View in EDS

Feasibility of Implicit Neural Representation Learned Motion Compensation for 3D Stack‐of‐Spirals Free‐Breathing Cardiac Quantitative Susceptibility Mapping.

Saved in:
Bibliographic Details
Title: Feasibility of Implicit Neural Representation Learned Motion Compensation for 3D Stack‐of‐Spirals Free‐Breathing Cardiac Quantitative Susceptibility Mapping.
Authors: Li, Jiahao1,2 (AUTHOR), Deng, Angela2,3 (AUTHOR), Li, Chao2,4 (AUTHOR), Villar‐Calle, Pablo5 (AUTHOR), Zhang, Jinwei1,2 (AUTHOR), Dimov, Alexey V.2 (AUTHOR), Kim, Jiwon5 (AUTHOR), Nguyen, Thanh D.2 (AUTHOR), Wang, Yi1,2 (AUTHOR), Weinsaft, Jonathan W.5 (AUTHOR), Spincemaille, Pascal2 (AUTHOR) pas2018@med.cornell.edu
Source: Magnetic Resonance in Medicine. Jul2026, Vol. 96 Issue 1, p227-237. 11p.
Subjects: Motion compensation (Signal processing), Cardiac magnetic resonance imaging, Image reconstruction, Heart function tests, Magnetic susceptibility, Artificial neural networks, Diagnostic imaging
Abstract: Purpose: Differential blood oxygenation between the right and left heart (ΔSO2) is an indicator of cardiovascular function currently assessed in clinical practice by invasive right heart catheterization. Cardiac MRI can non‐invasively quantify ΔSO2 with quantitative susceptibility mapping (QSM) using a prospective navigator gated 3D cartesian acquisition. However, this method suffers from long acquisition time and reduced robustness. Here, a free‐breathing cardiac QSM using spiral sampling and deep learning motion compensation is proposed. Methods: A retrospective self‐gated stack‐of‐spirals multi‐echo gradient echo sequence is combined with implicit neural representation (INR) learning for image reconstruction. The self‐gating signals measure superior–inferior cardiac and respiratory motion thus allowing k‐space binning. Using a physics‐informed signal model and the spatiotemporal coordinate input, INR infers motion fields as well as motion‐corrected water, fat, and field maps. Then, QSM and ΔSO2 are accordingly computed. Data were acquired in 10 healthy subjects. For comparison, a free‐breathing prospective navigator ECG‐triggered Cartesian acquisition (NAV) was performed. Results: INR reconstructed motion‐corrected water, fat, R2* and field maps were successfully obtained in all subjects. INR‐QSM showed superior image quality (p = 0.0067) and equivalent ΔSO2 measurement in the heart (r = 0.74, p < 0.001; 1.07% ± 3.52% bias/limits of agreement) compared to the reference NAV‐QSM. Conclusion: This study demonstrated the feasibility of INR for compensation of cardiac and respiratory motion in free‐breathing 3D cardiac QSM. [ABSTRACT FROM AUTHOR]
Copyright of Magnetic Resonance in Medicine is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 193626812
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Feasibility of Implicit Neural Representation Learned Motion Compensation for 3D Stack‐of‐Spirals Free‐Breathing Cardiac Quantitative Susceptibility Mapping.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Li%2C+Jiahao%22&quot;&gt;Li, Jiahao&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Deng%2C+Angela%22&quot;&gt;Deng, Angela&lt;/searchLink&gt;&lt;relatesTo&gt;2,3&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Li%2C+Chao%22&quot;&gt;Li, Chao&lt;/searchLink&gt;&lt;relatesTo&gt;2,4&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Villar‐Calle%2C+Pablo%22&quot;&gt;Villar‐Calle, Pablo&lt;/searchLink&gt;&lt;relatesTo&gt;5&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Zhang%2C+Jinwei%22&quot;&gt;Zhang, Jinwei&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Dimov%2C+Alexey+V%2E%22&quot;&gt;Dimov, Alexey V.&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Kim%2C+Jiwon%22&quot;&gt;Kim, Jiwon&lt;/searchLink&gt;&lt;relatesTo&gt;5&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Nguyen%2C+Thanh+D%2E%22&quot;&gt;Nguyen, Thanh D.&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Wang%2C+Yi%22&quot;&gt;Wang, Yi&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Weinsaft%2C+Jonathan+W%2E%22&quot;&gt;Weinsaft, Jonathan W.&lt;/searchLink&gt;&lt;relatesTo&gt;5&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Spincemaille%2C+Pascal%22&quot;&gt;Spincemaille, Pascal&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;i&gt; pas2018@med.cornell.edu&lt;/i&gt;
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%22Magnetic+Resonance+in+Medicine%22&quot;&gt;Magnetic Resonance in Medicine&lt;/searchLink&gt;. Jul2026, Vol. 96 Issue 1, p227-237. 11p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Motion+compensation+%28Signal+processing%29%22&quot;&gt;Motion compensation (Signal processing)&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Cardiac+magnetic+resonance+imaging%22&quot;&gt;Cardiac magnetic resonance imaging&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Image+reconstruction%22&quot;&gt;Image reconstruction&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Heart+function+tests%22&quot;&gt;Heart function tests&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Magnetic+susceptibility%22&quot;&gt;Magnetic susceptibility&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Artificial+neural+networks%22&quot;&gt;Artificial neural networks&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Diagnostic+imaging%22&quot;&gt;Diagnostic imaging&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Purpose: Differential blood oxygenation between the right and left heart (ΔSO2) is an indicator of cardiovascular function currently assessed in clinical practice by invasive right heart catheterization. Cardiac MRI can non‐invasively quantify ΔSO2 with quantitative susceptibility mapping (QSM) using a prospective navigator gated 3D cartesian acquisition. However, this method suffers from long acquisition time and reduced robustness. Here, a free‐breathing cardiac QSM using spiral sampling and deep learning motion compensation is proposed. Methods: A retrospective self‐gated stack‐of‐spirals multi‐echo gradient echo sequence is combined with implicit neural representation (INR) learning for image reconstruction. The self‐gating signals measure superior–inferior cardiac and respiratory motion thus allowing k‐space binning. Using a physics‐informed signal model and the spatiotemporal coordinate input, INR infers motion fields as well as motion‐corrected water, fat, and field maps. Then, QSM and ΔSO2 are accordingly computed. Data were acquired in 10 healthy subjects. For comparison, a free‐breathing prospective navigator ECG‐triggered Cartesian acquisition (NAV) was performed. Results: INR reconstructed motion‐corrected water, fat, R2* and field maps were successfully obtained in all subjects. INR‐QSM showed superior image quality (p = 0.0067) and equivalent ΔSO2 measurement in the heart (r = 0.74, p &lt; 0.001; 1.07% &#177; 3.52% bias/limits of agreement) compared to the reference NAV‐QSM. Conclusion: This study demonstrated the feasibility of INR for compensation of cardiac and respiratory motion in free‐breathing 3D cardiac QSM. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: &lt;i&gt;Copyright of Magnetic Resonance in Medicine is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder&#39;s express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.&lt;/i&gt; (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=193626812
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/mrm.70325
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 227
    Subjects:
      – SubjectFull: Motion compensation (Signal processing)
        Type: general
      – SubjectFull: Cardiac magnetic resonance imaging
        Type: general
      – SubjectFull: Image reconstruction
        Type: general
      – SubjectFull: Heart function tests
        Type: general
      – SubjectFull: Magnetic susceptibility
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Diagnostic imaging
        Type: general
    Titles:
      – TitleFull: Feasibility of Implicit Neural Representation Learned Motion Compensation for 3D Stack‐of‐Spirals Free‐Breathing Cardiac Quantitative Susceptibility Mapping.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Li, Jiahao
      – PersonEntity:
          Name:
            NameFull: Deng, Angela
      – PersonEntity:
          Name:
            NameFull: Li, Chao
      – PersonEntity:
          Name:
            NameFull: Villar‐Calle, Pablo
      – PersonEntity:
          Name:
            NameFull: Zhang, Jinwei
      – PersonEntity:
          Name:
            NameFull: Dimov, Alexey V.
      – PersonEntity:
          Name:
            NameFull: Kim, Jiwon
      – PersonEntity:
          Name:
            NameFull: Nguyen, Thanh D.
      – PersonEntity:
          Name:
            NameFull: Wang, Yi
      – PersonEntity:
          Name:
            NameFull: Weinsaft, Jonathan W.
      – PersonEntity:
          Name:
            NameFull: Spincemaille, Pascal
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 07
              Text: Jul2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 07403194
          Numbering:
            – Type: volume
              Value: 96
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Magnetic Resonance in Medicine
              Type: main
ResultId 1