Personalized synthetic MR imaging with deep learning enhancements
Purpose Personalized synthetic MRI (syn‐MRI) uses MR images of an individual subject acquired at a few design parameters (echo time, repetition time, flip angle) to obtain underlying parametric (ρ,T1,T2)$$ \left(\rho, {\mathrm{T}}_1,{\mathrm{T}}_2\right) $$ maps, from where MR images of that individ...
Uloženo v:
| Vydáno v: | Magnetic resonance in medicine Ročník 89; číslo 4; s. 1634 - 1643 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
United States
Wiley Subscription Services, Inc
01.04.2023
John Wiley and Sons Inc |
| Témata: | |
| ISSN: | 0740-3194, 1522-2594, 1522-2594 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Purpose
Personalized synthetic MRI (syn‐MRI) uses MR images of an individual subject acquired at a few design parameters (echo time, repetition time, flip angle) to obtain underlying parametric (ρ,T1,T2)$$ \left(\rho, {\mathrm{T}}_1,{\mathrm{T}}_2\right) $$ maps, from where MR images of that individual at other design parameter settings are synthesized. However, classical methods that use least‐squares (LS) or maximum likelihood estimators (MLE) are unsatisfactory at higher noise levels because the underlying inverse problem is ill‐posed. This article provides a pipeline to enhance the synthesis of such images in three‐dimensional (3D) using a deep learning (DL) neural network architecture for spatial regularization in a personalized setting where having more than a few training images is impractical.
Methods
Our DL enhancements employ a Deep Image Prior (DIP) with a U‐net type denoising architecture that includes situations with minimal training data, such as personalized syn‐MRI. We provide a general workflow for syn‐MRI from three or more training images. Our workflow, called DIPsyn‐MRI, uses DIP to enhance training images, then obtains parametric images using LS or MLE before synthesizing images at desired design parameter settings. DIPsyn‐MRI is implemented in our publicly available Python package DeepSynMRI available at:
https://github.com/StatPal/DeepSynMRI.
Results
We demonstrate feasibility and improved performance of DIPsyn‐MRI on 3D datasets acquired using the Brainweb interface for spin‐echo and FLASH imaging sequences, at different noise levels. Our DL enhancements improve syn‐MRI in the presence of different intensity nonuniformity levels of the magnetic field, for all but very low noise levels.
Conclusion
This article provides recipes and software to realistically facilitate DL‐enhanced personalized syn‐MRI. |
|---|---|
| AbstractList | Click here
for author‐reader discussions PurposePersonalized synthetic MRI (syn‐MRI) uses MR images of an individual subject acquired at a few design parameters (echo time, repetition time, flip angle) to obtain underlying parametric (ρ,T1,T2)$$ \left(\rho, {\mathrm{T}}_1,{\mathrm{T}}_2\right) $$ maps, from where MR images of that individual at other design parameter settings are synthesized. However, classical methods that use least‐squares (LS) or maximum likelihood estimators (MLE) are unsatisfactory at higher noise levels because the underlying inverse problem is ill‐posed. This article provides a pipeline to enhance the synthesis of such images in three‐dimensional (3D) using a deep learning (DL) neural network architecture for spatial regularization in a personalized setting where having more than a few training images is impractical.MethodsOur DL enhancements employ a Deep Image Prior (DIP) with a U‐net type denoising architecture that includes situations with minimal training data, such as personalized syn‐MRI. We provide a general workflow for syn‐MRI from three or more training images. Our workflow, called DIPsyn‐MRI, uses DIP to enhance training images, then obtains parametric images using LS or MLE before synthesizing images at desired design parameter settings. DIPsyn‐MRI is implemented in our publicly available Python package DeepSynMRI available at: https://github.com/StatPal/DeepSynMRI.ResultsWe demonstrate feasibility and improved performance of DIPsyn‐MRI on 3D datasets acquired using the Brainweb interface for spin‐echo and FLASH imaging sequences, at different noise levels. Our DL enhancements improve syn‐MRI in the presence of different intensity nonuniformity levels of the magnetic field, for all but very low noise levels.ConclusionThis article provides recipes and software to realistically facilitate DL‐enhanced personalized syn‐MRI. Personalized synthetic MRI (syn-MRI) uses MR images of an individual subject acquired at a few design parameters (echo time, repetition time, flip angle) to obtain underlying parametric ( ρ , T 1 , T 2 ) $$ \left(\rho, {\mathrm{T}}_1,{\mathrm{T}}_2\right) $$ maps, from where MR images of that individual at other design parameter settings are synthesized. However, classical methods that use least-squares (LS) or maximum likelihood estimators (MLE) are unsatisfactory at higher noise levels because the underlying inverse problem is ill-posed. This article provides a pipeline to enhance the synthesis of such images in three-dimensional (3D) using a deep learning (DL) neural network architecture for spatial regularization in a personalized setting where having more than a few training images is impractical.PURPOSEPersonalized synthetic MRI (syn-MRI) uses MR images of an individual subject acquired at a few design parameters (echo time, repetition time, flip angle) to obtain underlying parametric ( ρ , T 1 , T 2 ) $$ \left(\rho, {\mathrm{T}}_1,{\mathrm{T}}_2\right) $$ maps, from where MR images of that individual at other design parameter settings are synthesized. However, classical methods that use least-squares (LS) or maximum likelihood estimators (MLE) are unsatisfactory at higher noise levels because the underlying inverse problem is ill-posed. This article provides a pipeline to enhance the synthesis of such images in three-dimensional (3D) using a deep learning (DL) neural network architecture for spatial regularization in a personalized setting where having more than a few training images is impractical.Our DL enhancements employ a Deep Image Prior (DIP) with a U-net type denoising architecture that includes situations with minimal training data, such as personalized syn-MRI. We provide a general workflow for syn-MRI from three or more training images. Our workflow, called DIPsyn-MRI, uses DIP to enhance training images, then obtains parametric images using LS or MLE before synthesizing images at desired design parameter settings. DIPsyn-MRI is implemented in our publicly available Python package DeepSynMRI available at: https://github.com/StatPal/DeepSynMRI.METHODSOur DL enhancements employ a Deep Image Prior (DIP) with a U-net type denoising architecture that includes situations with minimal training data, such as personalized syn-MRI. We provide a general workflow for syn-MRI from three or more training images. Our workflow, called DIPsyn-MRI, uses DIP to enhance training images, then obtains parametric images using LS or MLE before synthesizing images at desired design parameter settings. DIPsyn-MRI is implemented in our publicly available Python package DeepSynMRI available at: https://github.com/StatPal/DeepSynMRI.We demonstrate feasibility and improved performance of DIPsyn-MRI on 3D datasets acquired using the Brainweb interface for spin-echo and FLASH imaging sequences, at different noise levels. Our DL enhancements improve syn-MRI in the presence of different intensity nonuniformity levels of the magnetic field, for all but very low noise levels.RESULTSWe demonstrate feasibility and improved performance of DIPsyn-MRI on 3D datasets acquired using the Brainweb interface for spin-echo and FLASH imaging sequences, at different noise levels. Our DL enhancements improve syn-MRI in the presence of different intensity nonuniformity levels of the magnetic field, for all but very low noise levels.This article provides recipes and software to realistically facilitate DL-enhanced personalized syn-MRI.CONCLUSIONThis article provides recipes and software to realistically facilitate DL-enhanced personalized syn-MRI. Personalized synthetic MRI (syn-MRI) uses MR images of an individual subject acquired at a few design parameters (echo time, repetition time, flip angle) to obtain underlying parametric maps, from where MR images of that individual at other design parameter settings are synthesized. However, classical methods that use least-squares (LS) or maximum likelihood estimators (MLE) are unsatisfactory at higher noise levels because the underlying inverse problem is ill-posed. This article provides a pipeline to enhance the synthesis of such images in three-dimensional (3D) using a deep learning (DL) neural network architecture for spatial regularization in a personalized setting where having more than a few training images is impractical. Our DL enhancements employ a Deep Image Prior (DIP) with a U-net type denoising architecture that includes situations with minimal training data, such as personalized syn-MRI. We provide a general workflow for syn-MRI from three or more training images. Our workflow, called DIPsyn-MRI, uses DIP to enhance training images, then obtains parametric images using LS or MLE before synthesizing images at desired design parameter settings. DIPsyn-MRI is implemented in our publicly available Python package DeepSynMRI available at: https://github.com/StatPal/DeepSynMRI. We demonstrate feasibility and improved performance of DIPsyn-MRI on 3D datasets acquired using the Brainweb interface for spin-echo and FLASH imaging sequences, at different noise levels. Our DL enhancements improve syn-MRI in the presence of different intensity nonuniformity levels of the magnetic field, for all but very low noise levels. This article provides recipes and software to realistically facilitate DL-enhanced personalized syn-MRI. Purpose Personalized synthetic MRI (syn‐MRI) uses MR images of an individual subject acquired at a few design parameters (echo time, repetition time, flip angle) to obtain underlying parametric (ρ,T1,T2)$$ \left(\rho, {\mathrm{T}}_1,{\mathrm{T}}_2\right) $$ maps, from where MR images of that individual at other design parameter settings are synthesized. However, classical methods that use least‐squares (LS) or maximum likelihood estimators (MLE) are unsatisfactory at higher noise levels because the underlying inverse problem is ill‐posed. This article provides a pipeline to enhance the synthesis of such images in three‐dimensional (3D) using a deep learning (DL) neural network architecture for spatial regularization in a personalized setting where having more than a few training images is impractical. Methods Our DL enhancements employ a Deep Image Prior (DIP) with a U‐net type denoising architecture that includes situations with minimal training data, such as personalized syn‐MRI. We provide a general workflow for syn‐MRI from three or more training images. Our workflow, called DIPsyn‐MRI, uses DIP to enhance training images, then obtains parametric images using LS or MLE before synthesizing images at desired design parameter settings. DIPsyn‐MRI is implemented in our publicly available Python package DeepSynMRI available at: https://github.com/StatPal/DeepSynMRI. Results We demonstrate feasibility and improved performance of DIPsyn‐MRI on 3D datasets acquired using the Brainweb interface for spin‐echo and FLASH imaging sequences, at different noise levels. Our DL enhancements improve syn‐MRI in the presence of different intensity nonuniformity levels of the magnetic field, for all but very low noise levels. Conclusion This article provides recipes and software to realistically facilitate DL‐enhanced personalized syn‐MRI. |
| Author | Maitra, Ranjan Dutta, Somak Pal, Subrata |
| AuthorAffiliation | 1 Department of Statistics Iowa State University Ames Iowa USA |
| AuthorAffiliation_xml | – name: 1 Department of Statistics Iowa State University Ames Iowa USA |
| Author_xml | – sequence: 1 givenname: Subrata orcidid: 0000-0002-3325-431X surname: Pal fullname: Pal, Subrata organization: Iowa State University – sequence: 2 givenname: Somak orcidid: 0000-0002-5613-8987 surname: Dutta fullname: Dutta, Somak organization: Iowa State University – sequence: 3 givenname: Ranjan orcidid: 0000-0002-3515-8532 surname: Maitra fullname: Maitra, Ranjan email: maitra@iastate.edu organization: Iowa State University |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/36420834$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kd1rFDEUxYNU7Lb64D8gA77ow7Q3nzN5klL8gi5K0eeQydzdTZlJ1mTWsv71ZtxatKBPgeR3T84954QchRiQkOcUzigAOx_TeMa0ZM0jsqCSsZpJLY7IAhoBNadaHJOTnG8AQOtGPCHHXAkGLRcLcvEZU47BDv4H9lXeh2mDk3fV8rryo137sK5u_bSpesRtNaBNYb7CsLHB4Yhhyk_J45UdMj67O0_J13dvv1x-qK8-vf94eXFVOyFEU3MLILRQ1qqGa6a6vgMlkIOzdGU7RVdUOtlL1woJzHVMsxYVhdYWmgvNT8mbg-52143Yu_J3soPZpuIz7U203vz9EvzGrON3Q6GEBGxWeHWnkOK3HebJjD47HAYbMO6yYcVYIyhIVdCXD9CbuEslpplqQLaiUbxQL_60dO_ld7wFeH0AXIo5J1zdIxTMXJ0p1Zlf1RX2_AHr_GQnH-dt_PC_iVs_4P7f0mZ5vTxM_AQHF6ks |
| CitedBy_id | crossref_primary_10_3390_bioengineering10091078 crossref_primary_10_1080_10618600_2023_2284208 crossref_primary_10_1016_j_apradiso_2025_112049 crossref_primary_10_1088_1361_6560_ad94c7 crossref_primary_10_1002_mp_16884 |
| Cites_doi | 10.1117/12.2293860 10.1103/PhysRev.69.37 10.1109/TMI.2019.2901750 10.1214/ss/1177013525 10.1016/j.neuroimage.2011.08.056 10.1109/TIP.2003.819861 10.1016/j.zemedi.2018.11.002 10.1117/12.2511653 10.1002/mrm.27786 10.1007/s13571‐012‐0055‐y 10.1002/(SICI)1522-2594(199912)42:6<1014::AID-MRM4>3.0.CO;2-F 10.1109/PROC.1983.12592 10.1002/j.1538-7305.1945.tb00453.x 10.1103/PhysRev.69.127 10.1016/j.neunet.2019.08.025 10.1148/radiology.155.3.4001377 10.1093/biomet/82.2.237 10.1103/PhysRev.70.474 10.1002/mrm.21635 10.1006/cbmr.1996.0014 10.1103/PhysRev.70.460 10.1109/CVPR.2018.00984 10.1109/TMI.2009.2039487 10.1007/978-3-030-00889-5_1 10.1088/1361-6560/ac46dd 10.1002/(SICI)1099-1492(199706/08)10:4/5<171::AID-NBM453>3.0.CO;2-L 10.1007/978-3-319-24574-4_28 10.1002/mrm.20314 10.1002/mrm.1910030602 10.3174/ajnr.A5927 10.1148/radiology.155.2.3983396 10.1002/jmri.27440 10.1109/TMI.2021.3084288 10.1002/mrm.1910010304 10.1016/S0730-725X(97)00199-9 10.1109/TMI.2018.2888491 10.1109/TMI.2009.2024415 10.1118/1.595711 10.1002/j.1538-7305.1944.tb00874.x |
| ContentType | Journal Article |
| Copyright | 2022 The Authors. published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine. 2022 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine. 2022. This article is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: 2022 The Authors. published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine. – notice: 2022 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine. – notice: 2022. This article is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | 24P AAYXX CITATION CGR CUY CVF ECM EIF NPM 8FD FR3 K9. M7Z P64 7X8 5PM |
| DOI | 10.1002/mrm.29527 |
| DatabaseName | Wiley Online Library Open Access CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Technology Research Database Engineering Research Database ProQuest Health & Medical Complete (Alumni) Biochemistry Abstracts 1 Biotechnology and BioEngineering Abstracts MEDLINE - Academic PubMed Central (Full Participant titles) |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Biochemistry Abstracts 1 ProQuest Health & Medical Complete (Alumni) Engineering Research Database Technology Research Database Biotechnology and BioEngineering Abstracts MEDLINE - Academic |
| DatabaseTitleList | CrossRef Biochemistry Abstracts 1 MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: 24P name: Wiley Online Library Open Access url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html sourceTypes: Publisher – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine Physics |
| DocumentTitleAlternate | PAL et al |
| EISSN | 1522-2594 |
| EndPage | 1643 |
| ExternalDocumentID | PMC10100029 36420834 10_1002_mrm_29527 MRM29527 |
| Genre | technicalNote Journal Article Research Support, N.I.H., Extramural |
| GrantInformation_xml | – fundername: National Institute of Biomedical Imaging and Bioengineering funderid: R21EB034184 – fundername: NIBIB NIH HHS grantid: R21EB034184 – fundername: NIBIB NIH HHS grantid: R21 EB016212 – fundername: NIBIB NIH HHS grantid: R21 EB034184 – fundername: ; grantid: R21EB034184 |
| GroupedDBID | --- -DZ .3N .55 .GA .Y3 05W 0R~ 10A 1L6 1OB 1OC 1ZS 24P 31~ 33P 3O- 3SF 3WU 4.4 4ZD 50Y 50Z 51W 51X 52M 52N 52O 52P 52R 52S 52T 52U 52V 52W 52X 53G 5GY 5RE 5VS 66C 702 7PT 8-0 8-1 8-3 8-4 8-5 8UM 930 A01 A03 AAESR AAEVG AAHHS AAHQN AAIPD AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCQN ABCUV ABDPE ABEML ABIJN ABJNI ABLJU ABPVW ABQWH ABXGK ACAHQ ACBWZ ACCFJ ACCZN ACFBH ACGFO ACGFS ACGOF ACIWK ACMXC ACPOU ACPRK ACRPL ACSCC ACXBN ACXQS ACYXJ ADBBV ADBTR ADEOM ADIZJ ADKYN ADMGS ADNMO ADOZA ADXAS ADZMN AEEZP AEGXH AEIGN AEIMD AENEX AEQDE AEUQT AEUYR AFBPY AFFNX AFFPM AFGKR AFPWT AFRAH AFWVQ AFZJQ AHBTC AHMBA AIACR AIAGR AITYG AIURR AIWBW AJBDE ALAGY ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMBMR AMYDB ASPBG ATUGU AVWKF AZBYB AZFZN AZVAB BAFTC BDRZF BFHJK BHBCM BMXJE BROTX BRXPI BY8 C45 CS3 D-6 D-7 D-E D-F DCZOG DPXWK DR2 DRFUL DRMAN DRSTM DU5 EBD EBS EJD EMOBN F00 F01 F04 FEDTE FUBAC G-S G.N GNP GODZA H.X HBH HDBZQ HF~ HGLYW HHY HHZ HVGLF HZ~ I-F IX1 J0M JPC KBYEO KQQ LATKE LAW LC2 LC3 LEEKS LH4 LITHE LOXES LP6 LP7 LUTES LW6 LYRES M65 MEWTI MK4 MRFUL MRMAN MRSTM MSFUL MSMAN MSSTM MXFUL MXMAN MXSTM N04 N05 N9A NF~ NNB O66 O9- OIG OVD P2P P2W P2X P2Z P4B P4D PALCI PQQKQ Q.N Q11 QB0 QRW R.K RGB RIWAO RJQFR ROL RWI RX1 RYL SAMSI SUPJJ SV3 TEORI TUS TWZ UB1 V2E V8K W8V W99 WBKPD WHWMO WIB WIH WIJ WIK WIN WJL WOHZO WQJ WRC WUP WVDHM WXI WXSBR X7M XG1 XPP XV2 ZGI ZXP ZZTAW ~IA ~WT AAMMB AAYXX AEFGJ AEYWJ AGHNM AGQPQ AGXDD AGYGG AIDQK AIDYY AIQQE CITATION O8X CGR CUY CVF ECM EIF NPM 8FD FR3 K9. M7Z P64 7X8 5PM |
| ID | FETCH-LOGICAL-c4447-3a004946aa673926bdb064e30ca1fab61f15c5d5c84502cb2928e6108a3923493 |
| IEDL.DBID | 24P |
| ISICitedReferencesCount | 5 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000889235700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0740-3194 1522-2594 |
| IngestDate | Tue Nov 04 02:06:45 EST 2025 Sun Nov 09 09:25:02 EST 2025 Tue Oct 07 06:47:26 EDT 2025 Mon Jul 21 06:02:30 EDT 2025 Sat Nov 29 06:34:36 EST 2025 Tue Nov 18 22:49:39 EST 2025 Wed Jan 22 16:20:17 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | denoising deep-learning Bloch transform synthetic MRI deep-image-prior |
| Language | English |
| License | Attribution-NonCommercial-NoDerivs 2022 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine. This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc-nd/4.0/ License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c4447-3a004946aa673926bdb064e30ca1fab61f15c5d5c84502cb2928e6108a3923493 |
| Notes | Funding information National Institute of Biomedical Imaging and Bioengineering, Grant/Award Number: R21EB034184 ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 Funding information National Institute of Biomedical Imaging and Bioengineering, Grant/Award Number: R21EB034184 |
| ORCID | 0000-0002-3325-431X 0000-0002-5613-8987 0000-0002-3515-8532 |
| OpenAccessLink | https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmrm.29527 |
| PMID | 36420834 |
| PQID | 2770584763 |
| PQPubID | 1016391 |
| PageCount | 10 |
| ParticipantIDs | pubmedcentral_primary_oai_pubmedcentral_nih_gov_10100029 proquest_miscellaneous_2739741056 proquest_journals_2770584763 pubmed_primary_36420834 crossref_primary_10_1002_mrm_29527 crossref_citationtrail_10_1002_mrm_29527 wiley_primary_10_1002_mrm_29527_MRM29527 |
| PublicationCentury | 2000 |
| PublicationDate | April 2023 |
| PublicationDateYYYYMMDD | 2023-04-01 |
| PublicationDate_xml | – month: 04 year: 2023 text: April 2023 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: Hoboken |
| PublicationTitle | Magnetic resonance in medicine |
| PublicationTitleAlternate | Magn Reson Med |
| PublicationYear | 2023 |
| Publisher | Wiley Subscription Services, Inc John Wiley and Sons Inc |
| Publisher_xml | – name: Wiley Subscription Services, Inc – name: John Wiley and Sons Inc |
| References | 1982; 16 2020; 121 1998 2022; 67 2019; 38 1983; 71 2019; 10949 1999; 42 2018; 10574 2018; 10573 1946; 69 1999 2009; 28 1998; 16 1986; 1 1995; 82 2019; 82 1996; 29 1946; 70 2019; 40 1997; 10 2010; 29 1984; 1 2020 1986; 3 1945; 24 2013; 75 2004; 13 2005; 53 2018 2019; 29 1982 2015 2014 2022; 55 1985; 12 2008; 60 2021; 40 2018; 38 1944; 23 1985; 155 2012; 62 e_1_2_10_23_1 e_1_2_10_46_1 e_1_2_10_24_1 e_1_2_10_45_1 e_1_2_10_21_1 e_1_2_10_44_1 e_1_2_10_22_1 e_1_2_10_43_1 e_1_2_10_42_1 e_1_2_10_20_1 e_1_2_10_41_1 Mansfield P (e_1_2_10_3_1) 1982 Maitra R (e_1_2_10_11_1) 1998 e_1_2_10_4_1 e_1_2_10_18_1 e_1_2_10_19_1 e_1_2_10_6_1 e_1_2_10_39_1 e_1_2_10_5_1 e_1_2_10_17_1 e_1_2_10_38_1 e_1_2_10_8_1 e_1_2_10_14_1 e_1_2_10_37_1 e_1_2_10_7_1 e_1_2_10_15_1 e_1_2_10_36_1 e_1_2_10_12_1 Katims LM (e_1_2_10_2_1) 1982; 16 e_1_2_10_9_1 e_1_2_10_13_1 e_1_2_10_34_1 e_1_2_10_10_1 e_1_2_10_33_1 e_1_2_10_32_1 e_1_2_10_31_1 e_1_2_10_30_1 Haacke EM (e_1_2_10_40_1) 1999 e_1_2_10_29_1 Bermudez C (e_1_2_10_16_1) 2018 R Core Team (e_1_2_10_35_1) 2020 e_1_2_10_27_1 e_1_2_10_28_1 e_1_2_10_49_1 e_1_2_10_25_1 e_1_2_10_48_1 e_1_2_10_26_1 e_1_2_10_47_1 |
| References_xml | – start-page: 9446 year: 2018 end-page: 9454 – start-page: 39 year: 1998 end-page: 47 – volume: 55 start-page: 1013 year: 2022 end-page: 1025 article-title: Synthetic MRI: technologies and applications in neuroradiology publication-title: J Magnet Reson Imaging – volume: 38 start-page: 1655 year: 2018 end-page: 1665 article-title: PET image reconstruction using deep image prior publication-title: IEEE Trans Med Imaging – volume: 53 start-page: 237 year: 2005 end-page: 241 article-title: High‐resolution and mapping of the brain in a clinically acceptable time with DESPOT1 and DESPOT2 publication-title: Magnet Reson Med – volume: 82 start-page: 237 year: 1995 end-page: 250 article-title: A Bayesian approach to synthetic magnetic resonance imaging publication-title: Biometrika – volume: 38 start-page: 2375 year: 2019 end-page: 2388 article-title: Image synthesis in multi‐contrast MRI with conditional generative adversarial networks publication-title: IEEE Trans Med Imaging – volume: 24 start-page: 46 year: 1945 end-page: 156 article-title: Mathematical analysis of random noise publication-title: Bell Syst Techn J – volume: 13 start-page: 600 year: 2004 end-page: 612 article-title: Image quality assessment: from error visibility to structural similarity publication-title: IEEE Trans Image Process – volume: 67 year: 2022 article-title: Generation of quantification maps and weighted images from synthetic magnetic resonance imaging using deep learning network publication-title: Phys Med Biol – volume: 82 start-page: 1177 year: 2019 end-page: 1186 article-title: Separation of water and fat signal in whole‐body gradient echo scans using convolutional neural networks publication-title: Magnet Reson Med – volume: 12 start-page: 232 year: 1985 end-page: 233 article-title: Measurement of signal intensities in the presence of noise in MR images publication-title: Med Phys – volume: 10573 start-page: 840 year: 2018 end-page: 849 – volume: 70 start-page: 474 year: 1946 end-page: 485 article-title: The nuclear induction experiment publication-title: Phys Rev. – volume: 71 start-page: 3 year: 1983 article-title: An introduction to NMR imaging: from the Bloch equation to the imaging equation publication-title: Proc IEEE – volume: 155 start-page: 437 year: 1985 end-page: 442 article-title: Multiple spin‐echo magnetic resonance imaging publication-title: Radiology – start-page: 3 year: 2018 end-page: 11 – year: 2014 – volume: 29 start-page: 895 year: 2010 end-page: 902 article-title: Synthetic magnetic resonance imaging revisited publication-title: IEEE Trans Med Imaging – volume: 42 start-page: 1014 year: 1999 end-page: 1018 article-title: Real‐time 3D image registration for functional MRI publication-title: Magnet Reson Med – volume: 40 start-page: 224 year: 2019 end-page: 230 article-title: Improving the quality of synthetic FLAIR images with deep learning using a conditional generative adversarial network for pixel‐by‐pixel image translation publication-title: Am J Neuroradiol – year: 1982 – volume: 10949 start-page: 21 year: 2019 end-page: 27 – volume: 155 start-page: 731 year: 1985 end-page: 738 article-title: Synthesized MR images: comparison with acquired images publication-title: Radiology – volume: 29 start-page: 162 year: 1996 end-page: 173 article-title: AFNI: software for analysis and visualization of functional magnetic resonance neuroimages publication-title: Comput Biomed Res Int J – volume: 75 start-page: 293 year: 2013 end-page: 318 article-title: On the expectation‐maximization algorithm for Rice‐Rayleigh mixtures with application to estimating the noise parameter in magnitude MR datasets publication-title: Sankhyā Ind J Stat Ser B – volume: 1 start-page: 316 year: 1984 end-page: 338 article-title: Signal to noise in derived NMR images publication-title: Magnet Reson Med – volume: 1 start-page: 502 year: 1986 end-page: 527 article-title: A statistical perspective on Ill‐posed inverse problems publication-title: Stat Sci – volume: 16 start-page: 213 year: 1982 end-page: 216 article-title: Nuclear magnetic resonance imaging: methods and current status publication-title: Med Instrum – volume: 60 start-page: 320 year: 2008 end-page: 329 article-title: Rapid magnetic resonance quantification on the brain: optimization for clinical usage publication-title: Magnet Reson Med – year: 2020 – volume: 70 start-page: 460 year: 1946 end-page: 474 article-title: Nuclear induction publication-title: Phys Rev – volume: 10574 start-page: 408 year: 2018 end-page: 414 – volume: 29 start-page: 102 year: 2019 end-page: 127 article-title: An overview of deep learning in medical imaging focusing on MRI publication-title: Zeitschrift für Medizinische Physik – volume: 16 start-page: 87 year: 1998 end-page: 90 article-title: Estimation of the noise in magnitude MR images publication-title: Magnet Reson Imaging – volume: 23 start-page: 282 year: 1944 end-page: 332 article-title: Mathematical analysis of random noise publication-title: Bell Syst Techn J – volume: 10 start-page: 171 year: 1997 end-page: 178 article-title: Software tools for analysis and visualization of fMRI data publication-title: NMR Biomed – volume: 69 start-page: 37 year: 1946 end-page: 38 article-title: Resonance absorption by nuclear magnetic moments in a solid publication-title: Phys. Rev. – volume: 69 start-page: 127 year: 1946 article-title: Nuclear induction publication-title: Phys Rev – volume: 40 start-page: 3337 year: 2021 end-page: 3348 article-title: Time‐dependent deep image prior for dynamic MRI publication-title: IEEE Trans Med Imaging – volume: 3 start-page: 823 year: 1986 end-page: 833 article-title: RARE imaging – A fast imaging method for clinical MR publication-title: Magnet Reson Med – volume: 62 start-page: 743 year: 2012 end-page: 747 article-title: AFNI: what a long strange trip it has been publication-title: NeuroImage – year: 2015 – volume: 121 start-page: 74 year: 2020 end-page: 87 article-title: MultiResUNet: rethinking the U‐Net architecture for multimodal biomedical image segmentation publication-title: Neural Netw – volume: 28 start-page: 1615 year: 2009 end-page: 1622 article-title: Noise estimation in magnitude MR datasets publication-title: IEEE Trans Med Imaging – year: 1999 – ident: e_1_2_10_14_1 doi: 10.1117/12.2293860 – ident: e_1_2_10_36_1 doi: 10.1103/PhysRev.69.37 – ident: e_1_2_10_24_1 doi: 10.1109/TMI.2019.2901750 – ident: e_1_2_10_30_1 – ident: e_1_2_10_48_1 doi: 10.1214/ss/1177013525 – ident: e_1_2_10_32_1 doi: 10.1016/j.neuroimage.2011.08.056 – ident: e_1_2_10_49_1 doi: 10.1109/TIP.2003.819861 – volume: 16 start-page: 213 year: 1982 ident: e_1_2_10_2_1 article-title: Nuclear magnetic resonance imaging: methods and current status publication-title: Med Instrum – volume-title: NMR Imaging in Biomedicine year: 1982 ident: e_1_2_10_3_1 – ident: e_1_2_10_17_1 doi: 10.1016/j.zemedi.2018.11.002 – ident: e_1_2_10_26_1 doi: 10.1117/12.2511653 – ident: e_1_2_10_29_1 doi: 10.1002/mrm.27786 – ident: e_1_2_10_47_1 doi: 10.1007/s13571‐012‐0055‐y – ident: e_1_2_10_33_1 doi: 10.1002/(SICI)1522-2594(199912)42:6<1014::AID-MRM4>3.0.CO;2-F – ident: e_1_2_10_4_1 doi: 10.1109/PROC.1983.12592 – ident: e_1_2_10_45_1 doi: 10.1002/j.1538-7305.1945.tb00453.x – ident: e_1_2_10_38_1 doi: 10.1103/PhysRev.69.127 – ident: e_1_2_10_21_1 – ident: e_1_2_10_22_1 doi: 10.1016/j.neunet.2019.08.025 – ident: e_1_2_10_8_1 doi: 10.1148/radiology.155.3.4001377 – ident: e_1_2_10_10_1 doi: 10.1093/biomet/82.2.237 – ident: e_1_2_10_39_1 doi: 10.1103/PhysRev.70.474 – ident: e_1_2_10_6_1 doi: 10.1002/mrm.21635 – ident: e_1_2_10_31_1 doi: 10.1006/cbmr.1996.0014 – ident: e_1_2_10_37_1 doi: 10.1103/PhysRev.70.460 – ident: e_1_2_10_28_1 doi: 10.1109/CVPR.2018.00984 – start-page: 39 volume-title: Bayesian Inference in Inverse Problems. Volume 3459 of Proceedings of the Society of Photo‐Optical Instrumentation Engineers (SPIE) Meetings year: 1998 ident: e_1_2_10_11_1 – volume-title: R: A Language and Environment for Statistical Computing year: 2020 ident: e_1_2_10_35_1 – ident: e_1_2_10_12_1 doi: 10.1109/TMI.2009.2039487 – volume-title: Magnetic Resonance Imaging: Physical Principles and Sequence Design year: 1999 ident: e_1_2_10_40_1 – start-page: 408 volume-title: Medical Imaging 2018: Image Processing year: 2018 ident: e_1_2_10_16_1 – ident: e_1_2_10_19_1 doi: 10.1007/978-3-030-00889-5_1 – ident: e_1_2_10_23_1 doi: 10.1088/1361-6560/ac46dd – ident: e_1_2_10_34_1 doi: 10.1002/(SICI)1099-1492(199706/08)10:4/5<171::AID-NBM453>3.0.CO;2-L – ident: e_1_2_10_18_1 doi: 10.1007/978-3-319-24574-4_28 – ident: e_1_2_10_5_1 doi: 10.1002/mrm.20314 – ident: e_1_2_10_15_1 doi: 10.1002/mrm.1910030602 – ident: e_1_2_10_20_1 doi: 10.3174/ajnr.A5927 – ident: e_1_2_10_42_1 – ident: e_1_2_10_9_1 doi: 10.1148/radiology.155.2.3983396 – ident: e_1_2_10_13_1 doi: 10.1002/jmri.27440 – ident: e_1_2_10_25_1 doi: 10.1109/TMI.2021.3084288 – ident: e_1_2_10_7_1 doi: 10.1002/mrm.1910010304 – ident: e_1_2_10_43_1 doi: 10.1016/S0730-725X(97)00199-9 – ident: e_1_2_10_27_1 doi: 10.1109/TMI.2018.2888491 – ident: e_1_2_10_46_1 doi: 10.1109/TMI.2009.2024415 – ident: e_1_2_10_41_1 doi: 10.1118/1.595711 – ident: e_1_2_10_44_1 doi: 10.1002/j.1538-7305.1944.tb00874.x |
| SSID | ssj0009974 |
| Score | 2.452884 |
| Snippet | Purpose
Personalized synthetic MRI (syn‐MRI) uses MR images of an individual subject acquired at a few design parameters (echo time, repetition time, flip... Click here for author‐reader discussions Personalized synthetic MRI (syn-MRI) uses MR images of an individual subject acquired at a few design parameters (echo time, repetition time, flip angle) to... PurposePersonalized synthetic MRI (syn‐MRI) uses MR images of an individual subject acquired at a few design parameters (echo time, repetition time, flip... |
| SourceID | pubmedcentral proquest pubmed crossref wiley |
| SourceType | Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 1634 |
| SubjectTerms | Bloch transform Computer architecture Customization Deep Learning deep‐image‐prior denoising Design parameters Image acquisition Image enhancement Image Processing, Computer-Assisted - methods Inverse problems Low noise Magnetic resonance imaging Magnetic Resonance Imaging - methods Maximum likelihood estimators Neural networks Neural Networks, Computer Noise levels Noise reduction Nonuniformity Regularization Signal-To-Noise Ratio Software Synthesis synthetic MRI Technical Note Technical Note—Computer Processing and Modeling Training Workflow |
| Title | Personalized synthetic MR imaging with deep learning enhancements |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmrm.29527 https://www.ncbi.nlm.nih.gov/pubmed/36420834 https://www.proquest.com/docview/2770584763 https://www.proquest.com/docview/2739741056 https://pubmed.ncbi.nlm.nih.gov/PMC10100029 |
| Volume | 89 |
| WOSCitedRecordID | wos000889235700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVWIB databaseName: Wiley Online Library customDbUrl: eissn: 1522-2594 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0009974 issn: 0740-3194 databaseCode: WIN dateStart: 19990101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell – providerCode: PRVWIB databaseName: Wiley Online Library - Journals customDbUrl: eissn: 1522-2594 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0009974 issn: 0740-3194 databaseCode: DRFUL dateStart: 19990101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB6VFhAXHuUVKJVBHLiEbvyKLU4VsAKpu1qtKOwtsh2HrsSm1aZFgl-Px3mUVUFC4hIl8lhx7JnxF3v8DcBLz8PfDdU8Vaw0KdeZSa12NKWmpNxXTOSRS-_zUT6dqsVCz7bgTX8WpuWHGBbc0DKiv0YDN7Y5uCQNXa1Xr6kWNL8GO1nGFOZtoHx2ybirWwrmnKOj0bynFRrRg6Hq5mR0BWFeDZT8HcDGGWh857_afhdud8CTHLaacg-2fL0LNyfd1vou3IixoK65D4ezHqD_9CVpftQBI4ZKZDIny1VMakRw9ZaU3p-RLuvEV-LrE1SgeGLuARyP3396-yHtMi2kjnMevIyJPDHSGJkHwCRtaQNU8WzkTFYZK7MqE06UwikuRtRZqqnyAXgpE6QZ1-whbNentX8MxFTBv2ayMkJ6bp1WliPdqEBa_lILm8CrvssL19GQYzaMb0VLoEyL0DlF7JwEXgyiZy33xp-E9vpxKzrzawqa5yPc_5UsgedDcTAc3A0xtT-9QJkAxTDIVSbwqB3m4S1MYtQB4wmoDQUYBJCUe7OkXp5Ecu7g4nCW0eE7owb8veXFZD6JN0_-XfQp3MJ8923o0B5sn68v_DO47r6fL5v1fjSAcM0Xah923s3Hx0fh6cvH6S_aAQrB |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NT9wwEB1RoC0XWmgpAUpN1UMvgY1jO7HEBSEQiM0KIaDcIsdxYCU2oF1Agl-Px_mAFSBV4hbJY8WxZ8Yv4_EbgD-G2b8bKpkfh7nymQyUn0lNfapyykwR8shx6Z12o14vPjuThxOw2dyFqfgh2oAbWobz12jgGJDeeGINHQwH61RyGn2AKWaBBhZu-Lffe6LclRUHc8TQ00jW8Ap16EbbdXw3egExX2ZKPkewbgva_fK-wX-F2Rp6kq1KV-ZgwpTz8CmpD9fn4aPLBtWjb7B12ED0B5OT0X1pUaLtRJIj0h-4skYE47ckN-aa1HUnzokpL1CF3J2573Cyu3O8vefXtRZ8zRizfkY5phihlIgsZBJZnlmwYsKOVkGhMhEUAdc85zpmvEN1RiWNjYVesbLSIZPhAkyWV6VZBKIK62EDUSguDMu0jDOGhKMciflzyTMP_jZznuqaiBzrYVymFYUyTe3kpG5yPPjdil5X7BuvCa00C5fWBjhKaRR18ARYhB6stc3WdPA8RJXm6hZlLBjDNFfhwY9qndu3hALzDkLmQTymAa0A0nKPt5T9C0fPbZ0c7jPSfqdTgbdHniZHiXtY-n_RX_B57zjppt393sEyzFCLuapEohWYvBnemp8wre9u-qPhqrOGR30cC4I |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3fT9swED51hVV7AcYGC2PMIB54yWgc24mlvaCxaoimqipAvEWO40AlmlYNTBp_Pbbzo6sAadLeIvmsOOe78xf7_B3AoSL67wZz4oZ-KlzCPeEmXGIXixQTlfk0sFx6V_1gMAivr_mwBd_ruzAlP0Sz4WY8w8Zr4-BqlmbHC9bQyXzyDXOKgzewQkwRmTasnI56l_0F6S4vWZgDYmINJzWzUBcfN52X16NnIPN5ruTfGNYuQr31_xv-BqxV4BOdlNbyHloq34ROVB2vb8Jbmw8qiw9wMqxB-qNKUfEn1zhRd0LRCI0ntrARMju4KFVqhqrKEzdI5bfGiOytuY9w2ft58eOXW1VbcCUhREcaYblimBAs0KCJJWmi4Yryu1J4mUiYl3lU0pTKkNAulgnmOFQafIVCS_uE-1vQzqe5-gRIZDrGeiwTlCmSSB4mxFCOUkPNn3KaOHBU6zyWFRW5qYhxF5ckyjjWyomtchw4aERnJf_GS0K79cTFlQsWMQ6CrjkDZr4D-02zdh5zIiJyNX0wMhqOmURX5sB2Oc_NW3xmMg984kC4ZAGNgCHmXm7Jx7eWoFuHObPScP2d1gReH3kcjSL7sPPvol-hMzztxf2zwflneIc16CoziXahfT9_UF9gVf6-HxfzvcodngA1Kgwr |
| 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=Personalized+synthetic+MR+imaging+with+deep+learning+enhancements&rft.jtitle=Magnetic+resonance+in+medicine&rft.au=Pal%2C+Subrata&rft.au=Dutta%2C+Somak&rft.au=Maitra%2C+Ranjan&rft.date=2023-04-01&rft.pub=Wiley+Subscription+Services%2C+Inc&rft.issn=0740-3194&rft.eissn=1522-2594&rft.volume=89&rft.issue=4&rft.spage=1634&rft.epage=1643&rft_id=info:doi/10.1002%2Fmrm.29527&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0740-3194&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0740-3194&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0740-3194&client=summon |