View in EDS HTML Full Text PDF Full Text

Suppression of artifact‐generating echoes in cine DENSE using deep learning.

Saved in:
Bibliographic Details
Title: Suppression of artifact‐generating echoes in cine DENSE using deep learning.
Authors: Abdi, Mohamad1 (AUTHOR), Feng, Xue1 (AUTHOR), Sun, Changyu1 (AUTHOR), Bilchick, Kenneth C.2 (AUTHOR), Meyer, Craig H.1,3 (AUTHOR), Epstein, Frederick H.1,3 (AUTHOR) fredepstein@virginia.edu
Source: Magnetic Resonance in Medicine. Oct2021, Vol. 86 Issue 4, p2095-2104. 10p.
Subjects: Deep learning, Echo suppression, Standard deviations, Sonar, Root-mean-squares
Abstract: Purpose: To use deep learning for suppression of the artifact‐generating T1‐relaxation echo in cine displacement encoding with stimulated echoes (DENSE) for the purpose of reducing the scan time. Methods: A U‐Net was trained to suppress the artifact‐generating T1‐relaxation echo using complementary phase‐cycled data as the ground truth. A data‐augmentation method was developed that generates synthetic DENSE images with arbitrary displacement‐encoding frequencies to suppress the T1‐relaxation echo modulated for a range of frequencies. The resulting U‐Net (DAS‐Net) was compared with k‐space zero‐filling as an alternative method. Non‐phase‐cycled DENSE images acquired in shorter breath‐holds were processed by DAS‐Net and compared with DENSE images acquired with phase cycling for the quantification of myocardial strain. Results: The DAS‐Net method effectively suppressed the T1‐relaxation echo and its artifacts, and achieved root Mean Square(RMS) error = 5.5 ± 0.8 and structural similarity index = 0.85 ± 0.02 for DENSE images acquired with a displacement encoding frequency of 0.10 cycles/mm. The DAS‐Net method outperformed zero‐filling (root Mean Square error = 5.8 ± 1.5 vs 13.5 ± 1.5, DAS‐Net vs zero‐filling, P <.01; and structural similarity index = 0.83 ± 0.04 vs 0.66 ± 0.03, DAS‐Net vs zero‐filling, P <.01). Strain data for non‐phase‐cycled DENSE images with DAS‐Net showed close agreement with strain from phase‐cycled DENSE. Conclusion: The DAS‐Net method provides an effective alternative approach for suppression of the artifact‐generating T1‐relaxation echo in DENSE MRI, enabling a 42% reduction in scan time compared to DENSE with phase‐cycling. [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
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 151570114
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Suppression of artifact‐generating echoes in cine DENSE using deep learning.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Abdi%2C+Mohamad%22&quot;&gt;Abdi, Mohamad&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Feng%2C+Xue%22&quot;&gt;Feng, Xue&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Sun%2C+Changyu%22&quot;&gt;Sun, Changyu&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Bilchick%2C+Kenneth+C%2E%22&quot;&gt;Bilchick, Kenneth C.&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Meyer%2C+Craig+H%2E%22&quot;&gt;Meyer, Craig H.&lt;/searchLink&gt;&lt;relatesTo&gt;1,3&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Epstein%2C+Frederick+H%2E%22&quot;&gt;Epstein, Frederick H.&lt;/searchLink&gt;&lt;relatesTo&gt;1,3&lt;/relatesTo&gt; (AUTHOR)&lt;i&gt; fredepstein@virginia.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;. Oct2021, Vol. 86 Issue 4, p2095-2104. 10p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Deep+learning%22&quot;&gt;Deep learning&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Echo+suppression%22&quot;&gt;Echo suppression&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Standard+deviations%22&quot;&gt;Standard deviations&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Sonar%22&quot;&gt;Sonar&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Root-mean-squares%22&quot;&gt;Root-mean-squares&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Purpose: To use deep learning for suppression of the artifact‐generating T1‐relaxation echo in cine displacement encoding with stimulated echoes (DENSE) for the purpose of reducing the scan time. Methods: A U‐Net was trained to suppress the artifact‐generating T1‐relaxation echo using complementary phase‐cycled data as the ground truth. A data‐augmentation method was developed that generates synthetic DENSE images with arbitrary displacement‐encoding frequencies to suppress the T1‐relaxation echo modulated for a range of frequencies. The resulting U‐Net (DAS‐Net) was compared with k‐space zero‐filling as an alternative method. Non‐phase‐cycled DENSE images acquired in shorter breath‐holds were processed by DAS‐Net and compared with DENSE images acquired with phase cycling for the quantification of myocardial strain. Results: The DAS‐Net method effectively suppressed the T1‐relaxation echo and its artifacts, and achieved root Mean Square(RMS) error = 5.5 &#177; 0.8 and structural similarity index = 0.85 &#177; 0.02 for DENSE images acquired with a displacement encoding frequency of 0.10 cycles/mm. The DAS‐Net method outperformed zero‐filling (root Mean Square error = 5.8 &#177; 1.5 vs 13.5 &#177; 1.5, DAS‐Net vs zero‐filling, P &lt;.01; and structural similarity index = 0.83 &#177; 0.04 vs 0.66 &#177; 0.03, DAS‐Net vs zero‐filling, P &lt;.01). Strain data for non‐phase‐cycled DENSE images with DAS‐Net showed close agreement with strain from phase‐cycled DENSE. Conclusion: The DAS‐Net method provides an effective alternative approach for suppression of the artifact‐generating T1‐relaxation echo in DENSE MRI, enabling a 42% reduction in scan time compared to DENSE with phase‐cycling. [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=151570114
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/mrm.28832
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 10
        StartPage: 2095
    Subjects:
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Echo suppression
        Type: general
      – SubjectFull: Standard deviations
        Type: general
      – SubjectFull: Sonar
        Type: general
      – SubjectFull: Root-mean-squares
        Type: general
    Titles:
      – TitleFull: Suppression of artifact‐generating echoes in cine DENSE using deep learning.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Abdi, Mohamad
      – PersonEntity:
          Name:
            NameFull: Feng, Xue
      – PersonEntity:
          Name:
            NameFull: Sun, Changyu
      – PersonEntity:
          Name:
            NameFull: Bilchick, Kenneth C.
      – PersonEntity:
          Name:
            NameFull: Meyer, Craig H.
      – PersonEntity:
          Name:
            NameFull: Epstein, Frederick H.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: Oct2021
              Type: published
              Y: 2021
          Identifiers:
            – Type: issn-print
              Value: 07403194
          Numbering:
            – Type: volume
              Value: 86
            – Type: issue
              Value: 4
          Titles:
            – TitleFull: Magnetic Resonance in Medicine
              Type: main
ResultId 1