View in EDS HTML Full Text PDF Full Text

Direct synthesis of multi‐contrast brain MR images from MR multitasking spatial factors using deep learning.

Saved in:
Bibliographic Details
Title: Direct synthesis of multi‐contrast brain MR images from MR multitasking spatial factors using deep learning.
Authors: Qiu, Shihan1,2 (AUTHOR), Ma, Sen1 (AUTHOR), Wang, Lixia1 (AUTHOR), Chen, Yuhua1,2 (AUTHOR), Fan, Zhaoyang1,3 (AUTHOR), Moser, Franklin G.4 (AUTHOR), Maya, Marcel4 (AUTHOR), Sati, Pascal1,5 (AUTHOR), Sicotte, Nancy L.5 (AUTHOR), Christodoulou, Anthony G.1,2 (AUTHOR), Xie, Yibin1 (AUTHOR), Li, Debiao1,2 (AUTHOR) debiao.li@cshs.org
Source: Magnetic Resonance in Medicine. Oct2023, Vol. 90 Issue 4, p1672-1681. 10p.
Subjects: Deep learning, Magnetic resonance imaging, Brain imaging, Standard deviations
Abstract: Purpose: To develop a deep learning method to synthesize conventional contrast‐weighted images in the brain from MR multitasking spatial factors. Methods: Eighteen subjects were imaged using a whole‐brain quantitative T1‐T2‐T1ρ MR multitasking sequence. Conventional contrast‐weighted images consisting of T1 MPRAGE, T1 gradient echo, and T2 fluid‐attenuated inversion recovery were acquired as target images. A 2D U‐Net–based neural network was trained to synthesize conventional weighted images from MR multitasking spatial factors. Quantitative assessment and image quality rating by two radiologists were performed to evaluate the quality of deep‐learning–based synthesis, in comparison with Bloch‐equation–based synthesis from MR multitasking quantitative maps. Results: The deep‐learning synthetic images showed comparable contrasts of brain tissues with the reference images from true acquisitions and were substantially better than the Bloch‐equation–based synthesis results. Averaging on the three contrasts, the deep learning synthesis achieved normalized root mean square error = 0.184 ± 0.075, peak SNR = 28.14 ± 2.51, and structural‐similarity index = 0.918 ± 0.034, which were significantly better than Bloch‐equation–based synthesis (p < 0.05). Radiologists' rating results show that compared with true acquisitions, deep learning synthesis had no notable quality degradation and was better than Bloch‐equation–based synthesis. Conclusion: A deep learning technique was developed to synthesize conventional weighted images from MR multitasking spatial factors in the brain, enabling the simultaneous acquisition of multiparametric quantitative maps and clinical contrast‐weighted images in a single scan. [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: 168591168
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Direct synthesis of multi‐contrast brain MR images from MR multitasking spatial factors using deep learning.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Qiu%2C+Shihan%22&quot;&gt;Qiu, Shihan&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Ma%2C+Sen%22&quot;&gt;Ma, Sen&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Wang%2C+Lixia%22&quot;&gt;Wang, Lixia&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Chen%2C+Yuhua%22&quot;&gt;Chen, Yuhua&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Fan%2C+Zhaoyang%22&quot;&gt;Fan, Zhaoyang&lt;/searchLink&gt;&lt;relatesTo&gt;1,3&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Moser%2C+Franklin+G%2E%22&quot;&gt;Moser, Franklin G.&lt;/searchLink&gt;&lt;relatesTo&gt;4&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Maya%2C+Marcel%22&quot;&gt;Maya, Marcel&lt;/searchLink&gt;&lt;relatesTo&gt;4&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Sati%2C+Pascal%22&quot;&gt;Sati, Pascal&lt;/searchLink&gt;&lt;relatesTo&gt;1,5&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Sicotte%2C+Nancy+L%2E%22&quot;&gt;Sicotte, Nancy L.&lt;/searchLink&gt;&lt;relatesTo&gt;5&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Christodoulou%2C+Anthony+G%2E%22&quot;&gt;Christodoulou, Anthony G.&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Xie%2C+Yibin%22&quot;&gt;Xie, Yibin&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Li%2C+Debiao%22&quot;&gt;Li, Debiao&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;i&gt; debiao.li@cshs.org&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;. Oct2023, Vol. 90 Issue 4, p1672-1681. 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;%22Magnetic+resonance+imaging%22&quot;&gt;Magnetic resonance imaging&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Brain+imaging%22&quot;&gt;Brain imaging&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Standard+deviations%22&quot;&gt;Standard deviations&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Purpose: To develop a deep learning method to synthesize conventional contrast‐weighted images in the brain from MR multitasking spatial factors. Methods: Eighteen subjects were imaged using a whole‐brain quantitative T1‐T2‐T1ρ MR multitasking sequence. Conventional contrast‐weighted images consisting of T1 MPRAGE, T1 gradient echo, and T2 fluid‐attenuated inversion recovery were acquired as target images. A 2D U‐Net–based neural network was trained to synthesize conventional weighted images from MR multitasking spatial factors. Quantitative assessment and image quality rating by two radiologists were performed to evaluate the quality of deep‐learning–based synthesis, in comparison with Bloch‐equation–based synthesis from MR multitasking quantitative maps. Results: The deep‐learning synthetic images showed comparable contrasts of brain tissues with the reference images from true acquisitions and were substantially better than the Bloch‐equation–based synthesis results. Averaging on the three contrasts, the deep learning synthesis achieved normalized root mean square error = 0.184 &#177; 0.075, peak SNR = 28.14 &#177; 2.51, and structural‐similarity index = 0.918 &#177; 0.034, which were significantly better than Bloch‐equation–based synthesis (p &lt; 0.05). Radiologists&#39; rating results show that compared with true acquisitions, deep learning synthesis had no notable quality degradation and was better than Bloch‐equation–based synthesis. Conclusion: A deep learning technique was developed to synthesize conventional weighted images from MR multitasking spatial factors in the brain, enabling the simultaneous acquisition of multiparametric quantitative maps and clinical contrast‐weighted images in a single scan. [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=168591168
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/mrm.29715
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 10
        StartPage: 1672
    Subjects:
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Magnetic resonance imaging
        Type: general
      – SubjectFull: Brain imaging
        Type: general
      – SubjectFull: Standard deviations
        Type: general
    Titles:
      – TitleFull: Direct synthesis of multi‐contrast brain MR images from MR multitasking spatial factors using deep learning.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Qiu, Shihan
      – PersonEntity:
          Name:
            NameFull: Ma, Sen
      – PersonEntity:
          Name:
            NameFull: Wang, Lixia
      – PersonEntity:
          Name:
            NameFull: Chen, Yuhua
      – PersonEntity:
          Name:
            NameFull: Fan, Zhaoyang
      – PersonEntity:
          Name:
            NameFull: Moser, Franklin G.
      – PersonEntity:
          Name:
            NameFull: Maya, Marcel
      – PersonEntity:
          Name:
            NameFull: Sati, Pascal
      – PersonEntity:
          Name:
            NameFull: Sicotte, Nancy L.
      – PersonEntity:
          Name:
            NameFull: Christodoulou, Anthony G.
      – PersonEntity:
          Name:
            NameFull: Xie, Yibin
      – PersonEntity:
          Name:
            NameFull: Li, Debiao
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: Oct2023
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-print
              Value: 07403194
          Numbering:
            – Type: volume
              Value: 90
            – Type: issue
              Value: 4
          Titles:
            – TitleFull: Magnetic Resonance in Medicine
              Type: main
ResultId 1