View in EDS HTML Full Text PDF Full Text

Model‐based self‐supervised learning for quantitative assessment of myocardial oxygen extraction fraction and myocardial blood volume.

Saved in:
Bibliographic Details
Title: Model‐based self‐supervised learning for quantitative assessment of myocardial oxygen extraction fraction and myocardial blood volume.
Authors: Huang, Qi1 (AUTHOR), Tang, Haoteng2 (AUTHOR), Wang, Keyan3 (AUTHOR), Li, Ran1 (AUTHOR), Eldeniz, Cihat1 (AUTHOR), Nguyen, Natalie1 (AUTHOR), Schindler, Thomas H.1 (AUTHOR), Peterson, Linda R.1 (AUTHOR), Yang, Yang4 (AUTHOR), Yan, Yan1 (AUTHOR), Cheng, Jingliang3 (AUTHOR), Woodard, Pamela K.1 (AUTHOR), Zheng, Jie1 (AUTHOR) zhengj@wustl.edu
Source: Magnetic Resonance in Medicine. Oct2025, Vol. 94 Issue 4, p1793-1803. 11p.
Subjects: Deep learning, Machine learning, Computer-assisted image analysis (Medicine), In vivo studies, Simulation methods & models, Blood volume
Abstract: Purpose: To develop a model‐driven, self‐supervised deep learning network for end‐to‐end simultaneous mapping of myocardial oxygen extraction fraction (mOEF) and myocardial blood volume (MBV). Methods: An asymmetrical spin echo–prepared sequence was used to acquire mOEF and MBV images. By integrating a physical model into the training process, a self‐supervised learning (SSL) pattern can be regulated. A loss function consisted of the mean squared error, plus cosine similarity was used to improve the performance of network predictions for estimating mOEF and MBV simultaneously. The SSL network was trained and evaluated using simulated data with ground truths and human data in vivo from 10 healthy subjects and 10 patients with myocardial infarction. Results: In the simulation study, the SSL method demonstrated the ability of generating relatively accurate mOEF, MBV, and ΔB maps simultaneously. In the in vivo study, healthy volunteers had an average mOEF of 0.6–0.7 and MBV of 0.11–0.13, comparable to literature‐reported values. In the myocardial infarction regions, the average mOEF and MBV in 5 tested patients reduced to 0.45 ± 0.09 and 0.09 ± 0.02, which were significantly lower (p < 0.001) than those in normal regions (0.67 ± 0.04 and 0.13 ± 0.01, respectively). Conclusion: This work has demonstrated the initial feasibility of generating mOEF and MBV maps simultaneously by a model‐driven, self‐supervised learning method. [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: 188365631
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Model‐based self‐supervised learning for quantitative assessment of myocardial oxygen extraction fraction and myocardial blood volume.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Huang%2C+Qi%22&quot;&gt;Huang, Qi&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Tang%2C+Haoteng%22&quot;&gt;Tang, Haoteng&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Wang%2C+Keyan%22&quot;&gt;Wang, Keyan&lt;/searchLink&gt;&lt;relatesTo&gt;3&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Li%2C+Ran%22&quot;&gt;Li, Ran&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Eldeniz%2C+Cihat%22&quot;&gt;Eldeniz, Cihat&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Nguyen%2C+Natalie%22&quot;&gt;Nguyen, Natalie&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Schindler%2C+Thomas+H%2E%22&quot;&gt;Schindler, Thomas H.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Peterson%2C+Linda+R%2E%22&quot;&gt;Peterson, Linda R.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Yang%2C+Yang%22&quot;&gt;Yang, Yang&lt;/searchLink&gt;&lt;relatesTo&gt;4&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Yan%2C+Yan%22&quot;&gt;Yan, Yan&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Cheng%2C+Jingliang%22&quot;&gt;Cheng, Jingliang&lt;/searchLink&gt;&lt;relatesTo&gt;3&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Woodard%2C+Pamela+K%2E%22&quot;&gt;Woodard, Pamela K.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Zheng%2C+Jie%22&quot;&gt;Zheng, Jie&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;i&gt; zhengj@wustl.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;. Oct2025, Vol. 94 Issue 4, p1793-1803. 11p.
– 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;%22Machine+learning%22&quot;&gt;Machine learning&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Computer-assisted+image+analysis+%28Medicine%29%22&quot;&gt;Computer-assisted image analysis (Medicine)&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22In+vivo+studies%22&quot;&gt;In vivo studies&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Simulation+methods+%26+models%22&quot;&gt;Simulation methods &amp; models&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Blood+volume%22&quot;&gt;Blood volume&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Purpose: To develop a model‐driven, self‐supervised deep learning network for end‐to‐end simultaneous mapping of myocardial oxygen extraction fraction (mOEF) and myocardial blood volume (MBV). Methods: An asymmetrical spin echo–prepared sequence was used to acquire mOEF and MBV images. By integrating a physical model into the training process, a self‐supervised learning (SSL) pattern can be regulated. A loss function consisted of the mean squared error, plus cosine similarity was used to improve the performance of network predictions for estimating mOEF and MBV simultaneously. The SSL network was trained and evaluated using simulated data with ground truths and human data in vivo from 10 healthy subjects and 10 patients with myocardial infarction. Results: In the simulation study, the SSL method demonstrated the ability of generating relatively accurate mOEF, MBV, and ΔB maps simultaneously. In the in vivo study, healthy volunteers had an average mOEF of 0.6–0.7 and MBV of 0.11–0.13, comparable to literature‐reported values. In the myocardial infarction regions, the average mOEF and MBV in 5 tested patients reduced to 0.45 &#177; 0.09 and 0.09 &#177; 0.02, which were significantly lower (p &lt; 0.001) than those in normal regions (0.67 &#177; 0.04 and 0.13 &#177; 0.01, respectively). Conclusion: This work has demonstrated the initial feasibility of generating mOEF and MBV maps simultaneously by a model‐driven, self‐supervised learning method. [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=188365631
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/mrm.30555
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 1793
    Subjects:
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Computer-assisted image analysis (Medicine)
        Type: general
      – SubjectFull: In vivo studies
        Type: general
      – SubjectFull: Simulation methods & models
        Type: general
      – SubjectFull: Blood volume
        Type: general
    Titles:
      – TitleFull: Model‐based self‐supervised learning for quantitative assessment of myocardial oxygen extraction fraction and myocardial blood volume.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Huang, Qi
      – PersonEntity:
          Name:
            NameFull: Tang, Haoteng
      – PersonEntity:
          Name:
            NameFull: Wang, Keyan
      – PersonEntity:
          Name:
            NameFull: Li, Ran
      – PersonEntity:
          Name:
            NameFull: Eldeniz, Cihat
      – PersonEntity:
          Name:
            NameFull: Nguyen, Natalie
      – PersonEntity:
          Name:
            NameFull: Schindler, Thomas H.
      – PersonEntity:
          Name:
            NameFull: Peterson, Linda R.
      – PersonEntity:
          Name:
            NameFull: Yang, Yang
      – PersonEntity:
          Name:
            NameFull: Yan, Yan
      – PersonEntity:
          Name:
            NameFull: Cheng, Jingliang
      – PersonEntity:
          Name:
            NameFull: Woodard, Pamela K.
      – PersonEntity:
          Name:
            NameFull: Zheng, Jie
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: Oct2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 07403194
          Numbering:
            – Type: volume
              Value: 94
            – Type: issue
              Value: 4
          Titles:
            – TitleFull: Magnetic Resonance in Medicine
              Type: main
ResultId 1