A subject-specific unsupervised deep learning method for quantitative susceptibility mapping using implicit neural representation
•Subject-specific and unsupervised deep learning for QSM reconstruction.•Integration of implicit continuous signal representation and explicit regularizations.•Phase compensation strategy for an accurate physical model.•Improved accuracy and quality compared with established methods. Quantitative su...
Gespeichert in:
| Veröffentlicht in: | Medical image analysis Jg. 95; S. 103173 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Netherlands
Elsevier B.V
01.07.2024
|
| Schlagworte: | |
| ISSN: | 1361-8415, 1361-8423, 1361-8423 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | •Subject-specific and unsupervised deep learning for QSM reconstruction.•Integration of implicit continuous signal representation and explicit regularizations.•Phase compensation strategy for an accurate physical model.•Improved accuracy and quality compared with established methods.
Quantitative susceptibility mapping (QSM) is an MRI-based technique that estimates the underlying tissue magnetic susceptibility based on phase signal. Deep learning (DL)-based methods have shown promise in handling the challenging ill-posed inverse problem for QSM reconstruction. However, they require extensive paired training data that are typically unavailable and suffer from generalization problems. Recent model-incorporated DL approaches also overlook the non-local effect of the tissue phase in applying the source-to-field forward model due to patch-based training constraint, resulting in a discrepancy between the prediction and measurement and subsequently suboptimal QSM reconstruction. This study proposes an unsupervised and subject-specific DL method for QSM reconstruction based on implicit neural representation (INR), referred to as INR-QSM. INR has emerged as a powerful framework for learning a high-quality continuous representation of the signal (image) by exploiting its internal information without training labels. In INR-QSM, the desired susceptibility map is represented as a continuous function of the spatial coordinates, parameterized by a fully-connected neural network. The weights are learned by minimizing a loss function that includes a data fidelity term incorporated by the physical model and regularization terms. Additionally, a novel phase compensation strategy is proposed for the first time to account for the non-local effect of tissue phase in data consistency calculation to make the physical model more accurate. Our experiments show that INR-QSM outperforms traditional established QSM reconstruction methods and the compared unsupervised DL method both qualitatively and quantitatively, and is competitive against supervised DL methods under data perturbations. |
|---|---|
| AbstractList | Quantitative susceptibility mapping (QSM) is an MRI-based technique that estimates the underlying tissue magnetic susceptibility based on phase signal. Deep learning (DL)-based methods have shown promise in handling the challenging ill-posed inverse problem for QSM reconstruction. However, they require extensive paired training data that are typically unavailable and suffer from generalization problems. Recent model-incorporated DL approaches also overlook the non-local effect of the tissue phase in applying the source-to-field forward model due to patch-based training constraint, resulting in a discrepancy between the prediction and measurement and subsequently suboptimal QSM reconstruction. This study proposes an unsupervised and subject-specific DL method for QSM reconstruction based on implicit neural representation (INR), referred to as INR-QSM. INR has emerged as a powerful framework for learning a high-quality continuous representation of the signal (image) by exploiting its internal information without training labels. In INR-QSM, the desired susceptibility map is represented as a continuous function of the spatial coordinates, parameterized by a fully-connected neural network. The weights are learned by minimizing a loss function that includes a data fidelity term incorporated by the physical model and regularization terms. Additionally, a novel phase compensation strategy is proposed for the first time to account for the non-local effect of tissue phase in data consistency calculation to make the physical model more accurate. Our experiments show that INR-QSM outperforms traditional established QSM reconstruction methods and the compared unsupervised DL method both qualitatively and quantitatively, and is competitive against supervised DL methods under data perturbations.Quantitative susceptibility mapping (QSM) is an MRI-based technique that estimates the underlying tissue magnetic susceptibility based on phase signal. Deep learning (DL)-based methods have shown promise in handling the challenging ill-posed inverse problem for QSM reconstruction. However, they require extensive paired training data that are typically unavailable and suffer from generalization problems. Recent model-incorporated DL approaches also overlook the non-local effect of the tissue phase in applying the source-to-field forward model due to patch-based training constraint, resulting in a discrepancy between the prediction and measurement and subsequently suboptimal QSM reconstruction. This study proposes an unsupervised and subject-specific DL method for QSM reconstruction based on implicit neural representation (INR), referred to as INR-QSM. INR has emerged as a powerful framework for learning a high-quality continuous representation of the signal (image) by exploiting its internal information without training labels. In INR-QSM, the desired susceptibility map is represented as a continuous function of the spatial coordinates, parameterized by a fully-connected neural network. The weights are learned by minimizing a loss function that includes a data fidelity term incorporated by the physical model and regularization terms. Additionally, a novel phase compensation strategy is proposed for the first time to account for the non-local effect of tissue phase in data consistency calculation to make the physical model more accurate. Our experiments show that INR-QSM outperforms traditional established QSM reconstruction methods and the compared unsupervised DL method both qualitatively and quantitatively, and is competitive against supervised DL methods under data perturbations. •Subject-specific and unsupervised deep learning for QSM reconstruction.•Integration of implicit continuous signal representation and explicit regularizations.•Phase compensation strategy for an accurate physical model.•Improved accuracy and quality compared with established methods. Quantitative susceptibility mapping (QSM) is an MRI-based technique that estimates the underlying tissue magnetic susceptibility based on phase signal. Deep learning (DL)-based methods have shown promise in handling the challenging ill-posed inverse problem for QSM reconstruction. However, they require extensive paired training data that are typically unavailable and suffer from generalization problems. Recent model-incorporated DL approaches also overlook the non-local effect of the tissue phase in applying the source-to-field forward model due to patch-based training constraint, resulting in a discrepancy between the prediction and measurement and subsequently suboptimal QSM reconstruction. This study proposes an unsupervised and subject-specific DL method for QSM reconstruction based on implicit neural representation (INR), referred to as INR-QSM. INR has emerged as a powerful framework for learning a high-quality continuous representation of the signal (image) by exploiting its internal information without training labels. In INR-QSM, the desired susceptibility map is represented as a continuous function of the spatial coordinates, parameterized by a fully-connected neural network. The weights are learned by minimizing a loss function that includes a data fidelity term incorporated by the physical model and regularization terms. Additionally, a novel phase compensation strategy is proposed for the first time to account for the non-local effect of tissue phase in data consistency calculation to make the physical model more accurate. Our experiments show that INR-QSM outperforms traditional established QSM reconstruction methods and the compared unsupervised DL method both qualitatively and quantitatively, and is competitive against supervised DL methods under data perturbations. Quantitative susceptibility mapping (QSM) is an MRI-based technique that estimates the underlying tissue magnetic susceptibility based on phase signal. Deep learning (DL)-based methods have shown promise in handling the challenging ill-posed inverse problem for QSM reconstruction. However, they require extensive paired training data that are typically unavailable and suffer from generalization problems. Recent model-incorporated DL approaches also overlook the non-local effect of the tissue phase in applying the source-to-field forward model due to patch-based training constraint, resulting in a discrepancy between the prediction and measurement and subsequently suboptimal QSM reconstruction. This study proposes an unsupervised and subject-specific DL method for QSM reconstruction based on implicit neural representation (INR), referred to as INR-QSM. INR has emerged as a powerful framework for learning a high-quality continuous representation of the signal (image) by exploiting its internal information without training labels. In INR-QSM, the desired susceptibility map is represented as a continuous function of the spatial coordinates, parameterized by a fully-connected neural network. The weights are learned by minimizing a loss function that includes a data fidelity term incorporated by the physical model and regularization terms. Additionally, a novel phase compensation strategy is proposed for the first time to account for the non-local effect of tissue phase in data consistency calculation to make the physical model more accurate. Our experiments show that INR-QSM outperforms traditional established QSM reconstruction methods and the compared unsupervised DL method both qualitatively and quantitatively, and is competitive against supervised DL methods under data perturbations. |
| ArticleNumber | 103173 |
| Author | Zhang, Yuyao Wu, Jinsong Feng, Jie Li, Zhenghao Feng, Ruimin Liu, Chunlei Wei, Hongjiang Zhang, Zhiyong Yan, Fuhua Wu, Qing Ma, Chengxin Zhang, Ming |
| Author_xml | – sequence: 1 givenname: Ming orcidid: 0000-0001-8260-0437 surname: Zhang fullname: Zhang, Ming organization: School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China – sequence: 2 givenname: Ruimin orcidid: 0000-0002-4428-2316 surname: Feng fullname: Feng, Ruimin organization: School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China – sequence: 3 givenname: Zhenghao orcidid: 0000-0002-2047-5041 surname: Li fullname: Li, Zhenghao organization: School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China – sequence: 4 givenname: Jie orcidid: 0000-0002-7734-902X surname: Feng fullname: Feng, Jie organization: School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China – sequence: 5 givenname: Qing surname: Wu fullname: Wu, Qing organization: School of Information Science and Technology, ShanghaiTech University, Shanghai, China – sequence: 6 givenname: Zhiyong orcidid: 0000-0001-9773-7348 surname: Zhang fullname: Zhang, Zhiyong organization: School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China – sequence: 7 givenname: Chengxin orcidid: 0009-0001-7682-0879 surname: Ma fullname: Ma, Chengxin organization: Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China – sequence: 8 givenname: Jinsong surname: Wu fullname: Wu, Jinsong organization: Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China – sequence: 9 givenname: Fuhua orcidid: 0000-0002-5910-1506 surname: Yan fullname: Yan, Fuhua organization: Department of Radiology, Ruijin Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China – sequence: 10 givenname: Chunlei orcidid: 0000-0001-8816-4832 surname: Liu fullname: Liu, Chunlei organization: Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA – sequence: 11 givenname: Yuyao surname: Zhang fullname: Zhang, Yuyao organization: School of Information Science and Technology, ShanghaiTech University, Shanghai, China – sequence: 12 givenname: Hongjiang orcidid: 0000-0002-9060-4152 surname: Wei fullname: Wei, Hongjiang email: hongjiang.wei@sjtu.edu.cn organization: School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/38657424$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kTtv1jAUhi1URC_wC5CQR5Z82LHjJANDVXGTKrHAbDnOCZxPieP68kkd-89xSMvA0MW2rOc5st_3kpy51QEhbzk7cMbVh-NhgRHNoWa1LDeCt-IFueBC8aqTtTj7d-bNObmM8cgYa6Vkr8i56FTTylpekIdrGvNwBJuq6MHihJZmF7OHcMIIIx0BPJ3BBIfuF10g_V5HOq2B3mXjEiaT8ARlRrTgEw44Y7qni_F-w3PcVlz8jBYTdZCDmWkAHyCC29zVvSYvJzNHePO4X5Gfnz_9uPla3X7_8u3m-rayoulT1Y5tb1oGo5XQmckMXEwdG6Tt2VR3RilQslGKC8aGabAdiNHafnOEELbrxBV5v8_1Yb3LEJNesDx6no2DNUctmFQNV7xuC_ruEc1DyVj7gIsJ9_optgL0O2DDGmOASVvcf5OCwVlzpreK9FH_rUhvFem9ouKK_9yn8c9bH3cLSkQnhKCjRXC2gKGUp8cVn_X_AIVervs |
| CitedBy_id | crossref_primary_10_1088_1361_6560_addfa5 crossref_primary_10_1016_j_bspc_2025_108217 crossref_primary_10_1016_j_bspc_2024_107446 crossref_primary_10_1016_j_redox_2025_103561 |
| Cites_doi | 10.1145/3503250 10.1148/radiol.2018180136 10.1109/TCI.2021.3097596 10.1002/mrm.29588 10.2214/ajr.145.4.843 10.1016/j.neuroimage.2012.04.042 10.1016/j.neuroimage.2011.08.077 10.1002/hbm.10062 10.1145/3528223.3530127 10.1016/j.neuroimage.2019.116064 10.1016/j.media.2022.102700 10.1016/j.media.2022.102477 10.1016/j.neuroimage.2019.03.060 10.18383/j.tom.2015.00136 10.1002/mrm.25358 10.1016/j.neuroimage.2022.119522 10.1109/TCI.2023.3281196 10.1088/0031-9155/51/24/007 10.1002/mrm.25029 10.1002/mrm.26830 10.1109/TMI.2023.3236216 10.1016/j.neuroimage.2023.120148 10.1002/mrm.28754 10.1002/mrm.22135 10.1002/mrm.28716 10.1002/mrm.29547 10.1002/nbm.3570 10.1016/j.neuroimage.2021.118376 10.1002/nbm.3383 10.1016/j.neuroimage.2014.12.043 10.1093/brain/aww278 10.1002/mrm.21828 10.1016/j.neuroimage.2018.06.036 10.1109/JBHI.2022.3223106 10.1109/MSP.2023.3236483 10.1002/mrm.23000 10.1016/j.neuroimage.2018.10.031 10.1002/mrm.27073 10.1364/OL.28.001194 10.1109/TNNLS.2022.3177134 10.1016/S1361-8415(01)00036-6 10.1002/nbm.4461 10.1016/j.neuroimage.2018.06.030 10.1136/jnnp-2019-322042 10.1109/TCI.2021.3125564 10.1016/j.neuroimage.2010.11.088 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier B.V. Copyright © 2024 Elsevier B.V. All rights reserved. |
| Copyright_xml | – notice: 2024 Elsevier B.V. – notice: Copyright © 2024 Elsevier B.V. All rights reserved. |
| DBID | AAYXX CITATION NPM 7X8 |
| DOI | 10.1016/j.media.2024.103173 |
| DatabaseName | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed |
| 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 Engineering |
| EISSN | 1361-8423 |
| ExternalDocumentID | 38657424 10_1016_j_media_2024_103173 S1361841524000987 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M .~1 0R~ 1B1 1~. 1~5 29M 4.4 457 4G. 53G 5GY 5VS 7-5 71M 8P~ AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABBQC ABJNI ABLVK ABMAC ABMZM ABXDB ACDAQ ACGFS ACIUM ACIWK ACNNM ACPRK ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFRAH AFTJW AFXIZ AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV AJRQY AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ANZVX AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC BNPGV C45 CAG COF CS3 DU5 EBS EFJIC EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HVGLF HX~ HZ~ IHE J1W JJJVA KOM M41 MO0 N9A O-L O9- OAUVE OVD OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SDF SDG SDP SEL SES SEW SPC SPCBC SSH SST SSV SSZ T5K TEORI UHS ~G- 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACIEU ACLOT ACRPL ACVFH ADCNI ADNMO ADVLN AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP ANKPU APXCP CITATION EFKBS EFLBG ~HD AGCQF AGRNS NPM 7X8 |
| ID | FETCH-LOGICAL-c359t-7d79a70edc4e8afab13f80b4c90f28a66e645661300bfbc8e3dcc979a7333c883 |
| ISICitedReferencesCount | 6 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001220917700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1361-8415 1361-8423 |
| IngestDate | Sat Sep 27 19:35:40 EDT 2025 Mon Jul 21 06:02:32 EDT 2025 Sat Nov 29 04:06:12 EST 2025 Tue Nov 18 21:59:47 EST 2025 Sat Jun 01 15:41:40 EDT 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Quantitative susceptibility mapping Implicit neural representation Unsupervised learning Phase compensation |
| Language | English |
| License | Copyright © 2024 Elsevier B.V. All rights reserved. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c359t-7d79a70edc4e8afab13f80b4c90f28a66e645661300bfbc8e3dcc979a7333c883 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-9060-4152 0000-0002-5910-1506 0000-0001-8260-0437 0000-0001-8816-4832 0000-0002-4428-2316 0000-0002-2047-5041 0009-0001-7682-0879 0000-0001-9773-7348 0000-0002-7734-902X |
| PMID | 38657424 |
| PQID | 3046516127 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_3046516127 pubmed_primary_38657424 crossref_citationtrail_10_1016_j_media_2024_103173 crossref_primary_10_1016_j_media_2024_103173 elsevier_sciencedirect_doi_10_1016_j_media_2024_103173 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-07-01 |
| PublicationDateYYYYMMDD | 2024-07-01 |
| PublicationDate_xml | – month: 07 year: 2024 text: 2024-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Netherlands |
| PublicationPlace_xml | – name: Netherlands |
| PublicationTitle | Medical image analysis |
| PublicationTitleAlternate | Med Image Anal |
| PublicationYear | 2024 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Cognolato, O'Brien, Jin, Robinson, Laun, Barth, Bollmann (bib0008) 2023; 84 Li, Wu, Liu (bib0021) 2011; 55 Wu, Li, Sun, Zhou, Wei, Yu, Zhang (bib0053) 2023; 27 Mildenhall, Srinivasan, Tancik, Barron, Ramamoorthi, Ng (bib0030) 2021; 65 Yoon, Gong, Chatnuntawech, Bilgic, Lee, Jung, Ko, Jung, Setsompop, Zaharchuk, Kim, Pauly, Lee (bib0055) 2018; 179 Li, Vikram, Lim, Jones, Farrell, van Zijl (bib0022) 2012; 62 Shi, Feng, Li, Zhuang, Zhang, Wei (bib0039) 2022; 261 Sun, Ma, MacDonald, Pike (bib0044) 2018; 179 Wang, Liu (bib0048) 2015; 73 Zivadinov, Tavazzi, Bergsland, Hagemeier, Lin, Dwyer, Carl, Kolb, Hojnacki, Ramasamy, Durfee, Weinstock-Guttman, Schweser (bib0059) 2018; 289 Marques, Meineke, Milovic, Bilgic, Chan, Hedouin, van der Zwaag, Langkammer, Schweser (bib0028) 2021; 86 Thomas, Leyland, Schrag, Lees, Acosta-Cabronero, Weil (bib0047) 2020; 91 Bilgic, Pfefferbaum, Rohlfing, Sullivan, Adalsteinsson (bib0004) 2012; 59 Koch, Papademetris, Rothman, de Graaf (bib0017) 2006; 51 Li, Feng, Liu, Feng, Lao, Zhang, Li, Zhang, Wei (bib0023) 2023; 274 Wu, Li, Guidon, Liu (bib0051) 2012; 67 Slavkova, DiCarlo, Wadhwa, Kumar, Wu, Virostko, Yankeelov, Tamir (bib0042) 2022; 89 Micikevicius, Narang, Alben, Diamos, Elsen, Garcia, Ginsburg, Houston, Kuchaiev, Venkatesh (bib0029) 2017 Li, Wang, Yu, Han, Cao, Romero, Tantiwongkosi, Duong, Liu (bib0020) 2015; 108 Shen, Pauly, Xing (bib0038) 2024; 35 Zhang, Shi, Wei, Han, Zhu, Liu (bib0057) 2019; 185 Oh, Bae, Ahn, Park, Moon, Ye (bib0035) 2022; 79 Bilgic, Fan, Polimeni, Cauley, Bianciardi, Adalsteinsson, Wald, Setsompop (bib0003) 2014; 72 Wu, Feng, Wei, Yu, Zhang (bib0052) 2023; 9 Feng, Zhao, Wang, Yang, Feng, Shi, Zhang, Liu, Zhang, Zhuang, Wei (bib0011) 2021; 240 Jung, Bollmann, Lee (bib0015) 2020 Lai, Aggarwal, van Zijl, Li, Sulam (bib0018) 2020 Zhu, Cheng, Cui, Zhu, Ying, Liang (bib0058) 2023; 40 Zalbagi Darestani, Heckel (bib0056) 2021; 7 Smith (bib0043) 2002; 17 Sun, Liu, Xie, Wohlberg, Kamilov (bib0045) 2021; 7 Bollmann, Rasmussen, Kristensen, Blendal, Ostergaard, Plocharski, O'Brien, Langkammer, Janke, Barth (bib0005) 2019; 195 Müller, Evans, Schied, Keller (bib0034) 2022; 41 Acosta-Cabronero, Cardenas-Blanco, Betts, Butryn, Valdes-Herrera, Galazky, Nestor (bib0001) 2017; 140 Langkammer, Schweser, Shmueli, Kames, Li, Guo, Milovic, Kim, Wei, Bredies, Buch, Guo, Liu, Meineke, Rauscher, Marques, Bilgic (bib0019) 2018; 79 Tancik, Srinivasan, Mildenhall, Fridovich-Keil, Raghavan, Singhal, Ramamoorthi, Barron, Ng (bib0046) 2020; 33 Milovic, Bilgic, Zhao, Acosta-Cabronero, Tejos (bib0031) 2018; 80 Xu, Moyer, Gagoski, Iglesias, Ellen Grant, Adalsteinsson (bib0054) 2023; 42 Wei, Cao, Zhang, Guan, Yan, Yeom, Liu (bib0049) 2019; 202 Sitzmann, Martel, Bergman, Lindell, Wetzstein (bib0041) 2020; 33 Liu, Wei, Gong, Cronin, Dibb, Decker (bib0024) 2015; 1 Liu, Spincemaille, de Rochefort, Kressler, Wang (bib0026) 2009; 61 Milovic, Tejos, Irarrazaval (bib0032) 2019 Fang, Lai, van Zijl, Li, Sulam (bib0010) 2023; 87, 102829 Shmueli, de Zwart, van Gelderen, Li, Dodd, Duyn (bib0040) 2009; 62 Chen, Liu, Wang (bib0007) 2021 Huber, Mueller, Heubes (bib0013) 1985; 145 Marques, Bowtell (bib0027) 2005 Bilgic, Langkammer, Marques, Meineke, Milovic, Schweser (bib0009) 2021; 86 Schofield, Zhu (bib0037) 2003; 28 Wei, Dibb, Zhou, Sun, Xu, Wang, Liu (bib0050) 2015; 28 Milovic, Tejos, Irarrazaval, Shmueli (bib0033) 2022 Kames, Doucette, Rauscher (bib0016) 2023; 89 Bao, Xiong, Wei, Chen, van Zijl, Li (bib0002) 2020; 67 Salomir, de Senneville, Moonen (bib0036) 2003 Liu, Koch (bib0025) 2019 Gao, Zhu, Moffat, Glarin, Wilman, Pike, Crozier, Liu, Sun (bib0012) 2021; 34 Chatnuntawech, McDaniel, Cauley, Gagoski, Langkammer, Martin, Grant, Wald, Setsompop, Adalsteinsson, Bilgic (bib0006) 2017; 30 Jenkinson, Smith (bib0014) 2001; 5 Jung (10.1016/j.media.2024.103173_bib0015) 2020 Milovic (10.1016/j.media.2024.103173_bib0031) 2018; 80 Bilgic (10.1016/j.media.2024.103173_bib0003) 2014; 72 Chen (10.1016/j.media.2024.103173_bib0007) 2021 Li (10.1016/j.media.2024.103173_bib0023) 2023; 274 Liu (10.1016/j.media.2024.103173_bib0025) 2019 Wu (10.1016/j.media.2024.103173_bib0053) 2023; 27 Sitzmann (10.1016/j.media.2024.103173_bib0041) 2020; 33 Liu (10.1016/j.media.2024.103173_bib0024) 2015; 1 Marques (10.1016/j.media.2024.103173_bib0027) 2005 Wu (10.1016/j.media.2024.103173_bib0051) 2012; 67 Acosta-Cabronero (10.1016/j.media.2024.103173_bib0001) 2017; 140 Zhang (10.1016/j.media.2024.103173_bib0057) 2019; 185 Shi (10.1016/j.media.2024.103173_bib0039) 2022; 261 Slavkova (10.1016/j.media.2024.103173_bib0042) 2022; 89 Feng (10.1016/j.media.2024.103173_bib0011) 2021; 240 Wang (10.1016/j.media.2024.103173_bib0048) 2015; 73 Schofield (10.1016/j.media.2024.103173_bib0037) 2003; 28 Zalbagi Darestani (10.1016/j.media.2024.103173_bib0056) 2021; 7 Cognolato (10.1016/j.media.2024.103173_bib0008) 2023; 84 Gao (10.1016/j.media.2024.103173_bib0012) 2021; 34 Milovic (10.1016/j.media.2024.103173_bib0032) 2019 Müller (10.1016/j.media.2024.103173_bib0034) 2022; 41 Sun (10.1016/j.media.2024.103173_bib0045) 2021; 7 Zivadinov (10.1016/j.media.2024.103173_bib0059) 2018; 289 Liu (10.1016/j.media.2024.103173_bib0026) 2009; 61 Bilgic (10.1016/j.media.2024.103173_bib0004) 2012; 59 Zhu (10.1016/j.media.2024.103173_bib0058) 2023; 40 Wei (10.1016/j.media.2024.103173_bib0050) 2015; 28 Langkammer (10.1016/j.media.2024.103173_bib0019) 2018; 79 Marques (10.1016/j.media.2024.103173_bib0028) 2021; 86 Salomir (10.1016/j.media.2024.103173_bib0036) 2003 Wu (10.1016/j.media.2024.103173_bib0052) 2023; 9 Jenkinson (10.1016/j.media.2024.103173_bib0014) 2001; 5 Li (10.1016/j.media.2024.103173_bib0021) 2011; 55 Kames (10.1016/j.media.2024.103173_bib0016) 2023; 89 Sun (10.1016/j.media.2024.103173_bib0044) 2018; 179 Li (10.1016/j.media.2024.103173_bib0022) 2012; 62 Mildenhall (10.1016/j.media.2024.103173_bib0030) 2021; 65 Bilgic (10.1016/j.media.2024.103173_bib0009) 2021; 86 Yoon (10.1016/j.media.2024.103173_bib0055) 2018; 179 Oh (10.1016/j.media.2024.103173_bib0035) 2022; 79 Lai (10.1016/j.media.2024.103173_bib0018) 2020 Smith (10.1016/j.media.2024.103173_bib0043) 2002; 17 Xu (10.1016/j.media.2024.103173_bib0054) 2023; 42 Wei (10.1016/j.media.2024.103173_bib0049) 2019; 202 Milovic (10.1016/j.media.2024.103173_bib0033) 2022 Bollmann (10.1016/j.media.2024.103173_bib0005) 2019; 195 Bao (10.1016/j.media.2024.103173_bib0002) 2020; 67 Li (10.1016/j.media.2024.103173_bib0020) 2015; 108 Tancik (10.1016/j.media.2024.103173_bib0046) 2020; 33 Koch (10.1016/j.media.2024.103173_bib0017) 2006; 51 Huber (10.1016/j.media.2024.103173_bib0013) 1985; 145 Thomas (10.1016/j.media.2024.103173_bib0047) 2020; 91 Shmueli (10.1016/j.media.2024.103173_bib0040) 2009; 62 Micikevicius (10.1016/j.media.2024.103173_bib0029) 2017 Shen (10.1016/j.media.2024.103173_bib0038) 2024; 35 Fang (10.1016/j.media.2024.103173_bib0010) 2023; 87, 102829 Chatnuntawech (10.1016/j.media.2024.103173_bib0006) 2017; 30 |
| References_xml | – volume: 5 start-page: 143 year: 2001 end-page: 156 ident: bib0014 article-title: A global optimisation method for robust affine registration of brain images publication-title: Med. Image Anal. – volume: 195 start-page: 373 year: 2019 end-page: 383 ident: bib0005 article-title: DeepQSM - using deep learning to solve the dipole inversion for quantitative susceptibility mapping publication-title: Neuroimage – volume: 108 start-page: 111 year: 2015 end-page: 122 ident: bib0020 article-title: A method for estimating and removing streaking artifacts in quantitative susceptibility mapping publication-title: Neuroimage – volume: 67 year: 2020 ident: bib0002 article-title: Diffusion-regularized susceptibility tensor imaging (DRSTI) of tissue microstructures in the human brain publication-title: Med. Image Anal. – volume: 261 year: 2022 ident: bib0039 article-title: Towards publication-title: Neuroimage – volume: 33 start-page: 7537 year: 2020 end-page: 7547 ident: bib0046 article-title: Fourier features let networks learn high frequency functions in low dimensional domains publication-title: Adv. Neural Inf. Process. Syst. – year: 2017 ident: bib0029 article-title: Mixed Precision Training – volume: 145 start-page: 843 year: 1985 end-page: 846 ident: bib0013 article-title: Oblique magnetic resonance imaging of normal structures publication-title: Am. J. Roentgenol. – volume: 62 start-page: 1510 year: 2009 end-page: 1522 ident: bib0040 article-title: Magnetic susceptibility mapping of brain tissue publication-title: Magn. Reson. Med. – year: 2019 ident: bib0025 article-title: Meta-QSM: an image-resolution-arbitrary network for QSM reconstruction. arXiv preprint arXiv:1908.00206 – volume: 72 start-page: 1444 year: 2014 end-page: 1459 ident: bib0003 article-title: Fast quantitative susceptibility mapping with L1-regularization and automatic parameter selection publication-title: Magn. Reson. Med. – volume: 89 start-page: 2391 year: 2023 end-page: 2401 ident: bib0016 article-title: Multi-echo dipole inversion for magnetic susceptibility mapping publication-title: Magn. Reson. Med. – volume: 33 start-page: 7462 year: 2020 end-page: 7473 ident: bib0041 article-title: Implicit neural representations with periodic activation functions publication-title: Adv. Neural Inf. Process. Syst. – volume: 62 start-page: 314 year: 2012 end-page: 330 ident: bib0022 article-title: Mapping magnetic susceptibility anisotropies of white matter publication-title: Neuroimage – volume: 67 start-page: 137 year: 2012 end-page: 147 ident: bib0051 article-title: Whole brain susceptibility mapping using compressed sensing publication-title: Magn. Reson. Med. – start-page: 65 year: 2005 end-page: 78 ident: bib0027 article-title: Application of a Fourier-based method For Rapid Calculation of Field Inhomogeneity Due to Spatial Variation of Magnetic Susceptibility – volume: 84 year: 2023 ident: bib0008 article-title: NeXtQSM-A complete deep learning pipeline for data-consistent quantitative susceptibility mapping trained with hybrid data publication-title: Med. Image Anal. – volume: 42 start-page: 1707 year: 2023 end-page: 1719 ident: bib0054 article-title: NeSVoR: implicit neural representation for slice-to-volume reconstruction in MRI publication-title: IEEE Trans. Med. Imaging – volume: 202 year: 2019 ident: bib0049 article-title: Learning-based single-step quantitative susceptibility mapping reconstruction without brain extraction publication-title: Neuroimage – volume: 289 start-page: 487 year: 2018 end-page: 496 ident: bib0059 article-title: Brain iron at quantitative mri is associated with disability in multiple sclerosis publication-title: Radiology – volume: 86 start-page: 1241 year: 2021 end-page: 1255 ident: bib0009 article-title: QSM reconstruction challenge 2.0: design and report of results publication-title: Magn. Reson. Med. – volume: 40 start-page: 116 year: 2023 end-page: 128 ident: bib0058 article-title: Physics-driven deep learning methods for fast quantitative magnetic resonance imaging: performance improvements through integration with deep neural networks publication-title: IEEE Signal. Process. Mag. – volume: 87, 102829 year: 2023 ident: bib0010 article-title: DeepSTI: towards tensor reconstruction using fewer orientations in susceptibility tensor imaging publication-title: Med. Image Anal. – volume: 86 start-page: 526 year: 2021 end-page: 542 ident: bib0028 article-title: QSM reconstruction challenge 2.0: a realistic in silico head phantom for MRI data simulation and evaluation of susceptibility mapping procedures publication-title: Magn. Reson. Med. – volume: 79 year: 2022 ident: bib0035 article-title: Unsupervised resolution-agnostic quantitative susceptibility mapping using adaptive instance normalization publication-title: Med. Image Anal. – volume: 7 start-page: 724 year: 2021 end-page: 733 ident: bib0056 article-title: Accelerated MRI with un-trained neural networks publication-title: IEEE Trans. Comput. Imaging – volume: 185 start-page: 349 year: 2019 end-page: 360 ident: bib0057 article-title: Neonate and infant brain development from birth to 2 years assessed using MRI-based quantitative susceptibility mapping publication-title: Neuroimage – year: 2022 ident: bib0033 publication-title: XSIM, a Susceptibility-Optimised Similarity Index Metric: Validation with 2016 and 2019 QSM Reconstruction Challenge Datasets, In: Joint Annual Meeting ISMRM-ESMRMB & ISMRT 31st Annual Meeting – volume: 28 start-page: 1194 year: 2003 end-page: 1196 ident: bib0037 article-title: Fast phase unwrapping algorithm for interferometric applications publication-title: Opt. Lett. – volume: 73 start-page: 82 year: 2015 end-page: 101 ident: bib0048 article-title: Quantitative susceptibility mapping (QSM): decoding MRI data for a tissue magnetic biomarker publication-title: Magn. Reson. Med. – volume: 17 start-page: 143 year: 2002 end-page: 155 ident: bib0043 article-title: Fast robust automated brain extraction publication-title: Hum. Brain Mapp. – volume: 28 start-page: 1294 year: 2015 end-page: 1303 ident: bib0050 article-title: Streaking artifact reduction for quantitative susceptibility mapping of sources with large dynamic range publication-title: NMR Biomed. – volume: 274 year: 2023 ident: bib0023 article-title: APART-QSM: an improved sub-voxel quantitative susceptibility mapping for susceptibility source separation using an iterative data fitting method publication-title: Neuroimage – volume: 7 start-page: 1400 year: 2021 end-page: 1412 ident: bib0045 article-title: CoIL: coordinate-based internal learning for tomographic imaging publication-title: IEEE Trans. Comput. Imaging – volume: 30 start-page: e3570 year: 2017 ident: bib0006 article-title: Single-step quantitative susceptibility mapping with variational penalties publication-title: NMR Biomed. – start-page: 8628 year: 2021 end-page: 8638 ident: bib0007 article-title: Learning continuous image representation with local implicit image function publication-title: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition – volume: 89 start-page: 1617 year: 2022 end-page: 1633 ident: bib0042 article-title: An untrained deep learning method for reconstructing dynamic MR images from accelerated model-based data publication-title: Magn. Reson. Med. – volume: 140 start-page: 118 year: 2017 end-page: 131 ident: bib0001 article-title: The whole-brain pattern of magnetic susceptibility perturbations in Parkinson's disease publication-title: Brain – volume: 179 start-page: 199 year: 2018 end-page: 206 ident: bib0055 article-title: Quantitative susceptibility mapping using deep neural network: QSMnet publication-title: Neuroimage – volume: 34 start-page: e4461 year: 2021 ident: bib0012 article-title: xQSM: quantitative susceptibility mapping with octave convolutional and noise-regularized neural networks publication-title: NMR Biomed. – volume: 35 start-page: 770 year: 2024 end-page: 782 ident: bib0038 article-title: NeRP: implicit neural representation learning with prior embedding for sparsely sampled image reconstruction publication-title: IEEE Trans. Neural Netw. Learn. – start-page: pp 125 year: 2020 end-page: 135 ident: bib0018 article-title: Learned proximal networks for quantitative susceptibility mapping publication-title: In: International Conference on Medical Image Computing and Computer-Assisted Intervention. – volume: 27 start-page: 1004 year: 2023 end-page: 1015 ident: bib0053 article-title: An arbitrary scale super-resolution approach for 3D MR images via implicit neural representation publication-title: IEEE J. Biomed. Health Inform. – volume: 9 start-page: 517 year: 2023 end-page: 529 ident: bib0052 article-title: Self-supervised coordinate projection network for sparse-view computed tomography publication-title: IEEE Trans. Comput. Imaging – start-page: 26 year: 2003 end-page: 34 ident: bib0036 article-title: A Fast Calculation Method For Magnetic Field Inhomogeneity Due to an Arbitrary Distribution of Bulk Susceptibility – volume: 41 start-page: 1 year: 2022 end-page: 15 ident: bib0034 article-title: Instant neural graphics primitives with a multiresolution hash encoding publication-title: ACM Trans. Graph. – volume: 1 start-page: 3 year: 2015 end-page: 17 ident: bib0024 article-title: Quantitative susceptibility mapping: contrast mechanisms and clinical applications publication-title: Tomography – volume: 179 start-page: 166 year: 2018 end-page: 175 ident: bib0044 article-title: Whole head quantitative susceptibility mapping using a least-norm direct dipole inversion method publication-title: Neuroimage – volume: 65 start-page: 99 year: 2021 end-page: 106 ident: bib0030 article-title: NeRF: representing scenes as neural radiance fields for view synthesis publication-title: Commun. ACM – volume: 79 start-page: 1661 year: 2018 end-page: 1673 ident: bib0019 article-title: Quantitative susceptibility mapping: report from the 2016 reconstruction challenge publication-title: Magn. Reson. Med. – year: 2019 ident: bib0032 article-title: Structural similarity index metric setup for QSM applications (XSIM) publication-title: 5th International Workshop on MRI Phase Contrast & Quantitative Susceptibility Mapping – volume: 80 start-page: 814 year: 2018 end-page: 821 ident: bib0031 article-title: Fast nonlinear susceptibility inversion with variational regularization publication-title: Magn. Reson. Med. – volume: 61 start-page: 196 year: 2009 end-page: 204 ident: bib0026 article-title: Calculation of susceptibility through multiple orientation sampling (COSMOS): a method for conditioning the inverse problem from measured magnetic field map to susceptibility source image in MRI publication-title: Magn. Reson. Med. – volume: 91 start-page: 418 year: 2020 end-page: 425 ident: bib0047 article-title: Brain iron deposition is linked with cognitive severity in Parkinson's disease publication-title: J. Neurol. Neurosurg. Psychiatry – volume: 59 start-page: 2625 year: 2012 end-page: 2635 ident: bib0004 article-title: MRI estimates of brain iron concentration in normal aging using quantitative susceptibility mapping publication-title: Neuroimage – start-page: e4292 year: 2020 ident: bib0015 article-title: Overview of quantitative susceptibility mapping using deep learning: current status, challenges and opportunities publication-title: NMR Biomed. – volume: 240 year: 2021 ident: bib0011 article-title: MoDL-QSM: model-based deep learning for quantitative susceptibility mapping publication-title: Neuroimage – volume: 51 start-page: 6381 year: 2006 end-page: 6402 ident: bib0017 article-title: Rapid calculations of susceptibility-induced magnetostatic field perturbations for publication-title: Phys. Med. Biol. – volume: 55 start-page: 1645 year: 2011 end-page: 1656 ident: bib0021 article-title: Quantitative susceptibility mapping of human brain reflects spatial variation in tissue composition publication-title: Neuroimage – volume: 65 start-page: 99 year: 2021 ident: 10.1016/j.media.2024.103173_bib0030 article-title: NeRF: representing scenes as neural radiance fields for view synthesis publication-title: Commun. ACM doi: 10.1145/3503250 – volume: 289 start-page: 487 year: 2018 ident: 10.1016/j.media.2024.103173_bib0059 article-title: Brain iron at quantitative mri is associated with disability in multiple sclerosis publication-title: Radiology doi: 10.1148/radiol.2018180136 – volume: 7 start-page: 724 year: 2021 ident: 10.1016/j.media.2024.103173_bib0056 article-title: Accelerated MRI with un-trained neural networks publication-title: IEEE Trans. Comput. Imaging doi: 10.1109/TCI.2021.3097596 – volume: 89 start-page: 2391 year: 2023 ident: 10.1016/j.media.2024.103173_bib0016 article-title: Multi-echo dipole inversion for magnetic susceptibility mapping publication-title: Magn. Reson. Med. doi: 10.1002/mrm.29588 – volume: 145 start-page: 843 year: 1985 ident: 10.1016/j.media.2024.103173_bib0013 article-title: Oblique magnetic resonance imaging of normal structures publication-title: Am. J. Roentgenol. doi: 10.2214/ajr.145.4.843 – volume: 62 start-page: 314 year: 2012 ident: 10.1016/j.media.2024.103173_bib0022 article-title: Mapping magnetic susceptibility anisotropies of white matter in vivo in the human brain at 7 T publication-title: Neuroimage doi: 10.1016/j.neuroimage.2012.04.042 – volume: 59 start-page: 2625 year: 2012 ident: 10.1016/j.media.2024.103173_bib0004 article-title: MRI estimates of brain iron concentration in normal aging using quantitative susceptibility mapping publication-title: Neuroimage doi: 10.1016/j.neuroimage.2011.08.077 – volume: 17 start-page: 143 year: 2002 ident: 10.1016/j.media.2024.103173_bib0043 article-title: Fast robust automated brain extraction publication-title: Hum. Brain Mapp. doi: 10.1002/hbm.10062 – start-page: 26 year: 2003 ident: 10.1016/j.media.2024.103173_bib0036 – volume: 41 start-page: 1 year: 2022 ident: 10.1016/j.media.2024.103173_bib0034 article-title: Instant neural graphics primitives with a multiresolution hash encoding publication-title: ACM Trans. Graph. doi: 10.1145/3528223.3530127 – volume: 202 year: 2019 ident: 10.1016/j.media.2024.103173_bib0049 article-title: Learning-based single-step quantitative susceptibility mapping reconstruction without brain extraction publication-title: Neuroimage doi: 10.1016/j.neuroimage.2019.116064 – volume: 84 year: 2023 ident: 10.1016/j.media.2024.103173_bib0008 article-title: NeXtQSM-A complete deep learning pipeline for data-consistent quantitative susceptibility mapping trained with hybrid data publication-title: Med. Image Anal. doi: 10.1016/j.media.2022.102700 – volume: 79 year: 2022 ident: 10.1016/j.media.2024.103173_bib0035 article-title: Unsupervised resolution-agnostic quantitative susceptibility mapping using adaptive instance normalization publication-title: Med. Image Anal. doi: 10.1016/j.media.2022.102477 – volume: 195 start-page: 373 year: 2019 ident: 10.1016/j.media.2024.103173_bib0005 article-title: DeepQSM - using deep learning to solve the dipole inversion for quantitative susceptibility mapping publication-title: Neuroimage doi: 10.1016/j.neuroimage.2019.03.060 – volume: 1 start-page: 3 year: 2015 ident: 10.1016/j.media.2024.103173_bib0024 article-title: Quantitative susceptibility mapping: contrast mechanisms and clinical applications publication-title: Tomography doi: 10.18383/j.tom.2015.00136 – volume: 73 start-page: 82 year: 2015 ident: 10.1016/j.media.2024.103173_bib0048 article-title: Quantitative susceptibility mapping (QSM): decoding MRI data for a tissue magnetic biomarker publication-title: Magn. Reson. Med. doi: 10.1002/mrm.25358 – volume: 87, 102829 year: 2023 ident: 10.1016/j.media.2024.103173_bib0010 article-title: DeepSTI: towards tensor reconstruction using fewer orientations in susceptibility tensor imaging publication-title: Med. Image Anal. – start-page: pp 125 year: 2020 ident: 10.1016/j.media.2024.103173_bib0018 article-title: Learned proximal networks for quantitative susceptibility mapping publication-title: In: International Conference on Medical Image Computing and Computer-Assisted Intervention. – volume: 261 year: 2022 ident: 10.1016/j.media.2024.103173_bib0039 article-title: Towards in vivo ground truth susceptibility for single-orientation deep learning QSM: a multi-orientation gradient-echo MRI dataset publication-title: Neuroimage doi: 10.1016/j.neuroimage.2022.119522 – volume: 33 start-page: 7462 year: 2020 ident: 10.1016/j.media.2024.103173_bib0041 article-title: Implicit neural representations with periodic activation functions publication-title: Adv. Neural Inf. Process. Syst. – volume: 9 start-page: 517 year: 2023 ident: 10.1016/j.media.2024.103173_bib0052 article-title: Self-supervised coordinate projection network for sparse-view computed tomography publication-title: IEEE Trans. Comput. Imaging doi: 10.1109/TCI.2023.3281196 – start-page: 8628 year: 2021 ident: 10.1016/j.media.2024.103173_bib0007 article-title: Learning continuous image representation with local implicit image function – start-page: e4292 year: 2020 ident: 10.1016/j.media.2024.103173_bib0015 article-title: Overview of quantitative susceptibility mapping using deep learning: current status, challenges and opportunities publication-title: NMR Biomed. – volume: 51 start-page: 6381 year: 2006 ident: 10.1016/j.media.2024.103173_bib0017 article-title: Rapid calculations of susceptibility-induced magnetostatic field perturbations for in vivo magnetic resonance publication-title: Phys. Med. Biol. doi: 10.1088/0031-9155/51/24/007 – volume: 72 start-page: 1444 year: 2014 ident: 10.1016/j.media.2024.103173_bib0003 article-title: Fast quantitative susceptibility mapping with L1-regularization and automatic parameter selection publication-title: Magn. Reson. Med. doi: 10.1002/mrm.25029 – volume: 79 start-page: 1661 year: 2018 ident: 10.1016/j.media.2024.103173_bib0019 article-title: Quantitative susceptibility mapping: report from the 2016 reconstruction challenge publication-title: Magn. Reson. Med. doi: 10.1002/mrm.26830 – start-page: 65 year: 2005 ident: 10.1016/j.media.2024.103173_bib0027 – volume: 42 start-page: 1707 year: 2023 ident: 10.1016/j.media.2024.103173_bib0054 article-title: NeSVoR: implicit neural representation for slice-to-volume reconstruction in MRI publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2023.3236216 – volume: 274 year: 2023 ident: 10.1016/j.media.2024.103173_bib0023 article-title: APART-QSM: an improved sub-voxel quantitative susceptibility mapping for susceptibility source separation using an iterative data fitting method publication-title: Neuroimage doi: 10.1016/j.neuroimage.2023.120148 – volume: 86 start-page: 1241 year: 2021 ident: 10.1016/j.media.2024.103173_bib0009 article-title: QSM reconstruction challenge 2.0: design and report of results publication-title: Magn. Reson. Med. doi: 10.1002/mrm.28754 – volume: 62 start-page: 1510 year: 2009 ident: 10.1016/j.media.2024.103173_bib0040 article-title: Magnetic susceptibility mapping of brain tissue in vivo using MRI phase data publication-title: Magn. Reson. Med. doi: 10.1002/mrm.22135 – volume: 86 start-page: 526 year: 2021 ident: 10.1016/j.media.2024.103173_bib0028 article-title: QSM reconstruction challenge 2.0: a realistic in silico head phantom for MRI data simulation and evaluation of susceptibility mapping procedures publication-title: Magn. Reson. Med. doi: 10.1002/mrm.28716 – volume: 89 start-page: 1617 year: 2022 ident: 10.1016/j.media.2024.103173_bib0042 article-title: An untrained deep learning method for reconstructing dynamic MR images from accelerated model-based data publication-title: Magn. Reson. Med. doi: 10.1002/mrm.29547 – volume: 33 start-page: 7537 year: 2020 ident: 10.1016/j.media.2024.103173_bib0046 article-title: Fourier features let networks learn high frequency functions in low dimensional domains publication-title: Adv. Neural Inf. Process. Syst. – volume: 67 year: 2020 ident: 10.1016/j.media.2024.103173_bib0002 article-title: Diffusion-regularized susceptibility tensor imaging (DRSTI) of tissue microstructures in the human brain publication-title: Med. Image Anal. – volume: 30 start-page: e3570 year: 2017 ident: 10.1016/j.media.2024.103173_bib0006 article-title: Single-step quantitative susceptibility mapping with variational penalties publication-title: NMR Biomed. doi: 10.1002/nbm.3570 – volume: 240 year: 2021 ident: 10.1016/j.media.2024.103173_bib0011 article-title: MoDL-QSM: model-based deep learning for quantitative susceptibility mapping publication-title: Neuroimage doi: 10.1016/j.neuroimage.2021.118376 – volume: 28 start-page: 1294 year: 2015 ident: 10.1016/j.media.2024.103173_bib0050 article-title: Streaking artifact reduction for quantitative susceptibility mapping of sources with large dynamic range publication-title: NMR Biomed. doi: 10.1002/nbm.3383 – volume: 108 start-page: 111 year: 2015 ident: 10.1016/j.media.2024.103173_bib0020 article-title: A method for estimating and removing streaking artifacts in quantitative susceptibility mapping publication-title: Neuroimage doi: 10.1016/j.neuroimage.2014.12.043 – volume: 140 start-page: 118 year: 2017 ident: 10.1016/j.media.2024.103173_bib0001 article-title: The whole-brain pattern of magnetic susceptibility perturbations in Parkinson's disease publication-title: Brain doi: 10.1093/brain/aww278 – volume: 61 start-page: 196 year: 2009 ident: 10.1016/j.media.2024.103173_bib0026 article-title: Calculation of susceptibility through multiple orientation sampling (COSMOS): a method for conditioning the inverse problem from measured magnetic field map to susceptibility source image in MRI publication-title: Magn. Reson. Med. doi: 10.1002/mrm.21828 – volume: 179 start-page: 166 year: 2018 ident: 10.1016/j.media.2024.103173_bib0044 article-title: Whole head quantitative susceptibility mapping using a least-norm direct dipole inversion method publication-title: Neuroimage doi: 10.1016/j.neuroimage.2018.06.036 – volume: 27 start-page: 1004 year: 2023 ident: 10.1016/j.media.2024.103173_bib0053 article-title: An arbitrary scale super-resolution approach for 3D MR images via implicit neural representation publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2022.3223106 – volume: 40 start-page: 116 year: 2023 ident: 10.1016/j.media.2024.103173_bib0058 article-title: Physics-driven deep learning methods for fast quantitative magnetic resonance imaging: performance improvements through integration with deep neural networks publication-title: IEEE Signal. Process. Mag. doi: 10.1109/MSP.2023.3236483 – volume: 67 start-page: 137 year: 2012 ident: 10.1016/j.media.2024.103173_bib0051 article-title: Whole brain susceptibility mapping using compressed sensing publication-title: Magn. Reson. Med. doi: 10.1002/mrm.23000 – volume: 185 start-page: 349 year: 2019 ident: 10.1016/j.media.2024.103173_bib0057 article-title: Neonate and infant brain development from birth to 2 years assessed using MRI-based quantitative susceptibility mapping publication-title: Neuroimage doi: 10.1016/j.neuroimage.2018.10.031 – volume: 80 start-page: 814 year: 2018 ident: 10.1016/j.media.2024.103173_bib0031 article-title: Fast nonlinear susceptibility inversion with variational regularization publication-title: Magn. Reson. Med. doi: 10.1002/mrm.27073 – year: 2019 ident: 10.1016/j.media.2024.103173_bib0032 article-title: Structural similarity index metric setup for QSM applications (XSIM) – year: 2019 ident: 10.1016/j.media.2024.103173_bib0025 – volume: 28 start-page: 1194 year: 2003 ident: 10.1016/j.media.2024.103173_bib0037 article-title: Fast phase unwrapping algorithm for interferometric applications publication-title: Opt. Lett. doi: 10.1364/OL.28.001194 – volume: 35 start-page: 770 year: 2024 ident: 10.1016/j.media.2024.103173_bib0038 article-title: NeRP: implicit neural representation learning with prior embedding for sparsely sampled image reconstruction publication-title: IEEE Trans. Neural Netw. Learn. doi: 10.1109/TNNLS.2022.3177134 – volume: 5 start-page: 143 year: 2001 ident: 10.1016/j.media.2024.103173_bib0014 article-title: A global optimisation method for robust affine registration of brain images publication-title: Med. Image Anal. doi: 10.1016/S1361-8415(01)00036-6 – volume: 34 start-page: e4461 year: 2021 ident: 10.1016/j.media.2024.103173_bib0012 article-title: xQSM: quantitative susceptibility mapping with octave convolutional and noise-regularized neural networks publication-title: NMR Biomed. doi: 10.1002/nbm.4461 – volume: 179 start-page: 199 year: 2018 ident: 10.1016/j.media.2024.103173_bib0055 article-title: Quantitative susceptibility mapping using deep neural network: QSMnet publication-title: Neuroimage doi: 10.1016/j.neuroimage.2018.06.030 – volume: 91 start-page: 418 year: 2020 ident: 10.1016/j.media.2024.103173_bib0047 article-title: Brain iron deposition is linked with cognitive severity in Parkinson's disease publication-title: J. Neurol. Neurosurg. Psychiatry doi: 10.1136/jnnp-2019-322042 – volume: 7 start-page: 1400 year: 2021 ident: 10.1016/j.media.2024.103173_bib0045 article-title: CoIL: coordinate-based internal learning for tomographic imaging publication-title: IEEE Trans. Comput. Imaging doi: 10.1109/TCI.2021.3125564 – volume: 55 start-page: 1645 year: 2011 ident: 10.1016/j.media.2024.103173_bib0021 article-title: Quantitative susceptibility mapping of human brain reflects spatial variation in tissue composition publication-title: Neuroimage doi: 10.1016/j.neuroimage.2010.11.088 – year: 2022 ident: 10.1016/j.media.2024.103173_bib0033 – year: 2017 ident: 10.1016/j.media.2024.103173_bib0029 |
| SSID | ssj0007440 |
| Score | 2.4540868 |
| Snippet | •Subject-specific and unsupervised deep learning for QSM reconstruction.•Integration of implicit continuous signal representation and explicit... Quantitative susceptibility mapping (QSM) is an MRI-based technique that estimates the underlying tissue magnetic susceptibility based on phase signal. Deep... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 103173 |
| SubjectTerms | Implicit neural representation Phase compensation Quantitative susceptibility mapping Unsupervised learning |
| Title | A subject-specific unsupervised deep learning method for quantitative susceptibility mapping using implicit neural representation |
| URI | https://dx.doi.org/10.1016/j.media.2024.103173 https://www.ncbi.nlm.nih.gov/pubmed/38657424 https://www.proquest.com/docview/3046516127 |
| Volume | 95 |
| WOSCitedRecordID | wos001220917700001&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: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1361-8423 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0007440 issn: 1361-8415 databaseCode: AIEXJ dateStart: 20161201 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELe6DSF4QDA-Vj4mI_FWUqWxE9uPFRqCiU0IDaniJbIdh3Xa0mxppvHI_8AfjD_iNG21ij3wElWufbJ6v96dnd_dAfBOMk4lymWgYn02wYKrgONcBNpZh0IhljNpq-t_IcfHdDJhX3u9Pz4X5vqcFAW9uWHlf1W1HtPKNqmzd1B3K1QP6M9a6fqp1a6f_6T48aCqhbldCUwWpWECDeqiqktjFCodXmZKlb5ZxM-mg7QlG17WvLApZ4ZMVNWVJbxY7uyvwQUvbWJVba8WppaGPp0PTDVM2xmgXGQxFd14178Hml4YbhBvKqCs3VYfeQdqg1I39q02DcdawpBlHfw41V-e8tnq3MOp6l5fRLilunqLi5JRQLHL6fQmmcUdm2oaUbh2J2vm3t08nA1tls3QiB8uZi8X115xei0V0bPczlIrJDVCUidkC-xEJGbaVu6MPx9MDlsPb4oqunw-t3VfzcryBtf2clvEc9uJxkY2J4_Bo-ZIAscOSk9ATxW74GGnUOUuuH_UUDCegt9juIov2MUXNPiCHl_Q4QtqfMEuvuAyvmCDL2jxBT2-oMMXXMbXM_D948HJh09B08cjkChm84BkhHESqkxiRXnOxQjlNBRYsjCPKE8Slegw3hxkQ5ELSRXKpGRmDUJIUoqeg-1iVqg9AGORk1BkgoyiDMdEiTgLY8FjzHjCtf_pg8j_1qlsitybXivn6QY998H7dlHparxsnp54JaZNmOrCz1TDcvPCt17lqTbi5s0cL9SsrlJDT4j12SsiffDCYaHdiWnKS3CEX95tl6_Ag8Xf7TXYnl_V6g24J6_n0-pqH2yRCd1vcP0XMhjRAA |
| 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=A+subject-specific+unsupervised+deep+learning+method+for+quantitative+susceptibility+mapping+using+implicit+neural+representation&rft.jtitle=Medical+image+analysis&rft.au=Zhang%2C+Ming&rft.au=Feng%2C+Ruimin&rft.au=Li%2C+Zhenghao&rft.au=Feng%2C+Jie&rft.date=2024-07-01&rft.issn=1361-8415&rft.volume=95&rft.spage=103173&rft_id=info:doi/10.1016%2Fj.media.2024.103173&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_media_2024_103173 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1361-8415&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1361-8415&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1361-8415&client=summon |