.2018.2821699 10.1002/mrm.28962 10.1002/jmri.27585 10.1109/TMI.2022.3147426 10.1007/s10278-017-9983-4 10.1002/mrm.27690 10.1002/mrm.28274 10.1148/radiol.2020192173 10.1109/TCI.2020.2964201 10.1016/j.mri.2019.07.010 10.1007/s10334-022-01041-3 10.1002/mp.14006 10.3390/app122211758 10.3390/app10061902 10.1007/b98882 10.1002/mrm.27106 10.1109/TCI.2016.2644865 10.1109/TMI.2017.2785879 10.1109/TMI.2020.2974858 10.1002/mrm.28148 10.1088/1361-6560/aac71a 10.1038/s41598-020-70479-z 10.1016/j.compbiomed.2021.105010 10.1016/j.ejrad.2020.109430 10.1038/s41598-021-87482-7 10.1002/jmri.27078 10.1109/MSP.2019.2950433 10.3390/s22051766 10.1016/j.mri.2020.04.007 10.1109/CVPR42600.2020.01284 10.1109/ICCVW54120.2021.00217 10.1109/TSP.2019.8768829 10.1007/978-3-319-24574-4_28 10.1109/CVPR.2015.7298594 10.18653/v1/P19-1266 10.1109/CVPRW.2019.00073 10.1109/VCIP.2017.8305143 10.23919/EUSIPCO54536.2021.9615963 10.1007/978-3-030-88081-1_60 10.1007/978-3-030-59861-7_64 10.1109/CVPR.2016.90 10.1007/978-3-030-33843-5_6 10.1007/978-3-030-11021-5_20 10.1109/ICASSP.2018.8461664 10.1007/978-3-031-43999-5_47 10.1109/NAECON46414.2019.9057834 10.1007/978-3-030-11726-9_21 10.1117/12.2513158 10.1007/978-3-030-00928-1_11
ContentType	Journal Article
Copyright	The Author(s), under exclusive licence to European Society for Magnetic Resonance in Medicine and Biology (ESMRMB) 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. 2023. The Author(s), under exclusive licence to European Society for Magnetic Resonance in Medicine and Biology (ESMRMB).
Copyright_xml	– notice: The Author(s), under exclusive licence to European Society for Magnetic Resonance in Medicine and Biology (ESMRMB) 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. – notice: 2023. The Author(s), under exclusive licence to European Society for Magnetic Resonance in Medicine and Biology (ESMRMB).
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8
DOI	10.1007/s10334-023-01127-6
DatabaseName	CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic MEDLINE
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	528
ExternalDocumentID	37989921 10_1007_s10334_023_01127_6
Genre	Journal Article
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 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
ID	FETCH-LOGICAL-c391t-cca55211a8f847de54fd3225c8ebd9c6250f7db90b87646c47d5b6861c81b4f43
IEDL.DBID	RSV
ISICitedReferencesCount	6
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001107753200001&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
IngestDate	Fri Sep 05 09:01:58 EDT 2025 Mon Jul 21 05:43:39 EDT 2025 Sat Nov 29 03:00:50 EST 2025 Tue Nov 18 22:18:17 EST 2025 Fri Feb 21 02:38:25 EST 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	3
Keywords	Deep learning Statistical significance Mixed effects modeling Enhance UNet Undersampled
Language	English
License	2023. The Author(s), under exclusive licence to European Society for Magnetic Resonance in Medicine and Biology (ESMRMB).
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c391t-cca55211a8f847de54fd3225c8ebd9c6250f7db90b87646c47d5b6861c81b4f43
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
OpenAccessLink	https://link.springer.com/content/pdf/10.1007/s10334-023-01127-6.pdf
PMID	37989921
PQID	2892658628
PQPubID	23479
PageCount	22
ParticipantIDs	proquest_miscellaneous_2892658628 pubmed_primary_37989921 crossref_primary_10_1007_s10334_023_01127_6 crossref_citationtrail_10_1007_s10334_023_01127_6 springer_journals_10_1007_s10334_023_01127_6
PublicationCentury	2000
PublicationDate	2024-07-01
PublicationDateYYYYMMDD	2024-07-01
PublicationDate_xml	– month: 07 year: 2024 text: 2024-07-01 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	Aghabiglou, Eksioglu (CR47) 2021; 139 Yang, Yu, Dong, Slabaugh, Dragotti, Ye, Liu, Arridge, Keegan, Guo, Firmin (CR29) 2018; 37 Dar, Özbey, Çatlı, Çukur (CR77) 2020; 84 Cuocolo, Comelli, Stefano, Benfante, Dahiya, Stanzione, Castaldo, De Lucia, Yezzi, Imbriaco (CR35) 2021; 54 CR39 CR38 CR37 Lyu, Shan, Steber, Helis, Whitlow, Chan, Wang (CR57) 2020; 39 Cole, Cheng, Pauly, Vasanawala (CR18) 2021; 86 CR32 CR31 Borji (CR72) 2022; 215 CR75 CR74 CR73 CR70 Sandino, Cheng, Chen, Mardani, Pauly, Vasanawala (CR5) 2020; 37 Lee, Yoo, Tak, Ye (CR9) 2018; 65 Glang, Deshmane, Prokudin, Martin, Herz, Lindig, Bender, Scheffler, Zaiss (CR20) 2020; 84 Zhao, Gallo, Frosio, Kautz (CR24) 2017; 3 Zaiss, Deshmane, Schuppert, Herz, Glang, Ehses, Lindig, Bender, Ernemann, Scheffler (CR21) 2019; 81 Wahlang, Maji, Saha, Chakrabarti, Jasinski, Leonowicz, Jasinska (CR34) 2022; 22 Korkmaz, Dar, Yurt, Ozbey, Cukur (CR78) 2022; 41 Kwon, Kim, Park (CR7) 2017; 44 Pinheiro, Bates (CR36) 2000 CR48 CR46 Ottesen, Caan, Groote, Bjørnerud (CR11) 2023; 36 CR44 Lin, Johnson, Knoll, Lui (CR25) 2021; 53 CR43 Ghodrati, Shao, Bydder, Zhou, Yin, Nguyen, Yang, Hu (CR50) 2019; 9 CR42 CR41 Marcus, Wang, Parker, Csernansky, Morris, Buckner (CR66) 2007; 19 Mazurowski, Buda, Saha, Bashir (CR1) 2019; 49 Han, Yoo, Kim, Shin, Sung, Ye (CR8) 2018; 80 Luo, Zhao, Jiang, Hui, Cao (CR30) 2020; 84 Koonjoo, Zhu, Bagnall, Bhutto, Rosen (CR62) 2021 Cai, Tian, Lui, Zeng, Wu, Chen (CR69) 2020; 10 Bressem, Adams, Erxleben, Hamm, Niehues, Vahldiek (CR76) 2020; 10 Do, Seo, Han, Ye, Choi, Park (CR4) 2020; 47 CR15 Mahapatra, Bozorgtabar, Garnavi (CR16) 2019; 71 Iqbal, Nguyen, Hangel, Motyka, Bogner, Jiang (CR19) 2019 CR56 CR55 CR54 Fuin, Bustin, Küstner, Oksuz, Clough, King, Schnabel, Botnar, Prieto (CR6) 2020; 70 CR53 Güngör, Dar, Öztürk, Korkmaz, Bedel, Elmas, Ozbey, Çukur (CR79) 2023; 88 Ueda, Ohno, Yamamoto, Iwase, Fukuba, Hanamatsu, Obama, Ikeda, Ikedo, Yui, Murayama, Toyama (CR3) 2021; 134 CR52 CR51 Sun, Fan, Ding, Huang, Paisley (CR64) 2019; 63 Akkus, Galimzianova, Hoogi, Rubin, Erickson (CR2) 2017; 30 Lyu, Shan, Wang (CR17) 2020; 6 Hashimoto, Ote, Oida, Teramoto, Ouchi (CR12) 2020; 10 Qiu, Chen, Ma, Fan, Moser, Maya, Christodoulou, Xie, Li (CR58) 2022; 87 LeCun, Bengio, Hinton (CR22) 2015; 521 Hyun, Kim, Lee, Lee, Seo (CR14) 2018; 63 Guan, Khan, Sikdar, Chitnis (CR45) 2020; 24 Li, Anwar, Porikli (CR59) 2020; 98 CR28 Wang, Bovik, Sheikh, Simoncelli (CR65) 2004; 13 CR27 Bustin, Fuin, Botnar, Prieto (CR13) 2020 CR26 Sharma, Tsiamyrtzis, Webb, Seimenis, Loukas, Leiss, Tsekos (CR49) 2022; 12 Abdollahi, Pradhan (CR60) 2021; 6 Han, Sunwoo, Ye (CR10) 2020; 39 CR68 CR23 CR67 Menze, Jakab, Bauer, Kalpathy-Cramer, Farahani, Kirby, Burren, Porz, Slotboom, Wiest, Lanczi, Gerstner, Weber, Arbel, Avants, Ayache, Buendia, Collins, Cordier, Corso, Criminisi, Das, Delingette, Demiralp, Durst, Dojat, Doyle, Festa, Forbes, Geremia, Glocker, Golland, Guo, Hamamci, Iftekharuddin, Jena, John, Konukoglu, Lashkari, Mariz, Meier, Pereira, Precup, Price, Raviv, Reza, Ryan, Sarikaya, Schwartz, Shin, Shotton, Silva, Sousa, Subbanna, Szekely, Taylor, Thomas, Tustison, Unal, Vasseur, Wintermark, Ye, Zhao, Zhao, Zikic, Prastawa, Reyes, Van Leemput (CR33) 2015; 34 Masutani, Bahrami, Hsiao (CR40) 2020; 295 Lauzon, Asman, Crainiceanu, Caffo, Landman, Fichtinger, Martel, Peters (CR61) 2011 CR63 Lucas, Tapia, Molina, Katsaggelos (CR71) 2018 Q Lyu (1127_CR57) 2020; 39 KK Bressem (1127_CR76) 2020; 10 C Li (1127_CR59) 2020; 98 SUH Dar (1127_CR77) 2020; 84 A Aghabiglou (1127_CR47) 2021; 139 A Borji (1127_CR72) 2022; 215 A Güngör (1127_CR79) 2023; 88 1127_CR48 1127_CR46 1127_CR44 Z Akkus (1127_CR2) 2017; 30 1127_CR43 Y LeCun (1127_CR22) 2015; 521 1127_CR42 S Guan (1127_CR45) 2020; 24 1127_CR41 CM Sandino (1127_CR5) 2020; 37 D Mahapatra (1127_CR16) 2019; 71 N Koonjoo (1127_CR62) 2021 Q Lyu (1127_CR17) 2020; 6 Z Wang (1127_CR65) 2004; 13 EM Masutani (1127_CR40) 2020; 295 1127_CR15 Y Han (1127_CR8) 2018; 80 1127_CR56 1127_CR55 1127_CR54 W Do (1127_CR4) 2020; 47 1127_CR53 1127_CR52 1127_CR51 V Ghodrati (1127_CR50) 2019; 9 A Bustin (1127_CR13) 2020 JA Ottesen (1127_CR11) 2023; 36 S Qiu (1127_CR58) 2022; 87 S Cai (1127_CR69) 2020; 10 H Zhao (1127_CR24) 2017; 3 K Kwon (1127_CR7) 2017; 44 DS Marcus (1127_CR66) 2007; 19 1127_CR28 1127_CR27 A Abdollahi (1127_CR60) 2021; 6 1127_CR26 CB Lauzon (1127_CR61) 2011 1127_CR68 1127_CR23 1127_CR67 Z Iqbal (1127_CR19) 2019 R Cuocolo (1127_CR35) 2021; 54 1127_CR63 JC Pinheiro (1127_CR36) 2000 D Lee (1127_CR9) 2018; 65 G Luo (1127_CR30) 2020; 84 T Ueda (1127_CR3) 2021; 134 R Sharma (1127_CR49) 2022; 12 M Zaiss (1127_CR21) 2019; 81 A Lucas (1127_CR71) 2018 Y Han (1127_CR10) 2020; 39 BH Menze (1127_CR33) 2015; 34 1127_CR39 L Sun (1127_CR64) 2019; 63 N Fuin (1127_CR6) 2020; 70 1127_CR38 MA Mazurowski (1127_CR1) 2019; 49 1127_CR37 DJ Lin (1127_CR25) 2021; 53 CM Hyun (1127_CR14) 2018; 63 E Cole (1127_CR18) 2021; 86 1127_CR32 1127_CR31 1127_CR75 1127_CR74 1127_CR73 I Wahlang (1127_CR34) 2022; 22 G Yang (1127_CR29) 2018; 37 1127_CR70 Y Korkmaz (1127_CR78) 2022; 41 F Hashimoto (1127_CR12) 2020; 10 F Glang (1127_CR20) 2020; 84
References_xml	– volume: 34 start-page: 1993 year: 2015 end-page: 2024 ident: CR33 article-title: The multimodal brain tumor image segmentation benchmark (BRATS) publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2014.2377694 – ident: CR70 – volume: 71 start-page: 30 year: 2019 end-page: 39 ident: CR16 article-title: Image super-resolution using progressive generative adversarial networks for medical image analysis publication-title: Comput Med Imaging Graph doi: 10.1016/j.compmedimag.2018.10.005 – ident: CR68 – ident: CR74 – ident: CR39 – ident: CR51 – year: 2020 ident: CR13 article-title: From compressed-sensing to artificial intelligence-based cardiac MRI reconstruction publication-title: Front Cardiovasc Med doi: 10.3389/fcvm.2020.00017 – volume: 24 start-page: 568 year: 2020 end-page: 576 ident: CR45 article-title: Fully dense UNet for 2-D sparse photoacoustic tomography artifact removal publication-title: IEEE J Biomed Health Inform doi: 10.1109/JBHI.2019.2912935 – ident: CR54 – volume: 98 year: 2020 ident: CR59 article-title: Underwater scene prior inspired deep underwater image and video enhancement publication-title: Pattern Recognit doi: 10.1016/j.patcog.2019.107038 – volume: 44 start-page: 6209 year: 2017 end-page: 6224 ident: CR7 article-title: A parallel MR imaging method using multilayer perceptron publication-title: Med Phys doi: 10.1002/mp.12600 – volume: 13 start-page: 600 year: 2004 end-page: 612 ident: CR65 article-title: Image quality assessment: from error visibility to structural similarity publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2003.819861 – volume: 84 start-page: 450 year: 2020 end-page: 466 ident: CR20 article-title: DeepCEST 3T: Robust MRI parameter determination and uncertainty quantification with neural networks—application to CEST imaging of the human brain at 3T publication-title: Magn Reson Med doi: 10.1002/mrm.28117 – volume: 9 start-page: 1516 year: 2019 end-page: 1527 ident: CR50 article-title: MR image reconstruction using deep learning: evaluation of network structure and loss functions publication-title: Quant Imaging Med Surg doi: 10.21037/qims.2019.08.10 – volume: 39 start-page: 377 year: 2020 end-page: 386 ident: CR10 article-title: k-space deep learning for accelerated MRI publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2019.2927101 – volume: 86 start-page: 1093 year: 2021 end-page: 1109 ident: CR18 article-title: Analysis of deep complex-valued convolutional neural networks for MRI reconstruction and phase-focused applications publication-title: Magn Reson Med doi: 10.1002/mrm.28733 – year: 2019 ident: CR19 article-title: Super-resolution 1H magnetic resonance spectroscopic imaging utilizing deep learning publication-title: Front Oncol doi: 10.3389/fonc.2019.01010 – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: CR22 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – ident: CR42 – volume: 19 start-page: 1498 year: 2007 end-page: 1507 ident: CR66 article-title: Open access series of imaging studies (OASIS): cross-sectional MRI data in young, middle aged, nondemented, and demented older adults publication-title: J Cogn Neurosci doi: 10.1162/jocn.2007.19.9.1498 – year: 2018 ident: CR71 article-title: Generative adversarial networks and perceptual losses for video super-resolution publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2019.2895768 – ident: CR46 – volume: 215 year: 2022 ident: CR72 article-title: Pros and cons of GAN evaluation measures: new developments publication-title: Comput Vis Image Underst doi: 10.1016/j.cviu.2021.103329 – volume: 88 year: 2023 ident: CR79 article-title: Adaptive diffusion priors for accelerated MRI reconstruction publication-title: Med Image Anal doi: 10.1016/j.media.2023.102872 – ident: CR67 – ident: CR75 – ident: CR15 – volume: 10 start-page: 1275 year: 2020 end-page: 1285 ident: CR69 article-title: Dense-UNet: a novel multiphoton in vivo cellular image segmentation model based on a convolutional neural network publication-title: Quant Imaging Med Surg doi: 10.21037/qims-19-1090 – volume: 49 start-page: 939 year: 2019 end-page: 954 ident: CR1 article-title: Deep learning in radiology: an overview of the concepts and a survey of the state of the art with focus on MRI publication-title: J Magn Reson Imaging doi: 10.1002/jmri.26534 – volume: 65 start-page: 1985 year: 2018 end-page: 1995 ident: CR9 article-title: Deep residual learning for accelerated MRI using magnitude and phase networks publication-title: IEEE Trans Biomed Eng doi: 10.1109/TBME.2018.2821699 – volume: 87 start-page: 488 year: 2022 end-page: 495 ident: CR58 article-title: Multiparametric mapping in the brain from conventional contrast-weighted images using deep learning publication-title: Magn Reson Med doi: 10.1002/mrm.28962 – volume: 54 start-page: 452 year: 2021 end-page: 459 ident: CR35 article-title: Deep learning whole-gland and zonal prostate segmentation on a public MRI dataset publication-title: J Magn Reson Imaging doi: 10.1002/jmri.27585 – ident: CR32 – volume: 41 start-page: 1747 year: 2022 end-page: 1763 ident: CR78 article-title: Unsupervised MRI reconstruction via zero-shot learned adversarial transformers publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2022.3147426 – volume: 30 start-page: 449 year: 2017 end-page: 459 ident: CR2 article-title: Deep learning for brain MRI segmentation: state of the art and future directions publication-title: J Digit Imaging doi: 10.1007/s10278-017-9983-4 – volume: 81 start-page: 3901 year: 2019 end-page: 3914 ident: CR21 article-title: DeepCEST: 9.4 T Chemical exchange saturation transfer MRI contrast predicted from 3 T data - a proof of concept study publication-title: Magn Reson Med doi: 10.1002/mrm.27690 – volume: 84 start-page: 2246 year: 2020 end-page: 2261 ident: CR30 article-title: MRI reconstruction using deep Bayesian estimation publication-title: Magn Reson Med doi: 10.1002/mrm.28274 – ident: CR26 – volume: 295 start-page: 552 year: 2020 end-page: 561 ident: CR40 article-title: Deep learning single-frame and multiframe super-resolution for cardiac MRI publication-title: Radiology doi: 10.1148/radiol.2020192173 – volume: 6 start-page: 615 year: 2020 end-page: 624 ident: CR17 article-title: MRI super-resolution with ensemble learning and complementary priors publication-title: IEEE Trans Comput Imaging doi: 10.1109/TCI.2020.2964201 – volume: 63 start-page: 185 year: 2019 end-page: 192 ident: CR64 article-title: Region-of-interest undersampled MRI reconstruction: a deep convolutional neural network approach publication-title: Magn Reson Imaging doi: 10.1016/j.mri.2019.07.010 – volume: 36 start-page: 65 year: 2023 end-page: 77 ident: CR11 article-title: A densely interconnected network for deep learning accelerated MRI publication-title: Magn Reson Mater Phys, Biol Med doi: 10.1007/s10334-022-01041-3 – ident: CR43 – start-page: 107 year: 2011 end-page: 115 ident: CR61 article-title: Assessment of bias for MRI diffusion tensor imaging using SIMEX publication-title: Medical image computing and computer-assisted intervention—MICCAI 2011 – volume: 47 start-page: 983 year: 2020 end-page: 997 ident: CR4 article-title: Reconstruction of multicontrast MR images through deep learning publication-title: Med Phys doi: 10.1002/mp.14006 – volume: 12 start-page: 11758 year: 2022 ident: CR49 article-title: A deep learning approach to upscaling “low-quality” MR Images: an in silico comparison study based on the UNet framework publication-title: Appl Sci doi: 10.3390/app122211758 – ident: CR37 – ident: CR53 – volume: 10 start-page: 1902 year: 2020 ident: CR12 article-title: Compressed-sensing magnetic resonance image reconstruction using an iterative convolutional neural network approach publication-title: Appl Sci doi: 10.3390/app10061902 – year: 2000 ident: CR36 article-title: Mixed-effects models in S and S-PLUS publication-title: Springer, Berlin doi: 10.1007/b98882 – volume: 80 start-page: 1189 year: 2018 end-page: 1205 ident: CR8 article-title: Deep learning with domain adaptation for accelerated projection-reconstruction MR publication-title: Magn Reson Med doi: 10.1002/mrm.27106 – ident: CR56 – volume: 3 start-page: 47 year: 2017 end-page: 57 ident: CR24 article-title: Loss functions for image restoration with neural networks publication-title: IEEE Trans Comput Imaging doi: 10.1109/TCI.2016.2644865 – volume: 37 start-page: 1310 year: 2018 end-page: 1321 ident: CR29 article-title: DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2017.2785879 – ident: CR63 – volume: 39 start-page: 2738 year: 2020 end-page: 2749 ident: CR57 article-title: Multi-contrast super-resolution MRI through a progressive network publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2020.2974858 – ident: CR27 – volume: 84 start-page: 663 year: 2020 end-page: 685 ident: CR77 article-title: A transfer-learning approach for accelerated MRI using deep neural networks publication-title: Magn Reson Med doi: 10.1002/mrm.28148 – ident: CR23 – volume: 63 year: 2018 ident: CR14 article-title: Deep learning for undersampled MRI reconstruction publication-title: Phys Med Biol doi: 10.1088/1361-6560/aac71a – volume: 10 start-page: 13590 year: 2020 ident: CR76 article-title: Comparing different deep learning architectures for classification of chest radiographs publication-title: Sci Rep doi: 10.1038/s41598-020-70479-z – ident: CR44 – ident: CR48 – ident: CR73 – volume: 139 year: 2021 ident: CR47 article-title: MR image reconstruction using densely connected residual convolutional networks publication-title: Comput Biol Med doi: 10.1016/j.compbiomed.2021.105010 – ident: CR38 – ident: CR52 – volume: 6 year: 2021 ident: CR60 article-title: Integrating semantic edges and segmentation information for building extraction from aerial images using UNet publication-title: Mach Learn Appl – ident: CR31 – volume: 134 year: 2021 ident: CR3 article-title: Compressed sensing and deep learning reconstruction for women’s pelvic MRI denoising: utility for improving image quality and examination time in routine clinical practice publication-title: Eur J Radiol doi: 10.1016/j.ejrad.2020.109430 – year: 2021 ident: CR62 article-title: Boosting the signal-to-noise of low-field MRI with deep learning image reconstruction publication-title: Sci Rep doi: 10.1038/s41598-021-87482-7 – volume: 53 start-page: 1015 year: 2021 end-page: 1028 ident: CR25 article-title: Artificial intelligence for mr image reconstruction: an overview for clinicians publication-title: J Magn Reson Imaging doi: 10.1002/jmri.27078 – ident: CR55 – volume: 37 start-page: 117 year: 2020 end-page: 127 ident: CR5 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: CR28 – ident: CR41 – volume: 22 start-page: 1766 year: 2022 ident: CR34 article-title: Brain magnetic resonance imaging classification using deep learning architectures with gender and age publication-title: Sensors doi: 10.3390/s22051766 – volume: 70 start-page: 155 year: 2020 end-page: 167 ident: CR6 article-title: A multi-scale variational neural network for accelerating motion-compensated whole-heart 3D coronary MR angiography publication-title: Magn Reson Imaging doi: 10.1016/j.mri.2020.04.007 – volume: 49 start-page: 939 year: 2019 ident: 1127_CR1 publication-title: J Magn Reson Imaging doi: 10.1002/jmri.26534 – ident: 1127_CR67 – ident: 1127_CR73 – volume: 80 start-page: 1189 year: 2018 ident: 1127_CR8 publication-title: Magn Reson Med doi: 10.1002/mrm.27106 – volume: 3 start-page: 47 year: 2017 ident: 1127_CR24 publication-title: IEEE Trans Comput Imaging doi: 10.1109/TCI.2016.2644865 – volume: 521 start-page: 436 year: 2015 ident: 1127_CR22 publication-title: Nature doi: 10.1038/nature14539 – volume: 65 start-page: 1985 year: 2018 ident: 1127_CR9 publication-title: IEEE Trans Biomed Eng doi: 10.1109/TBME.2018.2821699 – volume: 39 start-page: 377 year: 2020 ident: 1127_CR10 publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2019.2927101 – year: 2021 ident: 1127_CR62 publication-title: Sci Rep doi: 10.1038/s41598-021-87482-7 – ident: 1127_CR53 doi: 10.1109/CVPR42600.2020.01284 – ident: 1127_CR23 doi: 10.1109/ICCVW54120.2021.00217 – ident: 1127_CR46 doi: 10.1109/TSP.2019.8768829 – year: 2019 ident: 1127_CR19 publication-title: Front Oncol doi: 10.3389/fonc.2019.01010 – volume: 88 year: 2023 ident: 1127_CR79 publication-title: Med Image Anal doi: 10.1016/j.media.2023.102872 – ident: 1127_CR37 doi: 10.1007/978-3-319-24574-4_28 – start-page: 107 volume-title: Medical image computing and computer-assisted intervention—MICCAI 2011 year: 2011 ident: 1127_CR61 – ident: 1127_CR27 doi: 10.1109/CVPR.2015.7298594 – ident: 1127_CR31 doi: 10.18653/v1/P19-1266 – ident: 1127_CR70 – volume: 19 start-page: 1498 year: 2007 ident: 1127_CR66 publication-title: J Cogn Neurosci doi: 10.1162/jocn.2007.19.9.1498 – volume: 215 year: 2022 ident: 1127_CR72 publication-title: Comput Vis Image Underst doi: 10.1016/j.cviu.2021.103329 – volume: 30 start-page: 449 year: 2017 ident: 1127_CR2 publication-title: J Digit Imaging doi: 10.1007/s10278-017-9983-4 – volume: 84 start-page: 450 year: 2020 ident: 1127_CR20 publication-title: Magn Reson Med doi: 10.1002/mrm.28117 – ident: 1127_CR68 – volume: 34 start-page: 1993 year: 2015 ident: 1127_CR33 publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2014.2377694 – volume: 13 start-page: 600 year: 2004 ident: 1127_CR65 publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2003.819861 – volume: 22 start-page: 1766 year: 2022 ident: 1127_CR34 publication-title: Sensors doi: 10.3390/s22051766 – ident: 1127_CR38 doi: 10.1109/CVPRW.2019.00073 – year: 2018 ident: 1127_CR71 publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2019.2895768 – volume: 134 year: 2021 ident: 1127_CR3 publication-title: Eur J Radiol doi: 10.1016/j.ejrad.2020.109430 – ident: 1127_CR32 – volume: 81 start-page: 3901 year: 2019 ident: 1127_CR21 publication-title: Magn Reson Med doi: 10.1002/mrm.27690 – ident: 1127_CR54 doi: 10.1109/VCIP.2017.8305143 – year: 2000 ident: 1127_CR36 publication-title: Springer, Berlin doi: 10.1007/b98882 – volume: 12 start-page: 11758 year: 2022 ident: 1127_CR49 publication-title: Appl Sci doi: 10.3390/app122211758 – volume: 87 start-page: 488 year: 2022 ident: 1127_CR58 publication-title: Magn Reson Med doi: 10.1002/mrm.28962 – volume: 6 year: 2021 ident: 1127_CR60 publication-title: Mach Learn Appl – ident: 1127_CR74 – volume: 10 start-page: 1902 year: 2020 ident: 1127_CR12 publication-title: Appl Sci doi: 10.3390/app10061902 – volume: 295 start-page: 552 year: 2020 ident: 1127_CR40 publication-title: Radiology doi: 10.1148/radiol.2020192173 – ident: 1127_CR42 doi: 10.23919/EUSIPCO54536.2021.9615963 – ident: 1127_CR48 doi: 10.1007/978-3-030-88081-1_60 – ident: 1127_CR28 doi: 10.1007/978-3-030-59861-7_64 – volume: 44 start-page: 6209 year: 2017 ident: 1127_CR7 publication-title: Med Phys doi: 10.1002/mp.12600 – ident: 1127_CR26 doi: 10.1109/CVPR.2016.90 – year: 2020 ident: 1127_CR13 publication-title: Front Cardiovasc Med doi: 10.3389/fcvm.2020.00017 – ident: 1127_CR39 doi: 10.1007/978-3-030-33843-5_6 – volume: 70 start-page: 155 year: 2020 ident: 1127_CR6 publication-title: Magn Reson Imaging doi: 10.1016/j.mri.2020.04.007 – volume: 84 start-page: 663 year: 2020 ident: 1127_CR77 publication-title: Magn Reson Med doi: 10.1002/mrm.28148 – volume: 86 start-page: 1093 year: 2021 ident: 1127_CR18 publication-title: Magn Reson Med doi: 10.1002/mrm.28733 – ident: 1127_CR55 doi: 10.1007/978-3-030-11021-5_20 – volume: 63 start-page: 185 year: 2019 ident: 1127_CR64 publication-title: Magn Reson Imaging doi: 10.1016/j.mri.2019.07.010 – volume: 139 year: 2021 ident: 1127_CR47 publication-title: Comput Biol Med doi: 10.1016/j.compbiomed.2021.105010 – volume: 54 start-page: 452 year: 2021 ident: 1127_CR35 publication-title: J Magn Reson Imaging doi: 10.1002/jmri.27585 – ident: 1127_CR52 – volume: 47 start-page: 983 year: 2020 ident: 1127_CR4 publication-title: Med Phys doi: 10.1002/mp.14006 – volume: 6 start-page: 615 year: 2020 ident: 1127_CR17 publication-title: IEEE Trans Comput Imaging doi: 10.1109/TCI.2020.2964201 – ident: 1127_CR75 – volume: 9 start-page: 1516 year: 2019 ident: 1127_CR50 publication-title: Quant Imaging Med Surg doi: 10.21037/qims.2019.08.10 – volume: 53 start-page: 1015 year: 2021 ident: 1127_CR25 publication-title: J Magn Reson Imaging doi: 10.1002/jmri.27078 – volume: 41 start-page: 1747 year: 2022 ident: 1127_CR78 publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2022.3147426 – volume: 37 start-page: 117 year: 2020 ident: 1127_CR5 publication-title: IEEE Signal Process Mag doi: 10.1109/MSP.2019.2950433 – volume: 84 start-page: 2246 year: 2020 ident: 1127_CR30 publication-title: Magn Reson Med doi: 10.1002/mrm.28274 – ident: 1127_CR56 doi: 10.1109/ICASSP.2018.8461664 – ident: 1127_CR63 doi: 10.1007/978-3-031-43999-5_47 – ident: 1127_CR41 – ident: 1127_CR44 doi: 10.1109/NAECON46414.2019.9057834 – volume: 39 start-page: 2738 year: 2020 ident: 1127_CR57 publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2020.2974858 – ident: 1127_CR51 doi: 10.1007/978-3-030-11726-9_21 – volume: 24 start-page: 568 year: 2020 ident: 1127_CR45 publication-title: IEEE J Biomed Health Inform doi: 10.1109/JBHI.2019.2912935 – volume: 63 year: 2018 ident: 1127_CR14 publication-title: Phys Med Biol doi: 10.1088/1361-6560/aac71a – volume: 71 start-page: 30 year: 2019 ident: 1127_CR16 publication-title: Comput Med Imaging Graph doi: 10.1016/j.compmedimag.2018.10.005 – volume: 36 start-page: 65 year: 2023 ident: 1127_CR11 publication-title: Magn Reson Mater Phys, Biol Med doi: 10.1007/s10334-022-01041-3 – volume: 10 start-page: 13590 year: 2020 ident: 1127_CR76 publication-title: Sci Rep doi: 10.1038/s41598-020-70479-z – ident: 1127_CR43 doi: 10.1117/12.2513158 – volume: 10 start-page: 1275 year: 2020 ident: 1127_CR69 publication-title: Quant Imaging Med Surg doi: 10.21037/qims-19-1090 – volume: 98 year: 2020 ident: 1127_CR59 publication-title: Pattern Recognit doi: 10.1016/j.patcog.2019.107038 – volume: 37 start-page: 1310 year: 2018 ident: 1127_CR29 publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2017.2785879 – ident: 1127_CR15 doi: 10.1007/978-3-030-00928-1_11
SSID	ssj0021503
Score	2.4016383
Snippet	Objective This study aims to assess the statistical significance of training parameters in 240 dense UNets (DUNets) used for enhancing low Signal-to-Noise... This study aims to assess the statistical significance of training parameters in 240 dense UNets (DUNets) used for enhancing low Signal-to-Noise Ratio (SNR)...
SourceID	proquest pubmed crossref springer
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	507
SubjectTerms	Algorithms Analysis of Variance 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 Enhancement - methods Image Processing, Computer-Assisted - methods Imaging Magnetic Resonance Imaging - methods Medicine Medicine & Public Health Neural Networks, Computer Radiology Reproducibility of Results Research Article Signal-To-Noise Ratio Solid State Physics
Title	Learning to deep learning: statistics and a paradigm test in selecting a UNet architecture to enhance MRI
URI	https://link.springer.com/article/10.1007/s10334-023-01127-6 https://www.ncbi.nlm.nih.gov/pubmed/37989921 https://www.proquest.com/docview/2892658628
Volume	37
WOSCitedRecordID	wos001107753200001&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/eLvHCXMwnV1bS8MwFD64KeKL90u9jAi-aWFtekl9E3EouCHTyd5Km6RzoN1YO3-_J206J5OBvidpOV-S8x1OzncALmgk8dKj0qQRE6bDbd8MqJOYLlJZzqUdNONCxPXR73RYvx886aKwrHrtXqUki5t6rtiNUsdEH4Phr4VrejVYRXfHVMOG7vPrLMxCikN1eczv8366oAVeuZATLVxNa-t_P7kNm5pakptyL-zAikx3Yb2tk-d7MNRaqgOSj4iQckx0y4jBNVF1RaVkM4lSQSKiJMHFcPBBkIrmZJiSrGiYo2ZHpNeROZlPQagVZfqmdhBpdx_2ode6e7m9N3WnBZPTwMpNhNFFP25FLEFvJaTrJEKddM5kLAKOMVIz8UWMwOHl6Xgcx7ixxzyLI-t1EoceQD0dpfIICBO2aIqEBbFHHd9HfDhSIo_7gcWEcJsGWJXxQ65lyFU3jPfwW0BZ2TBEG4aFDUPPgMvZnHEpwrF09HmFaYhnRSVAolSOplmIwaWNjMuzmQGHJdiz9agfYOhpWwZcVciG-jhnSz52_LfhJ7BhIysq3_ueQj2fTOUZrPFPxHjSgJrfZ41iN38B3fTsIg
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3dT9swED-xgjZexudGGR9G4g0iJbGT2LxNE4iKtkJQEG9WYjtdpS1Fbbq_f-fEKSBQJXg_O9Gdffc7ne93AMc0Nej0qPFoyrXHVJh4grLcixDKKmVC4WcViWs36ff5w4O4dk1h0-a1e1OSrDz1s2Y3SpmHMQbT3wD3jD_BMsOIZRnzb27v52kWQhzq2mPeXvcyBL3Cla9qolWouVj72E-uw1cHLcnP-ixswJIpNuFzzxXPt2DkuFSHpBwTbcwjcSMjhmfE9hXVlM0kLTRJiaUE16PhX4JQtCSjgkyrgTl2dUru-qYkz0sQdkdT_LYniPRuOttwd3E--HXpuUkLnqIiKD00Y4RxPEh5jtFKm4jl2t50xU2mhcIcyc8TnaHh0HmyWKFMlMU8DhSiXpYz-g1axbgwO0C4DrWvcy6ymLIk8QVXCIlilYiAax35bQga5UvlaMjtNIw_8olA2epQog5lpUMZt-FkvuaxJuFYKH3U2FTiXbEFkLQw49lUYnIZIuKKQ96G77Wx5_vRRGDqGQZtOG0sK911ni742O77xA_hy-Wg15XdTv_qB6yGiJDqt7970ConM7MPK-of2ntyUJ3p_2ea7h4
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS8MwFD54Q3zxfpnXCL5pWdukbeKbqMOhDvGGb6FN0jnQbrjO3-9J282JIojvSVryneR8h5PzHYADGhu89KhxaMy1w5QfOYKy1AmQyiplfOEmhYjrVdRq8acncTNWxV-8dh-mJMuaBqvSlOX1nk7rY4VvlDIH_Q2Gwh6uH07CNLMP6W28fvc4CrmQ7tCqVObneV_d0TeO-S0_WridxsL_f3gR5ivKSU5KG1mCCZMtw-x1lVRfgU6lsdomeZdoY3qkaiXRPia23qiUciZxpklMrFS47rRfCVLUnHQy0i8a6djZMXlomZyMpybsiiZ7tpZFrm-bq_DQOL8_vXCqDgyOosLLHYQ3QP_uxTxFL6ZNwFJtbwDFTaKFwtjJTSOdIKB4qbJQ4ZggCXnoKWTDLGV0DaaybmY2gHDta1enXCQhZVHkCq6QKoUqEh7XOnBr4A2BkKqSJ7ddMl7kp7Cy3UOJeyiLPZRhDQ5Hc3qlOMevo_eH-Eo8QzYxEmemO-hLDDp9ZGKhz2uwXgI_Wo9GAkNS36vB0RBlWR3z_i8f2_zb8D2YvTlryKtm63IL5nwkTuWT4G2Yyt8GZgdm1DvC_bZbmPcHdJ73Ag
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+to+deep+learning%3A+statistics+and+a+paradigm+test+in+selecting+a+UNet+architecture+to+enhance+MRI&rft.jtitle=Magma+%28New+York%2C+N.Y.%29&rft.au=Sharma%2C+Rishabh&rft.au=Tsiamyrtzis%2C+Panagiotis&rft.au=Webb%2C+Andrew+G&rft.au=Leiss%2C+Ernst+L&rft.date=2024-07-01&rft.eissn=1352-8661&rft.volume=37&rft.issue=3&rft.spage=507&rft_id=info:doi/10.1007%2Fs10334-023-01127-6&rft_id=info%3Apmid%2F37989921&rft.externalDocID=37989921
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