Multiscale brain MRI super-resolution using deep 3D convolutional networks

[Display omitted] •A residual-based deep 3D CNN architecture for super-resolution.•Comprehensive performance analysis of key elements of neural networks.•Multi-scale training approach to handle arbitrary scale factors.•Multimodal CNN for super-resolution. The purpose of super-resolution approaches i...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Computerized medical imaging and graphics Jg. 77; S. 101647
Hauptverfasser:	Pham, Chi-Hieu, Tor-Díez, Carlos, Meunier, Hélène, Bednarek, Nathalie, Fablet, Ronan, Passat, Nicolas, Rousseau, François
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States Elsevier Ltd 01.10.2019 Elsevier Science Ltd Elsevier
Schlagworte:	3D convolutional neural network Artificial neural networks Brain Brain MRI Computer Science Computer Vision and Pattern Recognition Convolution Cortex Image acquisition Image enhancement Image Processing Image reconstruction Image resolution Internal Medicine Learning Magnetic resonance imaging Medical Imaging Neural networks Neuroimaging NMR Nuclear magnetic resonance Optimization Other Post-processing Resonance Scaling factors Structural analysis Super-resolution Training Transfer learning Super-resolution 3D convolutional neural network Brain MRI brain MRI super-resolution
ISSN:	0895-6111, 1879-0771, 1879-0771
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	[Display omitted] •A residual-based deep 3D CNN architecture for super-resolution.•Comprehensive performance analysis of key elements of neural networks.•Multi-scale training approach to handle arbitrary scale factors.•Multimodal CNN for super-resolution. The purpose of super-resolution approaches is to overcome the hardware limitations and the clinical requirements of imaging procedures by reconstructing high-resolution images from low-resolution acquisitions using post-processing methods. Super-resolution techniques could have strong impacts on structural magnetic resonance imaging when focusing on cortical surface or fine-scale structure analysis for instance. In this paper, we study deep three-dimensional convolutional neural networks for the super-resolution of brain magnetic resonance imaging data. First, our work delves into the relevance of several factors in the performance of the purely convolutional neural network-based techniques for the monomodal super-resolution: optimization methods, weight initialization, network depth, residual learning, filter size in convolution layers, number of the filters, training patch size and number of training subjects. Second, our study also highlights that one single network can efficiently handle multiple arbitrary scaling factors based on a multiscale training approach. Third, we further extend our super-resolution networks to the multimodal super-resolution using intermodality priors. Fourth, we investigate the impact of transfer learning skills onto super-resolution performance in terms of generalization among different datasets. Lastly, the learnt models are used to enhance real clinical low-resolution images. Results tend to demonstrate the potential of deep neural networks with respect to practical medical image applications.
AbstractList	The purpose of super-resolution approaches is to overcome the hardware limitations and the clinical requirements of imaging procedures by reconstructing high-resolution images from low-resolution acquisitions using post-processing methods. Super-resolution techniques could have strong impacts on structural magnetic resonance imaging when focusing on cortical surface or fine-scale structure analysis for instance. In this paper, we study deep three-dimensional convolutional neural networks for the super-resolution of brain magnetic resonance imaging data. First, our work delves into the relevance of several factors in the performance of the purely convolutional neural network-based techniques for the monomodal super-resolution: optimization methods, weight initialization, network depth, residual learning, filter size in convolution layers, number of the filters, training patch size and number of training subjects. Second, our study also highlights that one single network can efficiently handle multiple arbitrary scaling factors based on a multiscale training approach. Third, we further extend our super-resolution networks to the multimodal super-resolution using intermodality priors. Fourth, we investigate the impact of transfer learning skills onto super-resolution performance in terms of generalization among different datasets. Lastly, the learnt models are used to enhance real clinical low-resolution images. Results tend to demonstrate the potential of deep neural networks with respect to practical medical image applications. [Display omitted] •A residual-based deep 3D CNN architecture for super-resolution.•Comprehensive performance analysis of key elements of neural networks.•Multi-scale training approach to handle arbitrary scale factors.•Multimodal CNN for super-resolution. The purpose of super-resolution approaches is to overcome the hardware limitations and the clinical requirements of imaging procedures by reconstructing high-resolution images from low-resolution acquisitions using post-processing methods. Super-resolution techniques could have strong impacts on structural magnetic resonance imaging when focusing on cortical surface or fine-scale structure analysis for instance. In this paper, we study deep three-dimensional convolutional neural networks for the super-resolution of brain magnetic resonance imaging data. First, our work delves into the relevance of several factors in the performance of the purely convolutional neural network-based techniques for the monomodal super-resolution: optimization methods, weight initialization, network depth, residual learning, filter size in convolution layers, number of the filters, training patch size and number of training subjects. Second, our study also highlights that one single network can efficiently handle multiple arbitrary scaling factors based on a multiscale training approach. Third, we further extend our super-resolution networks to the multimodal super-resolution using intermodality priors. Fourth, we investigate the impact of transfer learning skills onto super-resolution performance in terms of generalization among different datasets. Lastly, the learnt models are used to enhance real clinical low-resolution images. Results tend to demonstrate the potential of deep neural networks with respect to practical medical image applications. The purpose of super-resolution approaches is to overcome the hardware limitations and the clinical requirements of imaging procedures by reconstructing high-resolution images from low-resolution acquisitions using post-processing methods. Super-resolution techniques could have strong impacts on structural magnetic resonance imaging when focusing on cortical surface or fine-scale structure analysis for instance. In this paper, we study deep three-dimensional convolutional neural networks for the super-resolution of brain magnetic resonance imaging data. First, our work delves into the relevance of several factors in the performance of the purely convolutional neural network-based techniques for the monomodal super-resolution: optimization methods, weight initialization, network depth, residual learning, filter size in convolution layers, number of the filters, training patch size and number of training subjects. Second, our study also highlights that one single network can efficiently handle multiple arbitrary scaling factors based on a multiscale training approach. Third, we further extend our super-resolution networks to the multimodal super-resolution using intermodality priors. Fourth, we investigate the impact of transfer learning skills onto super-resolution performance in terms of generalization among different datasets. Lastly, the learnt models are used to enhance real clinical low-resolution images. Results tend to demonstrate the potential of deep neural networks with respect to practical medical image applications.The purpose of super-resolution approaches is to overcome the hardware limitations and the clinical requirements of imaging procedures by reconstructing high-resolution images from low-resolution acquisitions using post-processing methods. Super-resolution techniques could have strong impacts on structural magnetic resonance imaging when focusing on cortical surface or fine-scale structure analysis for instance. In this paper, we study deep three-dimensional convolutional neural networks for the super-resolution of brain magnetic resonance imaging data. First, our work delves into the relevance of several factors in the performance of the purely convolutional neural network-based techniques for the monomodal super-resolution: optimization methods, weight initialization, network depth, residual learning, filter size in convolution layers, number of the filters, training patch size and number of training subjects. Second, our study also highlights that one single network can efficiently handle multiple arbitrary scaling factors based on a multiscale training approach. Third, we further extend our super-resolution networks to the multimodal super-resolution using intermodality priors. Fourth, we investigate the impact of transfer learning skills onto super-resolution performance in terms of generalization among different datasets. Lastly, the learnt models are used to enhance real clinical low-resolution images. Results tend to demonstrate the potential of deep neural networks with respect to practical medical image applications. Graphical abstract
ArticleNumber	101647
Author	Tor-Díez, Carlos Pham, Chi-Hieu Bednarek, Nathalie Passat, Nicolas Rousseau, François Meunier, Hélène Fablet, Ronan
Author_xml	– sequence: 1 givenname: Chi-Hieu surname: Pham fullname: Pham, Chi-Hieu email: ch.pham@imt-atlantique.fr organization: IMT Atlantique, LaTIM U1101 INSERM, UBL, Brest, France – sequence: 2 givenname: Carlos surname: Tor-Díez fullname: Tor-Díez, Carlos email: carlos.tordiez@imt-atlantique.fr organization: IMT Atlantique, LaTIM U1101 INSERM, UBL, Brest, France – sequence: 3 givenname: Hélène surname: Meunier fullname: Meunier, Hélène email: hmeunier@chu-reims.fr organization: Service de médecine néonatale et réanimation pédiatrique, CHU de Reims, France – sequence: 4 givenname: Nathalie surname: Bednarek fullname: Bednarek, Nathalie email: nbednarek@chu-reims.fr organization: Service de médecine néonatale et réanimation pédiatrique, CHU de Reims, France – sequence: 5 givenname: Ronan surname: Fablet fullname: Fablet, Ronan email: ronan.fablet@imt-atlantique.fr organization: IMT Atlantique, LabSTICC UMR CNRS 6285, UBL, Brest, France – sequence: 6 givenname: Nicolas surname: Passat fullname: Passat, Nicolas email: nicolas.passat@univ-reims.fr organization: Université de Reims Champagne Ardenne, CReSTIC EA 3804, 51097 Reims, France – sequence: 7 givenname: François surname: Rousseau fullname: Rousseau, François organization: IMT Atlantique, LaTIM U1101 INSERM, UBL, Brest, France
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/31493703$$D View this record in MEDLINE/PubMed https://hal.science/hal-01635455$$DView record in HAL
BookMark	eNqNkl1v0zAUhi00xLrBX0BB3MBFij8Su7kBVWWwoU5IfFxbjnMy3Ll2sJOi_fs5pJtQJaReWEeyH7_Hft9zhk6cd4DQK4LnBBP-bjPXftttoTFbdTOnmFR_9wvxBM3IQlQ5FoKcoBleVGXOCSGn6CzGDcaYYkGeoVNGiooJzGboy_VgexO1spDVQRmXXX-7yuLQQcgDRG-H3niXDdG4m6wB6DL2MdPe7fYnymYO-j8-3Mbn6GmrbIQX-3qOfn66-LG6zNdfP1-tlutcc8z6XFCoaloIwgpdF2XdAqdatK0WtC5VI4jmTYNr1qRS0wZzrlWhNVZU1xj4gp2jt5PuL2VlF5IH4U56ZeTlci3HvWQFK4uy3NHEvpnYLvjfA8RebtNnwVrlwA9RUrrgFSl5yRL6-gDd-CGkDyaKEZoWFkWiXu6poU4BPPZ_cDQBHyZABx9jgFZq06vRqj7ZayXBcsxKbuQ_GcoxQzllmBSqA4WHJsfcXU13IQWwMxBk1AacTmgA3cvGm6NU3h-oaGucSUNyC3cQH30hMlKJ5fdxzsYxIwuGC4LLJLD8v8CRj7gHvhLnxw
CitedBy_id	crossref_primary_10_1016_j_compbiomed_2025_110345 crossref_primary_10_1109_TCYB_2022_3178370 crossref_primary_10_1016_j_bspc_2022_104154 crossref_primary_10_1109_TNNLS_2023_3315271 crossref_primary_10_1109_ACCESS_2024_3516380 crossref_primary_10_1016_j_acra_2024_10_054 crossref_primary_10_3390_s24206639 crossref_primary_10_1109_ACCESS_2024_3427674 crossref_primary_10_1016_j_bspc_2021_103339 crossref_primary_10_1088_1361_6560_ad94c7 crossref_primary_10_1002_hbm_70112 crossref_primary_10_1109_JBHI_2023_3271815 crossref_primary_10_1007_s11548_021_02535_6 crossref_primary_10_1016_j_ejrad_2025_112289 crossref_primary_10_1016_j_compbiomed_2024_108151 crossref_primary_10_1016_j_mri_2023_01_012 crossref_primary_10_1002_mrm_29785 crossref_primary_10_1016_j_compbiomed_2020_103755 crossref_primary_10_1093_bib_bbaa310 crossref_primary_10_3390_electronics14153009 crossref_primary_10_1016_j_imu_2021_100713 crossref_primary_10_1016_j_bspc_2025_107777 crossref_primary_10_1109_ACCESS_2022_3140810 crossref_primary_10_1007_s10278_024_01139_1 crossref_primary_10_1016_j_mri_2025_110463 crossref_primary_10_1016_j_neuroimage_2021_118687 crossref_primary_10_1109_TETCI_2022_3215137 crossref_primary_10_3390_s22207925 crossref_primary_10_1109_TCDS_2022_3153090 crossref_primary_10_1002_mrm_29059 crossref_primary_10_1016_j_bspc_2022_104177 crossref_primary_10_1111_jon_13187 crossref_primary_10_1186_s12968_020_00651_x crossref_primary_10_3724_SP_J_1089_2022_18793 crossref_primary_10_1007_s11554_021_01181_0 crossref_primary_10_1016_j_media_2022_102393 crossref_primary_10_1109_ACCESS_2020_2992204 crossref_primary_10_1016_j_ymeth_2020_09_007 crossref_primary_10_3390_app15158744 crossref_primary_10_1007_s12194_024_00871_1 crossref_primary_10_1016_j_media_2021_101957 crossref_primary_10_1007_s00234_023_03271_1 crossref_primary_10_1016_j_compbiomed_2024_109301 crossref_primary_10_1097_RCT_0000000000001680 crossref_primary_10_3389_fnins_2024_1473132 crossref_primary_10_1016_j_cmpb_2024_108110 crossref_primary_10_1002_mrm_28911 crossref_primary_10_1016_j_compmedimag_2021_101973 crossref_primary_10_1016_j_bspc_2020_102120 crossref_primary_10_1002_mrm_29601 crossref_primary_10_1016_j_compbiomed_2023_107632 crossref_primary_10_3390_app9224874 crossref_primary_10_1109_TAI_2024_3397292 crossref_primary_10_1038_s41551_024_01283_7 crossref_primary_10_1038_s41598_025_90972_7 crossref_primary_10_1002_mp_17563 crossref_primary_10_1007_s00521_024_09890_w crossref_primary_10_1016_j_bspc_2023_104901 crossref_primary_10_1109_ACCESS_2024_3478829 crossref_primary_10_1093_cercor_bhaa237 crossref_primary_10_3390_brainsci15080821 crossref_primary_10_1134_S1054661824701438 crossref_primary_10_1016_j_neuroimage_2022_119033 crossref_primary_10_1016_j_diii_2022_06_006 crossref_primary_10_3389_frai_2022_780405 crossref_primary_10_1093_dmfr_twaf029 crossref_primary_10_3390_bioengineering11070643 crossref_primary_10_1002_mp_16860 crossref_primary_10_1002_jmri_29205 crossref_primary_10_1007_s00234_023_03212_y crossref_primary_10_1007_s00034_025_03150_5 crossref_primary_10_1016_j_neuroimage_2021_117946 crossref_primary_10_1038_s41598_023_38335_y crossref_primary_10_1016_j_neuroimage_2020_117017 crossref_primary_10_1109_JTEHM_2021_3076152 crossref_primary_10_1016_j_mri_2021_12_011 crossref_primary_10_1371_journal_pone_0244745 crossref_primary_10_3390_ma13061397 crossref_primary_10_1109_TMI_2024_3367321 crossref_primary_10_1002_mrm_30245 crossref_primary_10_1109_ACCESS_2020_2980266 crossref_primary_10_1002_acm2_13758 crossref_primary_10_1186_s43055_025_01574_2 crossref_primary_10_1016_j_imavis_2025_105652 crossref_primary_10_1371_journal_pone_0280076 crossref_primary_10_1109_ACCESS_2022_3155226 crossref_primary_10_3390_life13091893 crossref_primary_10_1007_s11831_023_09898_w crossref_primary_10_1007_s10278_022_00721_9 crossref_primary_10_3390_make6010033 crossref_primary_10_1016_j_acra_2023_05_010 crossref_primary_10_3389_fcvm_2021_682924 crossref_primary_10_1002_mrm_28553 crossref_primary_10_1016_j_cmpb_2023_107854 crossref_primary_10_1016_j_neuroimage_2021_118869 crossref_primary_10_1109_ACCESS_2020_2968395 crossref_primary_10_3233_ICA_200620 crossref_primary_10_3390_app14041351 crossref_primary_10_1016_j_heliyon_2024_e29331 crossref_primary_10_3389_fnins_2022_830143 crossref_primary_10_1016_j_phro_2022_06_008
Cites_doi	10.1016/j.media.2012.09.003 10.1016/S1361-8415(02)00061-0 10.1109/TMI.2015.2437894 10.1109/ISBI.2019.8759255 10.1007/978-3-642-27413-8_47 10.1016/j.neuroimage.2010.11.047 10.1016/j.media.2012.05.003 10.1109/TMI.2015.2415453 10.3389/fnins.2017.00013 10.1259/bjr/33169417 10.1145/2647868.2654889 10.1002/mrm.24233 10.1109/TPAMI.2015.2439281 10.1109/TMI.2017.2656907 10.1109/ICCV.2013.241 10.1109/TMI.2010.2051680 10.1109/ISBI.2017.7950500 10.1016/j.neuroimage.2011.09.015 10.1109/TIP.2003.819861 10.1109/TMI.2013.2284014 10.1109/TMI.2016.2535302 10.1109/TMI.2016.2611653 10.1109/5.726791 10.1109/ISBI.2018.8363594 10.1016/j.neuroimage.2018.01.054 10.1002/mrm.25597 10.1109/72.279181 10.1002/mrm.26262 10.1016/j.media.2010.04.005 10.1109/ISBI.2018.8363679 10.1016/j.media.2010.05.010 10.1016/j.media.2016.10.004 10.1093/comjnl/bxm075
ContentType	Journal Article
Copyright	2019 Elsevier Ltd Elsevier Ltd Copyright © 2019 Elsevier Ltd. All rights reserved. Copyright Elsevier Science Ltd. Oct 2019 Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml	– notice: 2019 Elsevier Ltd – notice: Elsevier Ltd – notice: Copyright © 2019 Elsevier Ltd. All rights reserved. – notice: Copyright Elsevier Science Ltd. Oct 2019 – notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID	AAYXX CITATION NPM 7QO 7SC 8FD FR3 JQ2 K9. L7M L~C L~D NAPCQ P64 7X8 1XC VOOES
DOI	10.1016/j.compmedimag.2019.101647
DatabaseName	CrossRef PubMed Biotechnology Research Abstracts Computer and Information Systems Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection ProQuest Health & Medical Complete (Alumni) Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Nursing & Allied Health Premium Biotechnology and BioEngineering Abstracts MEDLINE - Academic Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle	CrossRef PubMed Nursing & Allied Health Premium Biotechnology Research Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Health & Medical Complete (Alumni) Engineering Research Database Advanced Technologies Database with Aerospace Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitleList	PubMed Nursing & Allied Health Premium 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 Computer Science
EISSN	1879-0771
EndPage	101647
ExternalDocumentID	oai:HAL:hal-01635455v2 31493703 10_1016_j_compmedimag_2019_101647 S0895611118304105 1_s2_0_S0895611118304105
Genre	Research Support, Non-U.S. Gov't Journal Article
GroupedDBID	--- --K --M .1- .DC .FO .GJ .~1 0R~ 1B1 1P~ 1RT 1~. 1~5 29F 4.4 457 4G. 53G 5GY 5RE 5VS 7-5 71M 8P~ 9JM 9JN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABBQC ABFNM ABJNI ABMAC ABMZM ABWVN ABXDB ACDAQ ACGFS ACIEU ACIUM ACIWK ACLOT ACNNM ACPRK ACRLP ACRPL ACVFH ACZNC ADBBV ADCNI ADEZE ADJOM ADMUD ADNMO AEBSH AEIPS AEKER AENEX AEUPX AEVXI AFJKZ AFPUW AFRAH AFRHN AFTJW AFXIZ AGHFR AGQPQ AGUBO AGYEJ AHHHB AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX AOUOD APXCP ASPBG AVWKF AXJTR AZFZN BKOJK BLXMC BNPGV CS3 DU5 EBS EFJIC EFKBS EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HEI HLZ HMK HMO HVGLF HZ~ IHE J1W KOM LX9 M29 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- ROL RPZ SAE SBC SDF SDG SDP SEL SES SEW SPC SPCBC SSH SSV SSZ T5K WUQ Z5R ZGI ~G- ~HD AACTN AFCTW AFKWA AJOXV AMFUW RIG AAIAV ABLVK ABYKQ AJBFU LCYCR 9DU AAYXX CITATION NPM 7QO 7SC 8FD FR3 JQ2 K9. L7M L~C L~D NAPCQ P64 7X8 1XC VOOES
ID	FETCH-LOGICAL-c603t-72e9b247134cb45bfe62c7ffc72b5ad71c6dd0b3d6ddb2d066ca4cc0a2cb0e683
ISICitedReferencesCount	121
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000493216400002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0895-6111 1879-0771
IngestDate	Sat Nov 29 15:03:55 EST 2025 Sun Sep 28 10:47:05 EDT 2025 Tue Oct 07 06:58:45 EDT 2025 Thu Apr 03 06:58:33 EDT 2025 Tue Nov 18 22:04:16 EST 2025 Sat Nov 29 07:18:50 EST 2025 Fri Feb 23 02:29:48 EST 2024 Tue Feb 25 19:59:04 EST 2025 Tue Oct 14 19:37:59 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Keywords	Super-resolution 3D convolutional neural network Brain MRI brain MRI super-resolution
Language	English
License	Copyright © 2019 Elsevier Ltd. All rights reserved. Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c603t-72e9b247134cb45bfe62c7ffc72b5ad71c6dd0b3d6ddb2d066ca4cc0a2cb0e683
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0001-7415-7746 0000-0002-6462-423X 0000-0002-0320-4581 0000-0001-9837-7487
OpenAccessLink	https://hal.science/hal-01635455
PMID	31493703
PQID	2312231074
PQPubID	2047475
PageCount	1
ParticipantIDs	hal_primary_oai_HAL_hal_01635455v2 proquest_miscellaneous_2286915653 proquest_journals_2312231074 pubmed_primary_31493703 crossref_citationtrail_10_1016_j_compmedimag_2019_101647 crossref_primary_10_1016_j_compmedimag_2019_101647 elsevier_sciencedirect_doi_10_1016_j_compmedimag_2019_101647 elsevier_clinicalkeyesjournals_1_s2_0_S0895611118304105 elsevier_clinicalkey_doi_10_1016_j_compmedimag_2019_101647
PublicationCentury	2000
PublicationDate	2019-10-01
PublicationDateYYYYMMDD	2019-10-01
PublicationDate_xml	– month: 10 year: 2019 text: 2019-10-01 day: 01
PublicationDecade	2010
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	Computerized medical imaging and graphics
PublicationTitleAlternate	Comput Med Imaging Graph
PublicationYear	2019
Publisher	Elsevier Ltd Elsevier Science Ltd Elsevier
Publisher_xml	– name: Elsevier Ltd – name: Elsevier Science Ltd – name: Elsevier
References	Walter, Kruessell, Gindele, Brochhagen, Gossmann, Landwehr (bib0295) 2003; 76 Fogtmann, Seshamani, Kroenke, Cheng, Chapman, Wilm, Rousseau, Studholme (bib0035) 2014; 33 Milanfar (bib0175) 2010 Pham, Tor-Díez, Meunier, Bednarek, Fablet, Passat, Rousseau (bib0200) 2019 Ballester, Zisserman, Brady (bib0010) 2002; 6 Lim, Son, Kim, Nah, Lee (bib0155) 2017 Johnson, Alahi, Fei-Fei (bib0105) 2016 Pascanu, Mikolov, Bengio (bib0190) 2013; 28 Huang, Liu, Van Der Maaten, Weinberger (bib0065) 2017 Timofte, De Smet, Van Gool (bib0270) 2013 Ancel, Goffinet (bib0005) 2014 Krizhevsky, Sutskever, Hinton (bib0135) 2012 He, Zhang, Ren, Sun (bib0060) 2016 Jenkinson, Beckmann, Behrens, Woolrich, Smith (bib0085) 2012; 62 Manjón, Coupé, Buades, Fonov, Collins, Robles (bib0170) 2010; 14 Steenkiste, Jeurissen, Veraart, Den Dekker, Parizel, Poot, Sijbers (bib0250) 2016; 75 Jia, Shelhamer, Donahue, Karayev, Long, Girshick, Guadarrama, Darrell (bib0095) 2014 Oktay, Bai, Lee, Guerrero, Kamnitsas, Caballero, de Marvao, Cook, O’Regan, Rueckert (bib0185) 2016 Tajbakhsh, Shin, Gurudu, Hurst, Kendall, Gotway, Liang (bib0255) 2016; 35 Shi, Cheng, Wang, Yap, Shen (bib0235) 2015; 34 Zhao, Gallo, Frosio, Kautz (bib0315) 2017 LeCun, Bottou, Bengio, Haffner (bib0145) 1998; 86 Wang, Bovik, Sheikh, Simoncelli (bib0300) 2004; 13 Kamnitsas, Ledig, Newcombe, Simpson, Kane, Menon, Rueckert, Glocker (bib0115) 2017; 36 Scherrer, Gholipour, Warfield (bib0230) 2012; 16 Kainz, Steinberger, Wein, Kuklisova-Murgasova, Malamateniou, Keraudren, Torsney-Weir, Rutherford, Aljabar, Hajnal (bib0110) 2015; 34 Kim, Lee, Lee (bib0125) 2016 Rueda, Malpica, Romero (bib0225) 2013; 17 Pham, Ducournau, Fablet, Rousseau (bib0195) 2017 Glorot, Bengio (bib0045) 2010 Shi, Caballero, Huszar, Totz, Aitken, Bishop, Rueckert, Wang (bib0240) 2016 Zeyde, Elad, Protter (bib0305) 2012 Jog, Carass, Prince (bib0100) 2016 Ioffe, Szegedy (bib0075) 2015 Timofte, Rothe, Van Gool (bib0280) 2016 Simonyan, Zisserman (bib0245) 2014 Poot, Jeurissen, Bastiaensen, Veraart, Van Hecke, Parizel, Sijbers (bib0205) 2013; 69 Timofte, Agustsson, Van Gool, Yang, Zhang (bib0265) 2017 Dong, Loy, Tang (bib0030) 2016 Bengio, Simard, Frasconi (bib0015) 1994; 5 Rousseau, Initiative (bib0215) 2010; 14 Dong, Loy, He, Tang (bib0025) 2016; 38 Ledig, Theis, Huszár, Caballero, Cunningham, Acosta, Aitken, Tejani, Totz, Wang (bib0150) 2017 Kim, Lee, Lee (bib0120) 2016 Jia, Gholipour, He, Warfield (bib0090) 2017; 36 Chen, Xie, Zhou, Shi, Christodoulou, Li (bib0020) 2018 Gholipour, Estroff, Warfield (bib0040) 2010; 29 Landman, Huang, Gifford, Vikram, Lim, Farrell, Bogovic, Hua, Chen, Jarso (bib0140) 2011; 54 Nesterov (bib0180) 1983 Kingma, Ba (bib0130) 2015 Timofte, De Smet, Van Gool (bib0275) 2014 Greenspan (bib0050) 2008; 52 Tieleman, Hinton (bib0260) 2012; 4 He, Zhang, Ren, Sun (bib0055) 2015 Hughes, Grande, Murgasova, Hutter, Price, Gomes, Allsop, Steinweg, Tusor, Wurie (bib0070) 2017 Jain, Sima, Nezhad, Hangel, Bogner, Williams, Van Huffel, Maes, Smeets (bib0080) 2017; 11 Van Steenkiste, Poot, Jeurissen, Den Dekker, Vanhevel, Parizel, Sijbers (bib0290) 2017; 77 Manjón, Coupé, Buades, Collins, Robles (bib0165) 2010; 2010 Zhao, Carass, Dewey, Prince (bib0310) 2018 Tor-Díez, Pham, Meunier, Faisan, Bloch, Bednarek, Passat, Rousseau (bib0285) 2019 Ramos-Llordén, Arnold, Van Steenkiste, Jeurissen, Vanhevel, Van Audekerke, Verhoye, Sijbers (bib0210) 2017; 36 Rousseau, Kim, Studholme, Koob, Dietemann (bib0220) 2010 Makropoulos, Robinson, Schuh, Wright, Fitzgibbon, Bozek, Counsell, Steinweg, Vecchiato, Passerat-Palmbach (bib0160) 2018; 173 Wang (10.1016/j.compmedimag.2019.101647_bib0300) 2004; 13 Dong (10.1016/j.compmedimag.2019.101647_bib0030) 2016 Ledig (10.1016/j.compmedimag.2019.101647_bib0150) 2017 Tajbakhsh (10.1016/j.compmedimag.2019.101647_bib0255) 2016; 35 Makropoulos (10.1016/j.compmedimag.2019.101647_bib0160) 2018; 173 Van Steenkiste (10.1016/j.compmedimag.2019.101647_bib0290) 2017; 77 Oktay (10.1016/j.compmedimag.2019.101647_bib0185) 2016 Manjón (10.1016/j.compmedimag.2019.101647_bib0165) 2010; 2010 Rousseau (10.1016/j.compmedimag.2019.101647_bib0215) 2010; 14 Zhao (10.1016/j.compmedimag.2019.101647_bib0310) 2018 Timofte (10.1016/j.compmedimag.2019.101647_bib0275) 2014 Chen (10.1016/j.compmedimag.2019.101647_bib0020) 2018 Glorot (10.1016/j.compmedimag.2019.101647_bib0045) 2010 Kingma (10.1016/j.compmedimag.2019.101647_bib0130) 2015 Kim (10.1016/j.compmedimag.2019.101647_bib0120) 2016 Manjón (10.1016/j.compmedimag.2019.101647_bib0170) 2010; 14 Ramos-Llordén (10.1016/j.compmedimag.2019.101647_bib0210) 2017; 36 Jain (10.1016/j.compmedimag.2019.101647_bib0080) 2017; 11 Dong (10.1016/j.compmedimag.2019.101647_bib0025) 2016; 38 Nesterov (10.1016/j.compmedimag.2019.101647_bib0180) 1983 Tor-Díez (10.1016/j.compmedimag.2019.101647_bib0285) 2019 Pascanu (10.1016/j.compmedimag.2019.101647_bib0190) 2013; 28 Ballester (10.1016/j.compmedimag.2019.101647_bib0010) 2002; 6 Kamnitsas (10.1016/j.compmedimag.2019.101647_bib0115) 2017; 36 Zhao (10.1016/j.compmedimag.2019.101647_bib0315) 2017 LeCun (10.1016/j.compmedimag.2019.101647_bib0145) 1998; 86 Walter (10.1016/j.compmedimag.2019.101647_bib0295) 2003; 76 Simonyan (10.1016/j.compmedimag.2019.101647_bib0245) 2014 Kainz (10.1016/j.compmedimag.2019.101647_bib0110) 2015; 34 Zeyde (10.1016/j.compmedimag.2019.101647_bib0305) 2012 Landman (10.1016/j.compmedimag.2019.101647_bib0140) 2011; 54 Jia (10.1016/j.compmedimag.2019.101647_bib0095) 2014 Scherrer (10.1016/j.compmedimag.2019.101647_bib0230) 2012; 16 Shi (10.1016/j.compmedimag.2019.101647_bib0240) 2016 Rousseau (10.1016/j.compmedimag.2019.101647_bib0220) 2010 Pham (10.1016/j.compmedimag.2019.101647_bib0195) 2017 Greenspan (10.1016/j.compmedimag.2019.101647_bib0050) 2008; 52 Ioffe (10.1016/j.compmedimag.2019.101647_bib0075) 2015 Poot (10.1016/j.compmedimag.2019.101647_bib0205) 2013; 69 Fogtmann (10.1016/j.compmedimag.2019.101647_bib0035) 2014; 33 Tieleman (10.1016/j.compmedimag.2019.101647_bib0260) 2012; 4 Hughes (10.1016/j.compmedimag.2019.101647_bib0070) 2017 Jenkinson (10.1016/j.compmedimag.2019.101647_bib0085) 2012; 62 Jia (10.1016/j.compmedimag.2019.101647_bib0090) 2017; 36 Milanfar (10.1016/j.compmedimag.2019.101647_bib0175) 2010 Timofte (10.1016/j.compmedimag.2019.101647_bib0270) 2013 Timofte (10.1016/j.compmedimag.2019.101647_bib0280) 2016 Lim (10.1016/j.compmedimag.2019.101647_bib0155) 2017 Kim (10.1016/j.compmedimag.2019.101647_bib0125) 2016 Rueda (10.1016/j.compmedimag.2019.101647_bib0225) 2013; 17 Ancel (10.1016/j.compmedimag.2019.101647_bib0005) 2014 Huang (10.1016/j.compmedimag.2019.101647_bib0065) 2017 Gholipour (10.1016/j.compmedimag.2019.101647_bib0040) 2010; 29 Timofte (10.1016/j.compmedimag.2019.101647_bib0265) 2017 Krizhevsky (10.1016/j.compmedimag.2019.101647_bib0135) 2012 Shi (10.1016/j.compmedimag.2019.101647_bib0235) 2015; 34 Steenkiste (10.1016/j.compmedimag.2019.101647_bib0250) 2016; 75 Bengio (10.1016/j.compmedimag.2019.101647_bib0015) 1994; 5 He (10.1016/j.compmedimag.2019.101647_bib0055) 2015 Jog (10.1016/j.compmedimag.2019.101647_bib0100) 2016 Johnson (10.1016/j.compmedimag.2019.101647_bib0105) 2016 He (10.1016/j.compmedimag.2019.101647_bib0060) 2016 Pham (10.1016/j.compmedimag.2019.101647_bib0200) 2019
References_xml	– volume: 77 start-page: 1818 year: 2017 end-page: 1830 ident: bib0290 article-title: Super-resolution T1 estimation: quantitative high resolution T1 mapping from a set of low resolution T1-weighted images with different slice orientations publication-title: Magn. Reson. Med. – volume: 36 start-page: 1182 year: 2017 end-page: 1193 ident: bib0090 article-title: A new sparse representation framework for reconstruction of an isotropic high spatial resolution MR volume from orthogonal anisotropic resolution scans publication-title: IEEE Trans. Med. Imaging – start-page: 553 year: 2016 end-page: 560 ident: bib0100 article-title: Self super-resolution for magnetic resonance images publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 675 year: 2014 end-page: 678 ident: bib0095 article-title: Caffe: convolutional architecture for fast feature embedding publication-title: Proceedings of the 22nd ACM International Conference on Multimedia – start-page: 3 year: 2017 ident: bib0155 article-title: Enhanced deep residual networks for single image super-resolution publication-title: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops – start-page: 246 year: 2016 end-page: 254 ident: bib0185 article-title: Multi-input cardiac image super-resolution using convolutional neural networks publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 770 year: 2016 end-page: 778 ident: bib0060 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 365 year: 2018 end-page: 368 ident: bib0310 article-title: Self super-resolution for magnetic resonance images using deep networks publication-title: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) – volume: 33 start-page: 272 year: 2014 end-page: 289 ident: bib0035 article-title: A unified approach to diffusion direction sensitive slice registration and 3D DTI reconstruction from moving fetal brain anatomy publication-title: IEEE Trans. Med. Imaging – volume: 34 start-page: 2459 year: 2015 end-page: 2466 ident: bib0235 article-title: LRTV: MR image super-resolution with low-rank and total variation regularizations publication-title: IEEE Trans. Med. Imaging – volume: 76 start-page: 696 year: 2003 end-page: 703 ident: bib0295 article-title: Imaging of renal lesions: evaluation of fast MRI and helical CT publication-title: Br. J. Radiol. – year: 2019 ident: bib0285 article-title: Evaluation of cortical segmentation pipelines on clinical neonatal MRI data publication-title: 41st International Engineering in Medicine and Biology Conference. (EMBC 2019) – volume: 17 start-page: 113 year: 2013 end-page: 132 ident: bib0225 article-title: Single-image super-resolution of brain MR images using overcomplete dictionaries publication-title: Med. Image Anal. – start-page: 1920 year: 2013 end-page: 1927 ident: bib0270 article-title: Anchored neighborhood regression for fast example-based super-resolution publication-title: 2013 IEEE International Conference on Computer Vision (ICCV) – start-page: 1026 year: 2015 end-page: 1034 ident: bib0055 article-title: Delving deep into rectifiers: surpassing human-level performance on imagenet classification publication-title: Proceedings of the IEEE International Conference on Computer Vision – volume: 13 start-page: 600 year: 2004 end-page: 612 ident: bib0300 article-title: Image quality assessment: from error visibility to structural similarity publication-title: IEEE Trans. Image Process. – start-page: 4700 year: 2017 end-page: 4708 ident: bib0065 article-title: Densely connected convolutional networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 1097 year: 2012 end-page: 1105 ident: bib0135 article-title: Imagenet classification with deep convolutional neural networks publication-title: Advances in Neural Information Processing Systems – year: 2016 ident: bib0120 article-title: Accurate image super-resolution using very deep convolutional networks publication-title: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition – volume: 173 start-page: 88 year: 2018 end-page: 112 ident: bib0160 article-title: The developing human connectome project: a minimal processing pipeline for neonatal cortical surface reconstruction publication-title: Neuroimage – volume: 86 start-page: 2278 year: 1998 end-page: 2324 ident: bib0145 article-title: Gradient-based learning applied to document recognition publication-title: Proc. IEEE – year: 2019 ident: bib0200 article-title: Simultaneous super-resolution and segmentation using a generative adversarial network: application to neonatal brain MRI publication-title: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) – year: 2016 ident: bib0125 article-title: Deeply-recursive convolutional network for image super-resolution publication-title: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition – start-page: 25 year: 2017 end-page: 29 ident: bib0070 article-title: The developing human connectome: announcing the first release of open access neonatal brain imaging publication-title: 23rd Annual Meeting of the Organization for Human Brain Mapping – year: 2017 ident: bib0150 article-title: Photo-realistic single image super-resolution using a generative adversarial network publication-title: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition – volume: 14 start-page: 594 year: 2010 end-page: 605 ident: bib0215 article-title: A non-local approach for image super-resolution using intermodality priors publication-title: Med. Image Anal. – year: 2017 ident: bib0265 article-title: NTIRE 2017 challenge on single image super-resolution: methods and results publication-title: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops – volume: 34 start-page: 1901 year: 2015 end-page: 1913 ident: bib0110 article-title: Fast volume reconstruction from motion corrupted stacks of 2D slices publication-title: IEEE Trans. Med. Imaging – volume: 2010 start-page: 17 year: 2010 ident: bib0165 article-title: MRI superresolution using self-similarity and image priors publication-title: J. Biomed. Imaging – volume: 36 start-page: 433 year: 2017 end-page: 446 ident: bib0210 article-title: A unified maximum likelihood framework for simultaneous motion and publication-title: IEEE Trans. Med. Imaging – volume: 75 start-page: 181 year: 2016 end-page: 195 ident: bib0250 article-title: Super-resolution reconstruction of diffusion parameters from diffusion-weighted images with different slice orientations publication-title: Magn. Reson. Med. – start-page: 197 year: 2017 end-page: 200 ident: bib0195 article-title: Brain MRI super-resolution using deep 3D convolutional networks publication-title: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) – start-page: 355 year: 2010 end-page: 362 ident: bib0220 article-title: On super-resolution for fetal brain MRI publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 1874 year: 2016 end-page: 1883 ident: bib0240 article-title: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 739 year: 2018 end-page: 742 ident: bib0020 article-title: Brain MRI super resolution using 3D deep densely connected neural networks publication-title: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) – volume: 62 start-page: 782 year: 2012 end-page: 790 ident: bib0085 article-title: FSL publication-title: Neuroimage – volume: 28 start-page: 1310 year: 2013 end-page: 1318 ident: bib0190 article-title: On the difficulty of training recurrent neural networks publication-title: ICML – volume: 4 start-page: 26 year: 2012 end-page: 31 ident: bib0260 article-title: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude publication-title: COURSERA: Neural Netw. Mach. Learn. – start-page: 1865 year: 2016 end-page: 1873 ident: bib0280 article-title: Seven ways to improve example-based single image super resolution publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 6 start-page: 389 year: 2002 end-page: 405 ident: bib0010 article-title: Estimation of the partial volume effect in MRI publication-title: Med. Image Anal. – volume: 35 start-page: 1299 year: 2016 end-page: 1312 ident: bib0255 article-title: Convolutional neural networks for medical image analysis: full training or fine tuning? publication-title: IEEE Trans. Med. Imaging – volume: 16 start-page: 1465 year: 2012 end-page: 1476 ident: bib0230 article-title: Super-resolution reconstruction to increase the spatial resolution of diffusion weighted images from orthogonal anisotropic acquisitions publication-title: Med. Image Anal. – volume: 52 start-page: 43 year: 2008 end-page: 63 ident: bib0050 article-title: Super-resolution in medical imaging publication-title: Comput. J. – volume: 69 start-page: 103 year: 2013 end-page: 113 ident: bib0205 article-title: Super-resolution for multislice diffusion tensor imaging publication-title: Magn. Reson. Med. – volume: 36 start-page: 61 year: 2017 end-page: 78 ident: bib0115 article-title: Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation publication-title: Med. Image Anal. – year: 2010 ident: bib0175 article-title: Super-Resolution Imaging – start-page: 2017 year: 2017 ident: bib0315 article-title: Loss functions for neural networks for image processing publication-title: IEEE Trans. Comput. Imaging – year: 2015 ident: bib0130 article-title: Adam: a method for stochastic optimization publication-title: International Conference on Learning Representations – year: 2014 ident: bib0245 article-title: Very deep convolutional networks for large-scale image recognition publication-title: International Conference on Learning Representations – volume: 5 start-page: 157 year: 1994 end-page: 166 ident: bib0015 article-title: Learning long-term dependencies with gradient descent is difficult publication-title: IEEE Trans. Neural Netw. – start-page: 249 year: 2010 end-page: 256 ident: bib0045 article-title: Understanding the difficulty of training deep feedforward neural networks publication-title: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics – start-page: 111 year: 2014 end-page: 126 ident: bib0275 article-title: A+: adjusted anchored neighborhood regression for fast super-resolution publication-title: Computer Vision-ACCV 2014 – start-page: 14 year: 2014 end-page: 97 ident: bib0005 article-title: EPIPAGE2: A preterm birth cohort in France in 2011 publication-title: BMC Pediatr. – start-page: 391 year: 2016 end-page: 407 ident: bib0030 article-title: Accelerating the super-resolution convolutional neural network publication-title: European Conference on Computer Vision – volume: 54 start-page: 2854 year: 2011 end-page: 2866 ident: bib0140 article-title: Multi-parametric neuroimaging reproducibility: a 3T resource study publication-title: Neuroimage – volume: 14 start-page: 784 year: 2010 end-page: 792 ident: bib0170 article-title: Non-local MRI upsampling publication-title: Med. Image Anal. – start-page: 448 year: 2015 end-page: 456 ident: bib0075 article-title: Batch normalization: accelerating deep network training by reducing internal covariate shift publication-title: International Conference on Machine Learning – volume: 29 start-page: 1739 year: 2010 end-page: 1758 ident: bib0040 article-title: Robust super-resolution volume reconstruction from slice acquisitions: application to fetal brain MRI publication-title: IEEE Trans. Med. Imaging – start-page: 711 year: 2012 end-page: 730 ident: bib0305 article-title: On single image scale-up using sparse-representations publication-title: Curves and Surfaces – volume: 11 start-page: 13 year: 2017 ident: bib0080 article-title: Patch-based super-resolution of MR spectroscopic images: application to multiple sclerosis publication-title: Front. Neurosci. – start-page: 372 year: 1983 end-page: 376 ident: bib0180 article-title: A method of solving a convex programming problem with convergence rate publication-title: Soviet Mathematics Doklady – start-page: 694 year: 2016 end-page: 711 ident: bib0105 article-title: Perceptual losses for real-time style transfer and super-resolution publication-title: European Conference on Computer Vision – volume: 38 start-page: 295 year: 2016 end-page: 307 ident: bib0025 article-title: Image super-resolution using deep convolutional networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 17 start-page: 113 year: 2013 ident: 10.1016/j.compmedimag.2019.101647_bib0225 article-title: Single-image super-resolution of brain MR images using overcomplete dictionaries publication-title: Med. Image Anal. doi: 10.1016/j.media.2012.09.003 – volume: 6 start-page: 389 year: 2002 ident: 10.1016/j.compmedimag.2019.101647_bib0010 article-title: Estimation of the partial volume effect in MRI publication-title: Med. Image Anal. doi: 10.1016/S1361-8415(02)00061-0 – volume: 34 start-page: 2459 year: 2015 ident: 10.1016/j.compmedimag.2019.101647_bib0235 article-title: LRTV: MR image super-resolution with low-rank and total variation regularizations publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2015.2437894 – year: 2019 ident: 10.1016/j.compmedimag.2019.101647_bib0200 article-title: Simultaneous super-resolution and segmentation using a generative adversarial network: application to neonatal brain MRI publication-title: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) doi: 10.1109/ISBI.2019.8759255 – start-page: 1026 year: 2015 ident: 10.1016/j.compmedimag.2019.101647_bib0055 article-title: Delving deep into rectifiers: surpassing human-level performance on imagenet classification publication-title: Proceedings of the IEEE International Conference on Computer Vision – year: 2010 ident: 10.1016/j.compmedimag.2019.101647_bib0175 – year: 2017 ident: 10.1016/j.compmedimag.2019.101647_bib0150 article-title: Photo-realistic single image super-resolution using a generative adversarial network publication-title: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition – start-page: 711 year: 2012 ident: 10.1016/j.compmedimag.2019.101647_bib0305 article-title: On single image scale-up using sparse-representations publication-title: Curves and Surfaces doi: 10.1007/978-3-642-27413-8_47 – volume: 54 start-page: 2854 year: 2011 ident: 10.1016/j.compmedimag.2019.101647_bib0140 article-title: Multi-parametric neuroimaging reproducibility: a 3T resource study publication-title: Neuroimage doi: 10.1016/j.neuroimage.2010.11.047 – start-page: 3 year: 2017 ident: 10.1016/j.compmedimag.2019.101647_bib0155 article-title: Enhanced deep residual networks for single image super-resolution publication-title: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops – volume: 16 start-page: 1465 year: 2012 ident: 10.1016/j.compmedimag.2019.101647_bib0230 article-title: Super-resolution reconstruction to increase the spatial resolution of diffusion weighted images from orthogonal anisotropic acquisitions publication-title: Med. Image Anal. doi: 10.1016/j.media.2012.05.003 – volume: 34 start-page: 1901 year: 2015 ident: 10.1016/j.compmedimag.2019.101647_bib0110 article-title: Fast volume reconstruction from motion corrupted stacks of 2D slices publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2015.2415453 – volume: 11 start-page: 13 year: 2017 ident: 10.1016/j.compmedimag.2019.101647_bib0080 article-title: Patch-based super-resolution of MR spectroscopic images: application to multiple sclerosis publication-title: Front. Neurosci. doi: 10.3389/fnins.2017.00013 – volume: 76 start-page: 696 year: 2003 ident: 10.1016/j.compmedimag.2019.101647_bib0295 article-title: Imaging of renal lesions: evaluation of fast MRI and helical CT publication-title: Br. J. Radiol. doi: 10.1259/bjr/33169417 – start-page: 675 year: 2014 ident: 10.1016/j.compmedimag.2019.101647_bib0095 article-title: Caffe: convolutional architecture for fast feature embedding publication-title: Proceedings of the 22nd ACM International Conference on Multimedia doi: 10.1145/2647868.2654889 – volume: 69 start-page: 103 year: 2013 ident: 10.1016/j.compmedimag.2019.101647_bib0205 article-title: Super-resolution for multislice diffusion tensor imaging publication-title: Magn. Reson. Med. doi: 10.1002/mrm.24233 – year: 2015 ident: 10.1016/j.compmedimag.2019.101647_bib0130 article-title: Adam: a method for stochastic optimization publication-title: International Conference on Learning Representations – year: 2019 ident: 10.1016/j.compmedimag.2019.101647_bib0285 article-title: Evaluation of cortical segmentation pipelines on clinical neonatal MRI data publication-title: 41st International Engineering in Medicine and Biology Conference. (EMBC 2019) – start-page: 694 year: 2016 ident: 10.1016/j.compmedimag.2019.101647_bib0105 article-title: Perceptual losses for real-time style transfer and super-resolution publication-title: European Conference on Computer Vision – start-page: 1097 year: 2012 ident: 10.1016/j.compmedimag.2019.101647_bib0135 article-title: Imagenet classification with deep convolutional neural networks publication-title: Advances in Neural Information Processing Systems – volume: 38 start-page: 295 year: 2016 ident: 10.1016/j.compmedimag.2019.101647_bib0025 article-title: Image super-resolution using deep convolutional networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2015.2439281 – volume: 36 start-page: 1182 year: 2017 ident: 10.1016/j.compmedimag.2019.101647_bib0090 article-title: A new sparse representation framework for reconstruction of an isotropic high spatial resolution MR volume from orthogonal anisotropic resolution scans publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2017.2656907 – start-page: 246 year: 2016 ident: 10.1016/j.compmedimag.2019.101647_bib0185 article-title: Multi-input cardiac image super-resolution using convolutional neural networks publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 1920 year: 2013 ident: 10.1016/j.compmedimag.2019.101647_bib0270 article-title: Anchored neighborhood regression for fast example-based super-resolution publication-title: 2013 IEEE International Conference on Computer Vision (ICCV) doi: 10.1109/ICCV.2013.241 – start-page: 2017 year: 2017 ident: 10.1016/j.compmedimag.2019.101647_bib0315 article-title: Loss functions for neural networks for image processing publication-title: IEEE Trans. Comput. Imaging – volume: 29 start-page: 1739 year: 2010 ident: 10.1016/j.compmedimag.2019.101647_bib0040 article-title: Robust super-resolution volume reconstruction from slice acquisitions: application to fetal brain MRI publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2010.2051680 – volume: 28 start-page: 1310 issue: 3 year: 2013 ident: 10.1016/j.compmedimag.2019.101647_bib0190 article-title: On the difficulty of training recurrent neural networks publication-title: ICML – start-page: 4700 year: 2017 ident: 10.1016/j.compmedimag.2019.101647_bib0065 article-title: Densely connected convolutional networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 197 year: 2017 ident: 10.1016/j.compmedimag.2019.101647_bib0195 article-title: Brain MRI super-resolution using deep 3D convolutional networks publication-title: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) doi: 10.1109/ISBI.2017.7950500 – volume: 62 start-page: 782 year: 2012 ident: 10.1016/j.compmedimag.2019.101647_bib0085 article-title: FSL publication-title: Neuroimage doi: 10.1016/j.neuroimage.2011.09.015 – volume: 13 start-page: 600 year: 2004 ident: 10.1016/j.compmedimag.2019.101647_bib0300 article-title: Image quality assessment: from error visibility to structural similarity publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2003.819861 – volume: 33 start-page: 272 year: 2014 ident: 10.1016/j.compmedimag.2019.101647_bib0035 article-title: A unified approach to diffusion direction sensitive slice registration and 3D DTI reconstruction from moving fetal brain anatomy publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2013.2284014 – volume: 35 start-page: 1299 year: 2016 ident: 10.1016/j.compmedimag.2019.101647_bib0255 article-title: Convolutional neural networks for medical image analysis: full training or fine tuning? publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2016.2535302 – volume: 36 start-page: 433 year: 2017 ident: 10.1016/j.compmedimag.2019.101647_bib0210 article-title: A unified maximum likelihood framework for simultaneous motion and t _ {1} estimation in quantitative mr t _ {1} mapping publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2016.2611653 – volume: 86 start-page: 2278 year: 1998 ident: 10.1016/j.compmedimag.2019.101647_bib0145 article-title: Gradient-based learning applied to document recognition publication-title: Proc. IEEE doi: 10.1109/5.726791 – start-page: 365 year: 2018 ident: 10.1016/j.compmedimag.2019.101647_bib0310 article-title: Self super-resolution for magnetic resonance images using deep networks publication-title: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) doi: 10.1109/ISBI.2018.8363594 – volume: 173 start-page: 88 year: 2018 ident: 10.1016/j.compmedimag.2019.101647_bib0160 article-title: The developing human connectome project: a minimal processing pipeline for neonatal cortical surface reconstruction publication-title: Neuroimage doi: 10.1016/j.neuroimage.2018.01.054 – year: 2017 ident: 10.1016/j.compmedimag.2019.101647_bib0265 article-title: NTIRE 2017 challenge on single image super-resolution: methods and results publication-title: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops – volume: 75 start-page: 181 year: 2016 ident: 10.1016/j.compmedimag.2019.101647_bib0250 article-title: Super-resolution reconstruction of diffusion parameters from diffusion-weighted images with different slice orientations publication-title: Magn. Reson. Med. doi: 10.1002/mrm.25597 – volume: 5 start-page: 157 year: 1994 ident: 10.1016/j.compmedimag.2019.101647_bib0015 article-title: Learning long-term dependencies with gradient descent is difficult publication-title: IEEE Trans. Neural Netw. doi: 10.1109/72.279181 – year: 2016 ident: 10.1016/j.compmedimag.2019.101647_bib0120 article-title: Accurate image super-resolution using very deep convolutional networks publication-title: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition – start-page: 1865 year: 2016 ident: 10.1016/j.compmedimag.2019.101647_bib0280 article-title: Seven ways to improve example-based single image super resolution publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 770 year: 2016 ident: 10.1016/j.compmedimag.2019.101647_bib0060 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 553 year: 2016 ident: 10.1016/j.compmedimag.2019.101647_bib0100 article-title: Self super-resolution for magnetic resonance images publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – year: 2014 ident: 10.1016/j.compmedimag.2019.101647_bib0245 article-title: Very deep convolutional networks for large-scale image recognition publication-title: International Conference on Learning Representations – start-page: 1874 year: 2016 ident: 10.1016/j.compmedimag.2019.101647_bib0240 article-title: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 14 year: 2014 ident: 10.1016/j.compmedimag.2019.101647_bib0005 article-title: EPIPAGE2: A preterm birth cohort in France in 2011 publication-title: BMC Pediatr. – volume: 77 start-page: 1818 year: 2017 ident: 10.1016/j.compmedimag.2019.101647_bib0290 article-title: Super-resolution T1 estimation: quantitative high resolution T1 mapping from a set of low resolution T1-weighted images with different slice orientations publication-title: Magn. Reson. Med. doi: 10.1002/mrm.26262 – start-page: 249 year: 2010 ident: 10.1016/j.compmedimag.2019.101647_bib0045 article-title: Understanding the difficulty of training deep feedforward neural networks publication-title: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics – start-page: 25 year: 2017 ident: 10.1016/j.compmedimag.2019.101647_bib0070 article-title: The developing human connectome: announcing the first release of open access neonatal brain imaging publication-title: 23rd Annual Meeting of the Organization for Human Brain Mapping – start-page: 391 year: 2016 ident: 10.1016/j.compmedimag.2019.101647_bib0030 article-title: Accelerating the super-resolution convolutional neural network publication-title: European Conference on Computer Vision – volume: 14 start-page: 594 year: 2010 ident: 10.1016/j.compmedimag.2019.101647_bib0215 article-title: A non-local approach for image super-resolution using intermodality priors publication-title: Med. Image Anal. doi: 10.1016/j.media.2010.04.005 – volume: 4 start-page: 26 year: 2012 ident: 10.1016/j.compmedimag.2019.101647_bib0260 article-title: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude publication-title: COURSERA: Neural Netw. Mach. Learn. – start-page: 739 year: 2018 ident: 10.1016/j.compmedimag.2019.101647_bib0020 article-title: Brain MRI super resolution using 3D deep densely connected neural networks publication-title: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) doi: 10.1109/ISBI.2018.8363679 – start-page: 355 year: 2010 ident: 10.1016/j.compmedimag.2019.101647_bib0220 article-title: On super-resolution for fetal brain MRI publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – volume: 2010 start-page: 17 year: 2010 ident: 10.1016/j.compmedimag.2019.101647_bib0165 article-title: MRI superresolution using self-similarity and image priors publication-title: J. Biomed. Imaging – start-page: 111 year: 2014 ident: 10.1016/j.compmedimag.2019.101647_bib0275 article-title: A+: adjusted anchored neighborhood regression for fast super-resolution publication-title: Computer Vision-ACCV 2014 – start-page: 448 year: 2015 ident: 10.1016/j.compmedimag.2019.101647_bib0075 article-title: Batch normalization: accelerating deep network training by reducing internal covariate shift publication-title: International Conference on Machine Learning – year: 2016 ident: 10.1016/j.compmedimag.2019.101647_bib0125 article-title: Deeply-recursive convolutional network for image super-resolution publication-title: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition – volume: 14 start-page: 784 year: 2010 ident: 10.1016/j.compmedimag.2019.101647_bib0170 article-title: Non-local MRI upsampling publication-title: Med. Image Anal. doi: 10.1016/j.media.2010.05.010 – volume: 36 start-page: 61 year: 2017 ident: 10.1016/j.compmedimag.2019.101647_bib0115 article-title: Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation publication-title: Med. Image Anal. doi: 10.1016/j.media.2016.10.004 – start-page: 372 year: 1983 ident: 10.1016/j.compmedimag.2019.101647_bib0180 article-title: A method of solving a convex programming problem with convergence rate o(1/k2) publication-title: Soviet Mathematics Doklady – volume: 52 start-page: 43 year: 2008 ident: 10.1016/j.compmedimag.2019.101647_bib0050 article-title: Super-resolution in medical imaging publication-title: Comput. J. doi: 10.1093/comjnl/bxm075
SSID	ssj0002071
Score	2.589324
Snippet	[Display omitted] •A residual-based deep 3D CNN architecture for super-resolution.•Comprehensive performance analysis of key elements of neural... Graphical abstract The purpose of super-resolution approaches is to overcome the hardware limitations and the clinical requirements of imaging procedures by reconstructing...
SourceID	hal proquest pubmed crossref elsevier
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	101647
SubjectTerms	3D convolutional neural network Artificial neural networks Brain Brain MRI Computer Science Computer Vision and Pattern Recognition Convolution Cortex Image acquisition Image enhancement Image Processing Image reconstruction Image resolution Internal Medicine Learning Magnetic resonance imaging Medical Imaging Neural networks Neuroimaging NMR Nuclear magnetic resonance Optimization Other Post-processing Resonance Scaling factors Structural analysis Super-resolution Training Transfer learning
Title	Multiscale brain MRI super-resolution using deep 3D convolutional networks
URI	https://www.clinicalkey.com/#!/content/1-s2.0-S0895611118304105 https://www.clinicalkey.es/playcontent/1-s2.0-S0895611118304105 https://dx.doi.org/10.1016/j.compmedimag.2019.101647 https://www.ncbi.nlm.nih.gov/pubmed/31493703 https://www.proquest.com/docview/2312231074 https://www.proquest.com/docview/2286915653 https://hal.science/hal-01635455
Volume	77
WOSCitedRecordID	wos000493216400002&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: PRVESC databaseName: ScienceDirect database customDbUrl: eissn: 1879-0771 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002071 issn: 0895-6111 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db5swELeSdqr2Mu2zY-sqOu0togJDMEx7iZJMaddU1dZJebPAGJUqJRGUqNrftj9u5w8IXRcpm7QXiAwGc_fL-e58vkPog4uJUDSY5TKwVb3Y4VYQeoEl02XZiR3FXGbXPyPn58FsFl50Oj_rvTCrOcnz4O4uXP5XVkMbMFtsnf0LdjcPhQb4DUyHI7AdjlsxXm6pLYH0vBeL-g-96deTXlkteWGBaa1f3aukjyDhfNlzRzL2XF8BluUqNLxsK6519YfsB2ioN3p1J7tRNY6E811mvm6Fzl_oDdjDq8yaZLxau7MLaySX50fKeT2Mivmi6TblVZ4pGE3UIv5cnoLW8j9P8qjgqniQcP3PM952XjhhEwbXyLiwD9arlrdaIOu6LkqiOjLjWWt-Xjc8kP7KEXEtmLcUlAAiiOC98Lj9kHbG7fHwi2OV-Ni2vomRiIGAiLNF6Ov9m5W9REtMbfrg1i7axaQfgkzdHZyMZ6eNJoBtafA3H7mHjtbxhRsGuUk_6l6JQN1NVpDUhi6foifajDEHCn7PUIfnz9HeVAdqvECnaxSaEoUmoND8HYWmRKEpUGi6I_MeCs0ahS_R98_jy-HE0mU7LObb7q1FMA9j7IlNyiz2-nHKfcxImjKC436UEIf5SWLHbgKnGCeg87LIY8yOMItt7gfuK7STL3L-Gpmc-H6YemngeI7HiBPHnLM0ArqyxPV8x0BBTSzKdE57UVplTuvgxWvaojMVdKaKzgbCTdelSuyyTaePNUdovXMZ5loKANymM_lTZ15q4VHSTQAz0Kemp1aMlcK77YvfA3iarxQJ5SeDMyra4LoLNlR_hQ10UGOLNgMC4w8LA5B4BjpqLsMEJFYVo5wvKrgHB37ogF3oGmhfYbJ5let4YP7Y7pt__vS36PFabhygndui4u_QI7YCDBeHqEtmwaH-2_0CXtYHNA
linkProvider	Elsevier
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=Multiscale+brain+MRI+super-resolution+using+deep+3D+convolutional+networks&rft.jtitle=Computerized+medical+imaging+and+graphics&rft.au=Pham%2C+Chi-Hieu&rft.au=Tor-D%C3%ADez%2C+Carlos&rft.au=Meunier%2C+H%C3%A9l%C3%A8ne&rft.au=Bednarek%2C+Nathalie&rft.date=2019-10-01&rft.issn=0895-6111&rft.volume=77&rft.spage=101647&rft.epage=101647&rft_id=info:doi/10.1016%2Fj.compmedimag.2019.101647&rft.externalDBID=ECK1-s2.0-S0895611118304105&rft.externalDocID=1_s2_0_S0895611118304105
thumbnail_m	http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F08956111%2FS0895611119X00075%2Fcov150h.gif