Unsupervised single-image super-resolution for infant brain MRI
Acquiring high-resolution (HR) MR images of infant brains is challenging due to lengthy scan times and limited subject compliance. Image super-resolution (SR) techniques can generate HR images from low-resolution (LR) inputs, reducing the need for extended acquisitions. However, most existing SR met...
Saved in:
| Published in | NeuroImage (Orlando, Fla.) Vol. 317; p. 121293 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
Elsevier Inc
15.08.2025
Elsevier Limited Elsevier |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1053-8119 1095-9572 1095-9572 |
| DOI | 10.1016/j.neuroimage.2025.121293 |
Cover
| Abstract | Acquiring high-resolution (HR) MR images of infant brains is challenging due to lengthy scan times and limited subject compliance. Image super-resolution (SR) techniques can generate HR images from low-resolution (LR) inputs, reducing the need for extended acquisitions. However, most existing SR methods require HR images for training, limiting their practical use in real-world scenarios. To overcome this limitation, we propose an unsupervised single-image SR approach that requires only a single LR image for training. By integrating image space regularity with k-space consistency, our method enhances training stability and mitigates overfitting. Additionally, we introduce joint self-supervised learning to improve the fidelity of low-frequency content in the generated images. Our approach demonstrates both quantitative and qualitative improvements in MRI resolution for infants aged 1 week to 1 year, offering robust performance without manual hyperparameter tuning across diverse inputs. This innovation enables fully automated, high-throughput MRI resolution enhancement, addressing a critical need in pediatric neuroimaging.
[Display omitted]
•KC-DIP can be trained unsupervised on a single image for super-resolution.•KC-DIP employs various strategies to ensure good properties in the frequency space.•Training is stable with minimal hyperparameter adjustments across diverse images.•KC-DIP performs well on brain MR images of infants from 1 week to 1 year of age. |
|---|---|
| AbstractList | Acquiring high-resolution (HR) MR images of infant brains is challenging due to lengthy scan times and limited subject compliance. Image super-resolution (SR) techniques can generate HR images from low-resolution (LR) inputs, reducing the need for extended acquisitions. However, most existing SR methods require HR images for training, limiting their practical use in real-world scenarios. To overcome this limitation, we propose an unsupervised single-image SR approach that requires only a single LR image for training. By integrating image space regularity with k-space consistency, our method enhances training stability and mitigates overfitting. Additionally, we introduce joint self-supervised learning to improve the fidelity of low-frequency content in the generated images. Our approach demonstrates both quantitative and qualitative improvements in MRI resolution for infants aged 1 week to 1 year, offering robust performance without manual hyperparameter tuning across diverse inputs. This innovation enables fully automated, high-throughput MRI resolution enhancement, addressing a critical need in pediatric neuroimaging. Acquiring high-resolution (HR) MR images of infant brains is challenging due to lengthy scan times and limited subject compliance. Image super-resolution (SR) techniques can generate HR images from low-resolution (LR) inputs, reducing the need for extended acquisitions. However, most existing SR methods require HR images for training, limiting their practical use in real-world scenarios. To overcome this limitation, we propose an unsupervised single-image SR approach that requires only a single LR image for training. By integrating image space regularity with k-space consistency, our method enhances training stability and mitigates overfitting. Additionally, we introduce joint self-supervised learning to improve the fidelity of low-frequency content in the generated images. Our approach demonstrates both quantitative and qualitative improvements in MRI resolution for infants aged 1 week to 1 year, offering robust performance without manual hyperparameter tuning across diverse inputs. This innovation enables fully automated, high-throughput MRI resolution enhancement, addressing a critical need in pediatric neuroimaging. [Display omitted] •KC-DIP can be trained unsupervised on a single image for super-resolution.•KC-DIP employs various strategies to ensure good properties in the frequency space.•Training is stable with minimal hyperparameter adjustments across diverse images.•KC-DIP performs well on brain MR images of infants from 1 week to 1 year of age. Acquiring high-resolution (HR) MRI of infant brains is challenging due to lengthy scan times and limited subject compliance. Image super-resolution (SR) techniques can generate HR images from low-resolution (LR) inputs, reducing the need for extended acquisitions. However, most existing SR methods require HR images for training, limiting their practical use in real-world scenarios. To overcome this limitation, we propose an unsupervised single-image SR approach that requires only a single LR image for training. By integrating image space regularity with k-space consistency, our method enhances training stability and mitigates overfitting. Additionally, we introduce joint self-supervised learning to improve the fidelity of low-frequency content in the generated images. Our approach demonstrates both quantitative and qualitative improvements in MRI resolution for infants aged 1 week to 1 year, offering robust performance without manual hyperparameter tuning across diverse inputs. This innovation enables fully automated, high-throughput MRI resolution enhancement, addressing a critical need in pediatric neuroimaging.Acquiring high-resolution (HR) MRI of infant brains is challenging due to lengthy scan times and limited subject compliance. Image super-resolution (SR) techniques can generate HR images from low-resolution (LR) inputs, reducing the need for extended acquisitions. However, most existing SR methods require HR images for training, limiting their practical use in real-world scenarios. To overcome this limitation, we propose an unsupervised single-image SR approach that requires only a single LR image for training. By integrating image space regularity with k-space consistency, our method enhances training stability and mitigates overfitting. Additionally, we introduce joint self-supervised learning to improve the fidelity of low-frequency content in the generated images. Our approach demonstrates both quantitative and qualitative improvements in MRI resolution for infants aged 1 week to 1 year, offering robust performance without manual hyperparameter tuning across diverse inputs. This innovation enables fully automated, high-throughput MRI resolution enhancement, addressing a critical need in pediatric neuroimaging. AbstractAcquiring high-resolution (HR) MR images of infant brains is challenging due to lengthy scan times and limited subject compliance. Image super-resolution (SR) techniques can generate HR images from low-resolution (LR) inputs, reducing the need for extended acquisitions. However, most existing SR methods require HR images for training, limiting their practical use in real-world scenarios. To overcome this limitation, we propose an unsupervised single-image SR approach that requires only a single LR image for training. By integrating image space regularity with k-space consistency, our method enhances training stability and mitigates overfitting. Additionally, we introduce joint self-supervised learning to improve the fidelity of low-frequency content in the generated images. Our approach demonstrates both quantitative and qualitative improvements in MRI resolution for infants aged 1 week to 1 year, offering robust performance without manual hyperparameter tuning across diverse inputs. This innovation enables fully automated, high-throughput MRI resolution enhancement, addressing a critical need in pediatric neuroimaging. |
| ArticleNumber | 121293 |
| Author | Yap, Pew-Thian Chen, Xiaoyang Tsai, Cheng Che Ahmad, Sahar |
| AuthorAffiliation | b Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA c Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA a Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA |
| AuthorAffiliation_xml | – name: b Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA – name: a Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA – name: c Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA |
| Author_xml | – sequence: 1 givenname: Cheng Che orcidid: 0009-0002-0979-3855 surname: Tsai fullname: Tsai, Cheng Che organization: Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA – sequence: 2 givenname: Xiaoyang orcidid: 0000-0003-2390-9797 surname: Chen fullname: Chen, Xiaoyang organization: Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA – sequence: 3 givenname: Sahar orcidid: 0000-0001-7243-9977 surname: Ahmad fullname: Ahmad, Sahar organization: Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA – sequence: 4 givenname: Pew-Thian orcidid: 0000-0003-1489-2102 surname: Yap fullname: Yap, Pew-Thian email: ptyap@med.unc.edu organization: Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/40550405$$D View this record in MEDLINE/PubMed |
| BookMark | eNqNkktv1DAUhSNURNuBv4AisWGTwe_EGwpUPEYqQgK6tmznZvCQsQc7Gan_HmdSBloJqVnYjnPul-vjc16c-OChKEqMlhhh8Wqz9DDG4LZ6DUuCCF9igomkj4ozjCSvJK_JybTmtGowlqfFeUobhJDErHlSnDLEOcrDWXFx7dO4g7h3CdoyOb_uoTpwy8N-FSGFfhxc8GUXYul8p_1QmqidLz9_XT0tHne6T_Dsdl4U1x_ef7_8VF19-bi6fHtVWUHpULW8wTWShuQHUCuMra1omBUgWyRbzgUjQDGhBnNsWitrJi0mreGdYUJ3dFGsZm4b9EbtYm4x3qignTpshLhWOg7O9qCkYVh0EpDRNcs_nt4bZjqkwWBBWGZdzKzdaLbQWvBD1P0d6N0v3v1Q67BXmJC6zr5lwstbQgy_RkiD2rpkoe-1hzAmRQmhgvJsf5a-uCfdhDH67FVWUcpEg_K8KJ7_29Kxlz8XlQXNLLAxpBShO0owUlMm1Eb9zYSaMqHmTOTSd3Mp5PvZO4gqWQfeQusi2CEb6B4CeX0PYnvnndX9T7iBdDwTVokopL5N0ZuSRzhCRIrJ9Df_Bzysh9_TKO3G |
| Cites_doi | 10.1155/2021/8865582 10.1109/TPAMI.2020.2982166 10.1109/JBHI.2022.3232511 10.1109/TIP.2013.2293423 10.1109/CVPR.2017.243 10.1016/j.image.2019.115701 10.1109/CVPR.2017.618 10.1109/LSP.2020.3005043 10.1007/s11263-021-01572-7 10.1007/s00247-018-4116-x 10.1038/s41597-023-02400-y 10.1118/1.4935149 10.1016/j.neuroimage.2015.06.018 10.1109/CVPR.2018.00984 10.1016/j.media.2023.102877 10.1016/j.neuroimage.2018.04.044 10.1109/ACCESS.2019.2918926 10.1109/TCYB.2017.2786161 10.1109/TBME.2018.2821699 10.1109/TMI.2015.2437894 10.1016/j.compbiomed.2018.06.010 10.1109/TETCI.2022.3215137 10.1016/j.inffus.2021.09.005 10.1002/mrm.27420 10.1109/TMM.2019.2919431 10.1109/TPAMI.2022.3204527 10.1002/mrm.21132 10.1109/CVPRW.2018.00113 10.1016/j.neuroimage.2019.116324 10.1016/j.neuroimage.2018.03.049 10.1109/CVPR.2018.00329 10.1109/TIP.2003.819861 10.1038/nrn.2018.1 10.1145/3442188.3445932 10.1186/s13634-016-0315-5 10.1109/TMI.2020.3037187 10.1109/TCI.2016.2601296 10.1109/42.79473 10.1016/j.compbiomed.2020.103755 10.1109/TMI.2019.2927101 |
| ContentType | Journal Article |
| Copyright | 2025 The Author(s) The Author(s) Copyright © 2025 The Author(s). Published by Elsevier Inc. All rights reserved. |
| Copyright_xml | – notice: 2025 The Author(s) – notice: The Author(s) – notice: Copyright © 2025 The Author(s). Published by Elsevier Inc. All rights reserved. |
| DBID | 6I. AAFTH AAYXX CITATION CGR CUY CVF ECM EIF NPM 7TK 8FD FR3 K9. P64 RC3 7X8 5PM DOA |
| DOI | 10.1016/j.neuroimage.2025.121293 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Neurosciences Abstracts Technology Research Database Engineering Research Database ProQuest Health & Medical Complete (Alumni) Biotechnology and BioEngineering Abstracts Genetics Abstracts MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) ProQuest Health & Medical Complete (Alumni) Genetics Abstracts Engineering Research Database Technology Research Database Neurosciences Abstracts Biotechnology and BioEngineering Abstracts MEDLINE - Academic |
| DatabaseTitleList | ProQuest Health & Medical Complete (Alumni) MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1095-9572 |
| EndPage | 121293 |
| ExternalDocumentID | oai_doaj_org_article_9b416f9e0ba74d589b4184bf0aeb1624 PMC12277040 40550405 10_1016_j_neuroimage_2025_121293 S1053811925002964 1_s2_0_S1053811925002964 |
| Genre | Journal Article |
| GrantInformation_xml | – fundername: NIMH NIH HHS grantid: R01 MH125479 – fundername: NIMH NIH HHS grantid: R01 MH133836 – fundername: NINDS NIH HHS grantid: R01 NS134849 – fundername: NIBIB NIH HHS grantid: R01 EB008374 – fundername: NIBIB NIH HHS grantid: R01 EB035160 |
| GroupedDBID | --- --K --M .1- .FO .~1 0R~ 123 1B1 1RT 1~. 1~5 4.4 457 4G. 5RE 5VS 7-5 71M 8P~ 9JM AABNK AAEDT AAEDW AAFWJ AAIKJ AAKOC AALRI AAOAW AATTM AAXKI AAXLA AAXUO AAYWO ABBQC ABCQJ ABFNM ABFRF ABIVO ABJNI ABMAC ABMZM ACDAQ ACGFO ACGFS ACIEU ACPRK ACRLP ACVFH ADBBV ADCNI ADEZE ADFRT ADVLN AEBSH AEFWE AEIPS AEKER AENEX AEUPX AFJKZ AFPKN AFPUW AFRHN AFTJW AFXIZ AGCQF AGUBO AGWIK AGYEJ AHHHB AHMBA AIEXJ AIGII AIIUN AIKHN AITUG AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX APXCP AXJTR BENPR BHPHI BKOJK BLXMC BNPGV CS3 DM4 DU5 EBS EFBJH EFKBS EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GROUPED_DOAJ HCIFZ IHE J1W KOM LG5 LX8 M29 M2M M2V M41 M7P MO0 MOBAO N9A O-L O9- OAUVE OK1 OVD OZT P-8 P-9 P2P PC. Q38 ROL RPZ SAE SCC SDF SDG SDP SES SEW SSH SSN SSZ T5K TEORI UV1 YK3 Z5R ZU3 ~G- 29N 53G 7X7 88E 8AO 8FE 8FH 8FI 8FJ AAQFI AAQXK ABUWG ABXDB ACRPL ADFGL ADMUD ADNMO ADXHL AFKRA AGHFR AGQPQ AKRLJ ASPBG AVWKF AZFZN AZQEC BBNVY BPHCQ BVXVI CAG CCPQU COF DWQXO EJD FEDTE FGOYB FYUFA G-2 GNUQQ HDW HEI HMCUK HMK HMO HMQ HVGLF HZ~ LK8 M1P PHGZM PHGZT PJZUB PPXIY PQGLB PQQKQ PROAC PSQYO PSYQQ R2- SNS UKHRP WUQ XPP ZMT 6I. AAFTH AAYXX CITATION AGRNS ALIPV CGR CUY CVF ECM EIF NPM 7TK 8FD FR3 K9. P64 RC3 7X8 PUEGO 5PM |
| ID | FETCH-LOGICAL-c633t-d581709b2222e0d6bc7c684c6e9d09d55642e3123b151bdc9749c12db5fb46af3 |
| IEDL.DBID | DOA |
| ISSN | 1053-8119 1095-9572 |
| IngestDate | Wed Aug 27 01:27:37 EDT 2025 Thu Aug 21 18:25:43 EDT 2025 Fri Sep 05 15:49:27 EDT 2025 Sat Aug 23 13:31:00 EDT 2025 Fri Aug 01 03:41:23 EDT 2025 Wed Aug 20 07:45:34 EDT 2025 Sat Sep 06 17:20:35 EDT 2025 Fri Aug 22 09:50:48 EDT 2025 Tue Aug 26 17:21:53 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Unsupervised single-image super-resolution Trustworthy reconstruction Infant brain MRI |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. Copyright © 2025 The Author(s). Published by Elsevier Inc. All rights reserved. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/). |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c633t-d581709b2222e0d6bc7c684c6e9d09d55642e3123b151bdc9749c12db5fb46af3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 C.C. Tsai and X. Chen are co-first authors |
| ORCID | 0009-0002-0979-3855 0000-0003-2390-9797 0000-0001-7243-9977 0000-0003-1489-2102 |
| OpenAccessLink | https://doaj.org/article/9b416f9e0ba74d589b4184bf0aeb1624 |
| PMID | 40550405 |
| PQID | 3233468032 |
| PQPubID | 2031077 |
| PageCount | 1 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_9b416f9e0ba74d589b4184bf0aeb1624 pubmedcentral_primary_oai_pubmedcentral_nih_gov_12277040 proquest_miscellaneous_3223635053 proquest_journals_3233468032 pubmed_primary_40550405 crossref_primary_10_1016_j_neuroimage_2025_121293 elsevier_sciencedirect_doi_10_1016_j_neuroimage_2025_121293 elsevier_clinicalkeyesjournals_1_s2_0_S1053811925002964 elsevier_clinicalkey_doi_10_1016_j_neuroimage_2025_121293 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-08-15 |
| PublicationDateYYYYMMDD | 2025-08-15 |
| PublicationDate_xml | – month: 08 year: 2025 text: 2025-08-15 day: 15 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: Amsterdam |
| PublicationTitle | NeuroImage (Orlando, Fla.) |
| PublicationTitleAlternate | Neuroimage |
| PublicationYear | 2025 |
| Publisher | Elsevier Inc Elsevier Limited Elsevier |
| Publisher_xml | – name: Elsevier Inc – name: Elsevier Limited – name: Elsevier |
| References | Gilmore, Knickmeyer, Gao (b13) 2018; 19 Qayyum, Ilahi, Shamshad, Boussaid, Bennamoun, Qadir (b31) 2022 Darestani, Mohammad Zalbagi, Heckel, Reinhard, 2021. Can un-trained networks compete with trained ones for accelerated MRI?. In: Annual Meeting of the International Society for Magnetic Resonance in Medicine. ISMRM. Jin, Lee, Ye (b20) 2016; 2 Wang, Su, Ying, Peng, Zhu, Liang, Feng, Liang (b44) 2016 Shi, Cheng, Wang, Yap, Shen (b33) 2015; 34 Steed, Ryan, Caliskan, Aylin, 2021. Image representations learned with unsupervised pre-training contain human-like biases. In: ACM Conference on Fairness, Accountability, and Transparency. pp. 701–713. Liu, Sun, Xu, Kamilov (b28) 2019 Iwamoto, Takeda, Li, Shiino, Chen (b18) 2022; 7 Tsai, Chen, Ahmad, Yap (b40) 2023 Chen, Qu, Xie, Ahmad, Yap (b5) 2023; 10 Zeng, Zheng, Cai, Yang, Zhang, Chen (b52) 2018; 99 Tourbier, Bresson, Hagmann, Thiran, Meuli, Cuadra (b39) 2015; 118 Chen, Xie, Zhou, Shi, Christodoulou, Li (b6) 2018 Ulyanov, Dmitry, Vedaldi, Andrea, Lempitsky, Victor, 2018. Deep image prior. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 9446–9454. Chen, He, Qing, Wu, Ren, Sheriff, Zhu (b4) 2022; 79 Pham, Ducournau, Fablet, Rousseau (b30) 2017 Noll, Nishimura, Macovski (b29) 1991; 10 Deka, Mullah, Datta, Lakshmi, Ganesan (b9) 2019 Barkovich, Li, Desikan, Barkovich, Xu (b2) 2019; 185 Charbonnier, Blanc-Feraud, Aubert, Barlaud (b3) 1994; 2 Storey, Frigo, Hinks, Mock, Collick, Baker, Marmurek, Graham (b37) 2007; 57 Liu, Li, Huang, Ahn, Han, Razi, Xiang, Kim, Feng (b27) 2022 Zhang, Shi, Cheng, Wang, Yap, Shen (b54) 2018; 49 Wang, Bovik, Sheikh, Simoncelli (b42) 2004; 13 Zeng, Peng, Wang, Liu (b51) 2020; 81 Zhao, Carass, Dewey, Woo, Oh, Calabresi, Reich, Sati, Pham, Prince (b56) 2018 Gu, Li, Wang, Yang, Qiao, Yu (b14) 2019; 7 Howell, Styner, Gao, Yap, Wang, Baluyot, Yacoub, Chen, Potts, Salzwedel (b16) 2019; 185 Tang, Fang (b38) 2016; 2016 Lee, Yoo, Tak, Ye (b24) 2018; 65 Yazdanpanah, Afacan, Warfield (b49) 2019; vol. 10949 Zhang, He, Guo, Ettehadi, Aw, Semanek, Posner, Laine, Wang (b53) 2021 Jaimes, Kirsch, Gee (b19) 2018; 48 Zhao, Carass, Dewey, Prince (b55) 2018 Gholipour, Afacan, Aganj, Scherrer, Prabhu, Sahin, Warfield (b12) 2015; 42 Ebner, Wang, Li, Aertsen, Patel, Aughwane, Melbourne, Doel, Dymarkowski, De Coppi (b11) 2020; 206 Liu, Chen, Chen, Chen, Sun (b26) 2023 Shocher, Assaf, Cohen, Nadav, Irani, Michal, 2018. “Zero-shot” super-resolution using deep internal learning. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 3118–3126. Han, Sunwoo, Ye (b15) 2019; 39 Kim, Jung, Kim (b22) 2020; 27 Zhou, Huang, Li, Zhou, Zheng (b59) 2022; 27 Zhao, Huang, Zhao, Qin, Zheng (b58) 2021; 2021 Lai, Wei-Sheng, Huang, Jia-Bin, Ahuja, Narendra, Yang, Ming-Hsuan, 2017. Deep laplacian pyramid networks for fast and accurate super-resolution. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 624–632. Wang, Chen, Hoi (b43) 2020; 43 Liang, Lauterbur (b25) 2000 Akçakaya, Moeller, Weingärtner, Uğurbil (b1) 2019; 81 Delannoy, Pham, Cazorla, Tor-Díez, Dollé, Meunier, Bednarek, Fablet, Passat, Rousseau (b10) 2020; 120 Yaman, Hosseini, Akçakaya (b47) 2021 Yang, Zhang, Tian, Wang, Xue, Liao (b48) 2019; 21 Wu, Chen, Li, Wang, Wang, Wei, Zhang (b45) 2023 Huang, Gao, Liu, Zhuang, Van Der Maaten, Laurens, Weinberger, Kilian Q, 2017. Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 4700–4708. Jog, Carass, Prince (b21) 2016 Cui, Jia, Cao, Zhu, Liu, Qiu, Liu, Cheng, Wang, Zhu (b7) 2023; 88 Yuan, Yuan, Liu, Siyuan, Zhang, Jiawei, Zhang, Yongbing, Dong, Chao, Lin, Liang, 2018. Unsupervised image super-resolution using cycle-in-cycle generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop. pp. 701–710. Shi, Mettes, Maji, Snoek (b34) 2022; 130 Xue, Zhang, Mou, Bovik (b46) 2013; 23 Senouf, Vedula, Weiss, Bronstein, Michailovich, Zibulevsky (b32) 2019 Zhao, Dewey, Pham, Calabresi, Reich, Prince (b57) 2020; 40 Zhao (10.1016/j.neuroimage.2025.121293_b55) 2018 Chen (10.1016/j.neuroimage.2025.121293_b6) 2018 Iwamoto (10.1016/j.neuroimage.2025.121293_b18) 2022; 7 Yazdanpanah (10.1016/j.neuroimage.2025.121293_b49) 2019; vol. 10949 Wang (10.1016/j.neuroimage.2025.121293_b44) 2016 Jin (10.1016/j.neuroimage.2025.121293_b20) 2016; 2 10.1016/j.neuroimage.2025.121293_b17 Tang (10.1016/j.neuroimage.2025.121293_b38) 2016; 2016 Gholipour (10.1016/j.neuroimage.2025.121293_b12) 2015; 42 Zhou (10.1016/j.neuroimage.2025.121293_b59) 2022; 27 Cui (10.1016/j.neuroimage.2025.121293_b7) 2023; 88 10.1016/j.neuroimage.2025.121293_b23 Charbonnier (10.1016/j.neuroimage.2025.121293_b3) 1994; 2 Shi (10.1016/j.neuroimage.2025.121293_b33) 2015; 34 Xue (10.1016/j.neuroimage.2025.121293_b46) 2013; 23 Liu (10.1016/j.neuroimage.2025.121293_b26) 2023 Liang (10.1016/j.neuroimage.2025.121293_b25) 2000 Zhang (10.1016/j.neuroimage.2025.121293_b54) 2018; 49 Howell (10.1016/j.neuroimage.2025.121293_b16) 2019; 185 10.1016/j.neuroimage.2025.121293_b8 Zeng (10.1016/j.neuroimage.2025.121293_b51) 2020; 81 Senouf (10.1016/j.neuroimage.2025.121293_b32) 2019 Tsai (10.1016/j.neuroimage.2025.121293_b40) 2023 Shi (10.1016/j.neuroimage.2025.121293_b34) 2022; 130 Chen (10.1016/j.neuroimage.2025.121293_b4) 2022; 79 Zhao (10.1016/j.neuroimage.2025.121293_b57) 2020; 40 Han (10.1016/j.neuroimage.2025.121293_b15) 2019; 39 Jog (10.1016/j.neuroimage.2025.121293_b21) 2016 Zeng (10.1016/j.neuroimage.2025.121293_b52) 2018; 99 Zhang (10.1016/j.neuroimage.2025.121293_b53) 2021 Chen (10.1016/j.neuroimage.2025.121293_b5) 2023; 10 Wang (10.1016/j.neuroimage.2025.121293_b43) 2020; 43 Ebner (10.1016/j.neuroimage.2025.121293_b11) 2020; 206 Kim (10.1016/j.neuroimage.2025.121293_b22) 2020; 27 10.1016/j.neuroimage.2025.121293_b35 10.1016/j.neuroimage.2025.121293_b36 Wang (10.1016/j.neuroimage.2025.121293_b42) 2004; 13 Pham (10.1016/j.neuroimage.2025.121293_b30) 2017 10.1016/j.neuroimage.2025.121293_b41 Liu (10.1016/j.neuroimage.2025.121293_b28) 2019 Gu (10.1016/j.neuroimage.2025.121293_b14) 2019; 7 Lee (10.1016/j.neuroimage.2025.121293_b24) 2018; 65 Deka (10.1016/j.neuroimage.2025.121293_b9) 2019 Storey (10.1016/j.neuroimage.2025.121293_b37) 2007; 57 Zhao (10.1016/j.neuroimage.2025.121293_b56) 2018 Yang (10.1016/j.neuroimage.2025.121293_b48) 2019; 21 Noll (10.1016/j.neuroimage.2025.121293_b29) 1991; 10 Delannoy (10.1016/j.neuroimage.2025.121293_b10) 2020; 120 Yaman (10.1016/j.neuroimage.2025.121293_b47) 2021 Jaimes (10.1016/j.neuroimage.2025.121293_b19) 2018; 48 Qayyum (10.1016/j.neuroimage.2025.121293_b31) 2022 Wu (10.1016/j.neuroimage.2025.121293_b45) 2023 Zhao (10.1016/j.neuroimage.2025.121293_b58) 2021; 2021 Barkovich (10.1016/j.neuroimage.2025.121293_b2) 2019; 185 Gilmore (10.1016/j.neuroimage.2025.121293_b13) 2018; 19 Liu (10.1016/j.neuroimage.2025.121293_b27) 2022 10.1016/j.neuroimage.2025.121293_b50 Akçakaya (10.1016/j.neuroimage.2025.121293_b1) 2019; 81 Tourbier (10.1016/j.neuroimage.2025.121293_b39) 2015; 118 |
| References_xml | – volume: 130 start-page: 885 year: 2022 end-page: 908 ident: b34 article-title: On measuring and controlling the spectral bias of the deep image prior publication-title: Int. J. Comput. Vis. – volume: 120 year: 2020 ident: b10 article-title: SegSRGAN: Super-resolution and segmentation using generative adversarial networks—Application to neonatal brain MRI publication-title: Comput. Biol. Med. – start-page: 100 year: 2018 end-page: 108 ident: b56 article-title: A deep learning based anti-aliasing self super-resolution algorithm for MRI publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – reference: Darestani, Mohammad Zalbagi, Heckel, Reinhard, 2021. Can un-trained networks compete with trained ones for accelerated MRI?. In: Annual Meeting of the International Society for Magnetic Resonance in Medicine. ISMRM. – volume: 2016 start-page: 1 year: 2016 end-page: 21 ident: b38 article-title: Edge and contrast preserving in total variation image denoising publication-title: EURASIP J. Adv. Signal Process. – volume: 7 start-page: 426 year: 2022 end-page: 435 ident: b18 article-title: Unsupervised MRI super resolution using deep external learning and guided residual dense network with multimodal image priors publication-title: IEEE Trans. Emerg. Top. Comput. Intell. – start-page: 78 year: 2019 end-page: 86 ident: b9 article-title: Sparse representation based super-resolution of MRI images with non-local total variation regularization publication-title: International Conference on Pattern Recognition and Machine Intelligence – year: 2021 ident: b47 article-title: Zero-shot self-supervised learning for MRI reconstruction – volume: 118 start-page: 584 year: 2015 end-page: 597 ident: b39 article-title: An efficient total variation algorithm for super-resolution in fetal brain MRI with adaptive regularization publication-title: NeuroImage – volume: 40 start-page: 805 year: 2020 end-page: 817 ident: b57 article-title: SMORE: a self-supervised anti-aliasing and super-resolution algorithm for MRI using deep learning publication-title: IEEE Trans. Med. Imaging – volume: 88 year: 2023 ident: b7 article-title: K-UNN: k-space interpolation with untrained neural network publication-title: Med. Image Anal. – year: 2022 ident: b27 article-title: Unsupervised representation learning for 3D MRI super resolution with degradation adaptation – reference: Ulyanov, Dmitry, Vedaldi, Andrea, Lempitsky, Victor, 2018. Deep image prior. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 9446–9454. – volume: 42 start-page: 6919 year: 2015 end-page: 6932 ident: b12 article-title: Super-resolution reconstruction in frequency, image, and wavelet domains to reduce through-plane partial voluming in MRI publication-title: Med. Phys. – reference: Steed, Ryan, Caliskan, Aylin, 2021. Image representations learned with unsupervised pre-training contain human-like biases. In: ACM Conference on Fairness, Accountability, and Transparency. pp. 701–713. – year: 2021 ident: b53 article-title: PTNet: A high-resolution infant MRI synthesizer based on transformer – volume: 49 start-page: 662 year: 2018 end-page: 674 ident: b54 article-title: Longitudinally guided super-resolution of neonatal brain magnetic resonance images publication-title: IEEE Trans. Cybern. – volume: 10 start-page: 489 year: 2023 ident: b5 article-title: A paired dataset of T1-and T2-weighted MRI at 3 Tesla and 7 Tesla publication-title: Sci. Data – volume: 2 start-page: 168 year: 1994 end-page: 172 ident: b3 article-title: Two deterministic half-quadratic regularization algorithms for computed imaging publication-title: International Conference on Image Processing – volume: 2 start-page: 480 year: 2016 end-page: 495 ident: b20 article-title: A general framework for compressed sensing and parallel MRI using annihilating filter based low-rank Hankel matrix publication-title: IEEE Trans. Comput. Imaging – start-page: 197 year: 2017 end-page: 200 ident: b30 article-title: Brain MRI super-resolution using deep 3D convolutional networks publication-title: International Symposium on Biomedical Imaging – volume: 79 start-page: 124 year: 2022 end-page: 145 ident: b4 article-title: Real-world single image super-resolution: A brief review publication-title: Inf. Fusion – volume: 13 start-page: 600 year: 2004 end-page: 612 ident: b42 article-title: Image quality assessment: from error visibility to structural similarity publication-title: IEEE Trans. Image Process. – volume: 23 start-page: 684 year: 2013 end-page: 695 ident: b46 article-title: Gradient magnitude similarity deviation: A highly efficient perceptual image quality index publication-title: IEEE Trans. Image Process. – reference: Yuan, Yuan, Liu, Siyuan, Zhang, Jiawei, Zhang, Yongbing, Dong, Chao, Lin, Liang, 2018. Unsupervised image super-resolution using cycle-in-cycle generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop. pp. 701–710. – reference: Huang, Gao, Liu, Zhuang, Van Der Maaten, Laurens, Weinberger, Kilian Q, 2017. Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 4700–4708. – volume: 185 start-page: 891 year: 2019 end-page: 905 ident: b16 article-title: The UNC/UMN baby connectome project (BCP): An overview of the study design and protocol development publication-title: NeuroImage – year: 2022 ident: b31 article-title: Untrained neural network priors for inverse imaging problems: A survey publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 553 year: 2016 end-page: 560 ident: b21 article-title: Self super-resolution for magnetic resonance images publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – year: 2000 ident: b25 article-title: Principles of Magnetic Resonance Imaging – start-page: 1 year: 2023 end-page: 5 ident: b45 article-title: Assured: A self-supervised deep decoder network for fetus brain MRI reconstruction publication-title: International Symposium on Biomedical Imaging – volume: 81 start-page: 439 year: 2019 end-page: 453 ident: b1 article-title: Scan-specific robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction: Database-free deep learning for fast imaging publication-title: Magn. Reson. Med. – volume: 2021 year: 2021 ident: b58 article-title: Reference-driven undersampled MR image reconstruction using wavelet sparsity-constrained deep image prior publication-title: Comput. Math. Methods Med. – start-page: 739 year: 2018 end-page: 742 ident: b6 article-title: Brain MRI super resolution using 3D deep densely connected neural networks publication-title: International Symposium on Biomedical Imaging – volume: 7 start-page: 68290 year: 2019 end-page: 68304 ident: b14 article-title: Deep generative adversarial networks for thin-section infant MR image reconstruction publication-title: IEEE Access – reference: Shocher, Assaf, Cohen, Nadav, Irani, Michal, 2018. “Zero-shot” super-resolution using deep internal learning. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 3118–3126. – volume: 99 start-page: 133 year: 2018 end-page: 141 ident: b52 article-title: Simultaneous single-and multi-contrast super-resolution for brain MRI images based on a convolutional neural network publication-title: Comput. Biol. Med. – volume: 48 start-page: 1197 year: 2018 end-page: 1208 ident: b19 article-title: Fast, free-breathing and motion-minimized techniques for pediatric body magnetic resonance imaging publication-title: Pediatr. Radiol. – volume: 65 start-page: 1985 year: 2018 end-page: 1995 ident: b24 article-title: Deep residual learning for accelerated MRI using magnitude and phase networks publication-title: IEEE Trans. Biomed. Eng. – start-page: 365 year: 2018 end-page: 368 ident: b55 article-title: Self super-resolution for magnetic resonance images using deep networks publication-title: International Symposium on Biomedical Imaging – volume: 57 start-page: 614 year: 2007 end-page: 619 ident: b37 article-title: Partial k-space reconstruction in single-shot diffusion-weighted echo-planar imaging publication-title: Magn. Reson. Med. Off. J. Int. Soc. Magn. Reson. Med. – reference: Lai, Wei-Sheng, Huang, Jia-Bin, Ahuja, Narendra, Yang, Ming-Hsuan, 2017. Deep laplacian pyramid networks for fast and accurate super-resolution. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 624–632. – volume: 185 start-page: 793 year: 2019 end-page: 801 ident: b2 article-title: Challenges in pediatric neuroimaging publication-title: NeuroImage – start-page: 111 year: 2019 end-page: 119 ident: b32 article-title: Self-supervised learning of inverse problem solvers in medical imaging publication-title: MICCAI Workshop on Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect Data – volume: 39 start-page: 377 year: 2019 end-page: 386 ident: b15 article-title: K-space deep learning for accelerated MRI publication-title: IEEE Trans. Med. Imaging – start-page: 514 year: 2016 end-page: 517 ident: b44 article-title: Accelerating magnetic resonance imaging via deep learning publication-title: International Symposium on Biomedical Imaging – volume: 10 start-page: 154 year: 1991 end-page: 163 ident: b29 article-title: Homodyne detection in magnetic resonance imaging publication-title: IEEE Trans. Med. Imaging – volume: 81 year: 2020 ident: b51 article-title: A comparative study of CNN-based super-resolution methods in MRI reconstruction and its beyond publication-title: Signal Process., Image Commun. – volume: 19 start-page: 123 year: 2018 end-page: 137 ident: b13 article-title: Imaging structural and functional brain development in early childhood publication-title: Nature Rev. Neurosci. – volume: 27 start-page: 1409 year: 2022 end-page: 1418 ident: b59 article-title: Blind super-resolution of 3D MRI via unsupervised domain transformation publication-title: IEEE J. Biomed. Heal. Inform. – volume: 21 start-page: 3106 year: 2019 end-page: 3121 ident: b48 article-title: Deep learning for single image super-resolution: A brief review publication-title: IEEE Trans. Multimed. – volume: 206 year: 2020 ident: b11 article-title: An automated framework for localization, segmentation and super-resolution reconstruction of fetal brain MRI publication-title: NeuroImage – volume: vol. 10949 start-page: 21 year: 2019 end-page: 27 ident: b49 article-title: Non-learning based deep parallel MRI reconstruction publication-title: SPIE Medical Imaging – volume: 27 start-page: 1190 year: 2020 end-page: 1194 ident: b22 article-title: Dual back-projection-based internal learning for blind super-resolution publication-title: IEEE Signal Process. Lett. – start-page: 42 year: 2023 end-page: 51 ident: b40 article-title: Robust unsupervised super-resolution of infant MRI via dual-modal deep image prior publication-title: MICCAI Workshop on Machine Learning in Medical Imaging – volume: 34 start-page: 2459 year: 2015 end-page: 2466 ident: b33 article-title: LRTV: MR image super-resolution with low-rank and total variation regularizations publication-title: IEEE Trans. Med. Imaging – volume: 43 start-page: 3365 year: 2020 end-page: 3387 ident: b43 article-title: Deep learning for image super-resolution: A survey publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 403 year: 2023 end-page: 414 ident: b26 article-title: An unsupervised framework for joint MRI super resolution and Gibbs artifact removal publication-title: International Conference on Information Processing in Medical Imaging – start-page: 7715 year: 2019 end-page: 7719 ident: b28 article-title: Image restoration using total variation regularized deep image prior publication-title: International Conference on Acoustics, Speech and Signal Processing – volume: 2021 year: 2021 ident: 10.1016/j.neuroimage.2025.121293_b58 article-title: Reference-driven undersampled MR image reconstruction using wavelet sparsity-constrained deep image prior publication-title: Comput. Math. Methods Med. doi: 10.1155/2021/8865582 – start-page: 739 year: 2018 ident: 10.1016/j.neuroimage.2025.121293_b6 article-title: Brain MRI super resolution using 3D deep densely connected neural networks – volume: 43 start-page: 3365 issue: 10 year: 2020 ident: 10.1016/j.neuroimage.2025.121293_b43 article-title: Deep learning for image super-resolution: A survey publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2020.2982166 – volume: 27 start-page: 1409 issue: 3 year: 2022 ident: 10.1016/j.neuroimage.2025.121293_b59 article-title: Blind super-resolution of 3D MRI via unsupervised domain transformation publication-title: IEEE J. Biomed. Heal. Inform. doi: 10.1109/JBHI.2022.3232511 – volume: 23 start-page: 684 issue: 2 year: 2013 ident: 10.1016/j.neuroimage.2025.121293_b46 article-title: Gradient magnitude similarity deviation: A highly efficient perceptual image quality index publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2013.2293423 – ident: 10.1016/j.neuroimage.2025.121293_b17 doi: 10.1109/CVPR.2017.243 – start-page: 553 year: 2016 ident: 10.1016/j.neuroimage.2025.121293_b21 article-title: Self super-resolution for magnetic resonance images – volume: 81 year: 2020 ident: 10.1016/j.neuroimage.2025.121293_b51 article-title: A comparative study of CNN-based super-resolution methods in MRI reconstruction and its beyond publication-title: Signal Process., Image Commun. doi: 10.1016/j.image.2019.115701 – ident: 10.1016/j.neuroimage.2025.121293_b23 doi: 10.1109/CVPR.2017.618 – volume: vol. 10949 start-page: 21 year: 2019 ident: 10.1016/j.neuroimage.2025.121293_b49 article-title: Non-learning based deep parallel MRI reconstruction – volume: 27 start-page: 1190 year: 2020 ident: 10.1016/j.neuroimage.2025.121293_b22 article-title: Dual back-projection-based internal learning for blind super-resolution publication-title: IEEE Signal Process. Lett. doi: 10.1109/LSP.2020.3005043 – volume: 130 start-page: 885 issue: 4 year: 2022 ident: 10.1016/j.neuroimage.2025.121293_b34 article-title: On measuring and controlling the spectral bias of the deep image prior publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-021-01572-7 – volume: 48 start-page: 1197 year: 2018 ident: 10.1016/j.neuroimage.2025.121293_b19 article-title: Fast, free-breathing and motion-minimized techniques for pediatric body magnetic resonance imaging publication-title: Pediatr. Radiol. doi: 10.1007/s00247-018-4116-x – volume: 10 start-page: 489 issue: 1 year: 2023 ident: 10.1016/j.neuroimage.2025.121293_b5 article-title: A paired dataset of T1-and T2-weighted MRI at 3 Tesla and 7 Tesla publication-title: Sci. Data doi: 10.1038/s41597-023-02400-y – year: 2022 ident: 10.1016/j.neuroimage.2025.121293_b27 – volume: 2 start-page: 168 year: 1994 ident: 10.1016/j.neuroimage.2025.121293_b3 article-title: Two deterministic half-quadratic regularization algorithms for computed imaging – volume: 42 start-page: 6919 issue: 12 year: 2015 ident: 10.1016/j.neuroimage.2025.121293_b12 article-title: Super-resolution reconstruction in frequency, image, and wavelet domains to reduce through-plane partial voluming in MRI publication-title: Med. Phys. doi: 10.1118/1.4935149 – volume: 118 start-page: 584 year: 2015 ident: 10.1016/j.neuroimage.2025.121293_b39 article-title: An efficient total variation algorithm for super-resolution in fetal brain MRI with adaptive regularization publication-title: NeuroImage doi: 10.1016/j.neuroimage.2015.06.018 – ident: 10.1016/j.neuroimage.2025.121293_b41 doi: 10.1109/CVPR.2018.00984 – volume: 88 year: 2023 ident: 10.1016/j.neuroimage.2025.121293_b7 article-title: K-UNN: k-space interpolation with untrained neural network publication-title: Med. Image Anal. doi: 10.1016/j.media.2023.102877 – volume: 185 start-page: 793 year: 2019 ident: 10.1016/j.neuroimage.2025.121293_b2 article-title: Challenges in pediatric neuroimaging publication-title: NeuroImage doi: 10.1016/j.neuroimage.2018.04.044 – ident: 10.1016/j.neuroimage.2025.121293_b8 – volume: 7 start-page: 68290 year: 2019 ident: 10.1016/j.neuroimage.2025.121293_b14 article-title: Deep generative adversarial networks for thin-section infant MR image reconstruction publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2918926 – start-page: 1 year: 2023 ident: 10.1016/j.neuroimage.2025.121293_b45 article-title: Assured: A self-supervised deep decoder network for fetus brain MRI reconstruction – volume: 49 start-page: 662 issue: 2 year: 2018 ident: 10.1016/j.neuroimage.2025.121293_b54 article-title: Longitudinally guided super-resolution of neonatal brain magnetic resonance images publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2017.2786161 – year: 2021 ident: 10.1016/j.neuroimage.2025.121293_b53 – start-page: 403 year: 2023 ident: 10.1016/j.neuroimage.2025.121293_b26 article-title: An unsupervised framework for joint MRI super resolution and Gibbs artifact removal – volume: 65 start-page: 1985 issue: 9 year: 2018 ident: 10.1016/j.neuroimage.2025.121293_b24 article-title: Deep residual learning for accelerated MRI using magnitude and phase networks publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2018.2821699 – volume: 34 start-page: 2459 issue: 12 year: 2015 ident: 10.1016/j.neuroimage.2025.121293_b33 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 – start-page: 42 year: 2023 ident: 10.1016/j.neuroimage.2025.121293_b40 article-title: Robust unsupervised super-resolution of infant MRI via dual-modal deep image prior – volume: 99 start-page: 133 year: 2018 ident: 10.1016/j.neuroimage.2025.121293_b52 article-title: Simultaneous single-and multi-contrast super-resolution for brain MRI images based on a convolutional neural network publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2018.06.010 – volume: 7 start-page: 426 issue: 2 year: 2022 ident: 10.1016/j.neuroimage.2025.121293_b18 article-title: Unsupervised MRI super resolution using deep external learning and guided residual dense network with multimodal image priors publication-title: IEEE Trans. Emerg. Top. Comput. Intell. doi: 10.1109/TETCI.2022.3215137 – volume: 79 start-page: 124 year: 2022 ident: 10.1016/j.neuroimage.2025.121293_b4 article-title: Real-world single image super-resolution: A brief review publication-title: Inf. Fusion doi: 10.1016/j.inffus.2021.09.005 – start-page: 514 year: 2016 ident: 10.1016/j.neuroimage.2025.121293_b44 article-title: Accelerating magnetic resonance imaging via deep learning – volume: 81 start-page: 439 issue: 1 year: 2019 ident: 10.1016/j.neuroimage.2025.121293_b1 article-title: Scan-specific robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction: Database-free deep learning for fast imaging publication-title: Magn. Reson. Med. doi: 10.1002/mrm.27420 – start-page: 7715 year: 2019 ident: 10.1016/j.neuroimage.2025.121293_b28 article-title: Image restoration using total variation regularized deep image prior – volume: 21 start-page: 3106 issue: 12 year: 2019 ident: 10.1016/j.neuroimage.2025.121293_b48 article-title: Deep learning for single image super-resolution: A brief review publication-title: IEEE Trans. Multimed. doi: 10.1109/TMM.2019.2919431 – year: 2022 ident: 10.1016/j.neuroimage.2025.121293_b31 article-title: Untrained neural network priors for inverse imaging problems: A survey publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2022.3204527 – volume: 57 start-page: 614 issue: 3 year: 2007 ident: 10.1016/j.neuroimage.2025.121293_b37 article-title: Partial k-space reconstruction in single-shot diffusion-weighted echo-planar imaging publication-title: Magn. Reson. Med. Off. J. Int. Soc. Magn. Reson. Med. doi: 10.1002/mrm.21132 – ident: 10.1016/j.neuroimage.2025.121293_b50 doi: 10.1109/CVPRW.2018.00113 – start-page: 78 year: 2019 ident: 10.1016/j.neuroimage.2025.121293_b9 article-title: Sparse representation based super-resolution of MRI images with non-local total variation regularization – start-page: 197 year: 2017 ident: 10.1016/j.neuroimage.2025.121293_b30 article-title: Brain MRI super-resolution using deep 3D convolutional networks – volume: 206 year: 2020 ident: 10.1016/j.neuroimage.2025.121293_b11 article-title: An automated framework for localization, segmentation and super-resolution reconstruction of fetal brain MRI publication-title: NeuroImage doi: 10.1016/j.neuroimage.2019.116324 – volume: 185 start-page: 891 year: 2019 ident: 10.1016/j.neuroimage.2025.121293_b16 article-title: The UNC/UMN baby connectome project (BCP): An overview of the study design and protocol development publication-title: NeuroImage doi: 10.1016/j.neuroimage.2018.03.049 – start-page: 111 year: 2019 ident: 10.1016/j.neuroimage.2025.121293_b32 article-title: Self-supervised learning of inverse problem solvers in medical imaging – ident: 10.1016/j.neuroimage.2025.121293_b35 doi: 10.1109/CVPR.2018.00329 – volume: 13 start-page: 600 issue: 4 year: 2004 ident: 10.1016/j.neuroimage.2025.121293_b42 article-title: Image quality assessment: from error visibility to structural similarity publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2003.819861 – volume: 19 start-page: 123 issue: 3 year: 2018 ident: 10.1016/j.neuroimage.2025.121293_b13 article-title: Imaging structural and functional brain development in early childhood publication-title: Nature Rev. Neurosci. doi: 10.1038/nrn.2018.1 – year: 2021 ident: 10.1016/j.neuroimage.2025.121293_b47 – ident: 10.1016/j.neuroimage.2025.121293_b36 doi: 10.1145/3442188.3445932 – volume: 2016 start-page: 1 issue: 1 year: 2016 ident: 10.1016/j.neuroimage.2025.121293_b38 article-title: Edge and contrast preserving in total variation image denoising publication-title: EURASIP J. Adv. Signal Process. doi: 10.1186/s13634-016-0315-5 – volume: 40 start-page: 805 issue: 3 year: 2020 ident: 10.1016/j.neuroimage.2025.121293_b57 article-title: SMORE: a self-supervised anti-aliasing and super-resolution algorithm for MRI using deep learning publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2020.3037187 – start-page: 100 year: 2018 ident: 10.1016/j.neuroimage.2025.121293_b56 article-title: A deep learning based anti-aliasing self super-resolution algorithm for MRI – volume: 2 start-page: 480 issue: 4 year: 2016 ident: 10.1016/j.neuroimage.2025.121293_b20 article-title: A general framework for compressed sensing and parallel MRI using annihilating filter based low-rank Hankel matrix publication-title: IEEE Trans. Comput. Imaging doi: 10.1109/TCI.2016.2601296 – volume: 10 start-page: 154 issue: 2 year: 1991 ident: 10.1016/j.neuroimage.2025.121293_b29 article-title: Homodyne detection in magnetic resonance imaging publication-title: IEEE Trans. Med. Imaging doi: 10.1109/42.79473 – volume: 120 year: 2020 ident: 10.1016/j.neuroimage.2025.121293_b10 article-title: SegSRGAN: Super-resolution and segmentation using generative adversarial networks—Application to neonatal brain MRI publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2020.103755 – start-page: 365 year: 2018 ident: 10.1016/j.neuroimage.2025.121293_b55 article-title: Self super-resolution for magnetic resonance images using deep networks – volume: 39 start-page: 377 issue: 2 year: 2019 ident: 10.1016/j.neuroimage.2025.121293_b15 article-title: K-space deep learning for accelerated MRI publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2019.2927101 – year: 2000 ident: 10.1016/j.neuroimage.2025.121293_b25 |
| SSID | ssj0009148 |
| Score | 2.4841456 |
| Snippet | Acquiring high-resolution (HR) MR images of infant brains is challenging due to lengthy scan times and limited subject compliance. Image super-resolution (SR)... AbstractAcquiring high-resolution (HR) MR images of infant brains is challenging due to lengthy scan times and limited subject compliance. Image... Acquiring high-resolution (HR) MRI of infant brains is challenging due to lengthy scan times and limited subject compliance. Image super-resolution (SR)... |
| SourceID | doaj pubmedcentral proquest pubmed crossref elsevier |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Publisher |
| StartPage | 121293 |
| SubjectTerms | Babies Brain Brain - diagnostic imaging Female Humans Image Processing, Computer-Assisted - methods Infant Infant brain MRI Infant, Newborn Infants Magnetic resonance imaging Magnetic Resonance Imaging - methods Male Neuroimaging Neuroimaging - methods Pediatrics Radiology/Diagnostic Imaging Random variables Trustworthy reconstruction Unsupervised Machine Learning Unsupervised single-image super-resolution |
| SummonAdditionalLinks | – databaseName: Elsevier SD Freedom Collection Journals [SCFCJ] dbid: AIKHN link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB6VrYS4oPIOFBQkrtYmfiUWB9RWrbag7QFYqTcrjh0aBNlVs_v_GSdO2lAOlTjGsWPn83jmm3g8AfhQJNbRonIkQ_JAeE4dKdANITlqwtJTdln4w8nLC7lY8c-X4nIPToazMD6sMuj-Xqd32jqUzAOa801dz78hM0BzgwxF-K0lyR_APmVKihnsH51_WVzc5N5NeX8iTjDiG4SAnj7Mq0sbWf_GxYvOIhU-2wJVbGKlumT-E2N1l4z-HVN5y0idHcDjwC7jo_4FnsCea57Cw2XYP38Gn1ZNu9t49dA6G_vPBL8c6YYVd-UEne8gizGy2RjFD5GPjf-PRLz8ev4cVmen308WJPxCgZSSsS2xwifgUwZZAHWJlabMSpnzUjplE2WFQPfDMbReBi2_sSV6F6pMqTWiMlwWFXsBs2bduFcQl5XJeMULic_klcUqrDIWdQBjRubWRZAOkOlNnylDDyFkP_UNzNrDrHuYIzj22I71fa7rrmB9_UOHydbKIGmslEtMkXHs3F_n3FRJgXZGUh6BGmZGD8dJUQHig-p7DCD7V1vXhpXc6lS3VCf6jrRF8HFsORHYe_Z7OIiQHrtilDEu84TRCN6Pt3G5-z2conHrna9DGXJEHEwEL3uJG9FD7i1wPkQE-UQWJ_BO7zT1VZdSPKU0y7Dt6_96qzfwyF_5T-6pOITZ9nrn3iJn25p3YU3-AYC9QIg priority: 102 providerName: Elsevier |
| Title | Unsupervised single-image super-resolution for infant brain MRI |
| URI | https://www.clinicalkey.com/#!/content/1-s2.0-S1053811925002964 https://www.clinicalkey.es/playcontent/1-s2.0-S1053811925002964 https://dx.doi.org/10.1016/j.neuroimage.2025.121293 https://www.ncbi.nlm.nih.gov/pubmed/40550405 https://www.proquest.com/docview/3233468032 https://www.proquest.com/docview/3223635053 https://pubmed.ncbi.nlm.nih.gov/PMC12277040 https://doaj.org/article/9b416f9e0ba74d589b4184bf0aeb1624 |
| Volume | 317 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwEB5BkRAXxJuUsgoSV4PjV2JxQAVRbUHbA7BSb5Yd22IRpFWze-W3M86LBpDogeMmduz9ZsbzTTwZAzy31AdmYyAlkgciKhaIxTCEVLgS1omyK5s-Tl6dqOVavD-Vp5eO-ko5YX154B64l9ohZYg6UGdL4WWVflfCRWpxlVGsqwRKNR2DqbHcLrL8IW-nz-bqqkNuvqONYkzIZCqqwDSfOaOuZv_MJ_3JOX9Pnbzki47uwO2BROaH_eTvwrXQ3IObq2Gb_D68Xjft7jytAm3weXob8C2Qblp5d51gjD2oXI6kNUctQ4Bzl46LyFcfjx_A-ujd57dLMpyUQGrF-ZYgLkVJtUNnzwL1ytVlrSpRq6A91V5KjDICRyfl0ME7X2MQoeuCeSejE8pG_hD2mrMmPIa8jq4UUViFzxTRYxMenUdT59ypyocMihEyc94XxDBjpthX8wtmk2A2PcwZvEnYTu1TSevuAgraDII2_xJ0BnqUjBm_GsV1Dh-0ucIEyr_1De1gsK0pTMsMNZ-QbiKHQdor036lwlFfTT0HTtJzjSuOezCqkJmG4oxzoSrKWQbPptto1WmrxjbhbJfaMI5UECeTwaNe4yb0kGJLlIfMoJrp4gze-Z1m86WrHF4wVpbYd_9_COQJ3Ep_Nb1gL-QB7G0vduEpMrStW8D1Fz-KBdw4PP6wPFl0pvkTWnY9Qw |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB6VIgEXxLuBAkHiajbxK7E4IKiottDtAbpSb1YcOxBUsqtm98pvZ5w4KaEcKnFcP2Lv5_HMN_F4AvC6SKyjReVIhuSB8Jw6UqAbQnLUhKWn7LLwl5MXJ3K-5J_OxNkOHAx3YXxYZdD9vU7vtHUomQU0Z-u6nn1FZoDmBhmK8EdLkt-Am1ywzMf1vfl1GeehUt7fhxOM-OYhnKcP8uqSRtY_ceuiq0iFz7VAFZvYqC6V_8RUXaWif0dU_mGiDu_B3cAt4_f99O_DjmsewK1FOD1_CO-WTbtde-XQOhv7lwTnjnTTirtygq53kMQYuWyMwoe4x8Z_RSJefDl6BMvDj6cHcxI-oEBKydiGWOHT7ymDHIC6xEpTZqXMeSmdsomyQqDz4RjaLoN239gSfQtVptQaURkui4o9ht1m1bg9iMvKZLzihcRn8spiE1YZixqAMSNz6yJIB8j0us-ToYcAsh_6EmbtYdY9zBF88NiO7X2m665gdfFNh6XWyiBlrJRLTJFxHNz_zrmpkgKtjKQ8AjWsjB4uk6L6wwfV15hA9q--rg37uNWpbqlO9BVZi-Dt2HMirtccd38QIT0OxShjXOYJoxG8Gqtxs_sTnKJxq61vQxkyRJxMBE96iRvRQ-YtcD1EBPlEFifwTmua-nuXUDylNMuw79P_-lcv4fb8dHGsj49OPj-DO77Gv3xPxT7sbi627jmyt4150e3O38kLQlE |
| 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=Unsupervised+single-image+super-resolution+for+infant+brain+MRI&rft.jtitle=NeuroImage+%28Orlando%2C+Fla.%29&rft.au=Tsai%2C+Cheng+Che&rft.au=Chen%2C+Xiaoyang&rft.au=Ahmad%2C+Sahar&rft.au=Yap%2C+Pew-Thian&rft.date=2025-08-15&rft.issn=1053-8119&rft.eissn=1095-9572&rft.volume=317&rft.spage=121293&rft.epage=121293&rft_id=info:doi/10.1016%2Fj.neuroimage.2025.121293&rft_id=info%3Apmid%2F40550405&rft.externalDocID=PMC12277040 |
| thumbnail_m | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F10538119%2FS1053811925X00100%2Fcov150h.gif |