Report
View in EDS

SRNR: Training neural networks for Super-Resolution MRI using Noisy high-resolution Reference data

Bibliographic Details
Title: SRNR: Training neural networks for Super-Resolution MRI using Noisy high-resolution Reference data
Authors: Xiao, Jiaxin, Li, Zihan, Bilgic, Berkin, Polimeni, Jonathan R., Huang, Susie, Tian, Qiyuan
Publication Year: 2022
Subject Terms: Electrical Engineering and Systems Science - Image and Video Processing
More Details: Neural network (NN) based approaches for super-resolution MRI typically require high-SNR high-resolution reference data acquired in many subjects, which is time consuming and a barrier to feasible and accessible implementation. We propose to train NNs for Super-Resolution using Noisy Reference data (SRNR), leveraging the mechanism of the classic NN-based denoising method Noise2Noise. We systematically demonstrate that results from NNs trained using noisy and high-SNR references are similar for both simulated and empirical data. SRNR suggests a smaller number of repetitions of high-resolution reference data can be used to simplify the training data preparation for super-resolution MRI.
Comment: 2 pages, 5 figures, submitted to ISMRM
Document Type: Working Paper
Access URL: http://arxiv.org/abs/2211.05360
Accession Number: edsarx.2211.05360
Database: arXiv
FullText Text:
  Availability: 0
CustomLinks:
  – Url: http://arxiv.org/abs/2211.05360
    Name: EDS - Arxiv
    Category: fullText
    Text: View this record from Arxiv
    MouseOverText: View this record from Arxiv
  – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20221110&spage=&pages=&title=SRNR: Training neural networks for Super-Resolution MRI using Noisy high-resolution Reference data&atitle=SRNR%3A%20Training%20neural%20networks%20for%20Super-Resolution%20MRI%20using%20Noisy%20high-resolution%20Reference%20data&aulast=Xiao%2C%20Jiaxin&id=DOI:
    Name: Full Text Finder (for New FTF UI) (s8985755)
    Category: fullText
    Text: Find It @ SCU Libraries
    MouseOverText: Find It @ SCU Libraries
Header DbId: edsarx
DbLabel: arXiv
An: edsarx.2211.05360
RelevancyScore: 1043
AccessLevel: 3
PubType: Report
PubTypeId: report
PreciseRelevancyScore: 1043.48132324219
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: SRNR: Training neural networks for Super-Resolution MRI using Noisy high-resolution Reference data
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Xiao%2C+Jiaxin%22">Xiao, Jiaxin</searchLink><br /><searchLink fieldCode="AR" term="%22Li%2C+Zihan%22">Li, Zihan</searchLink><br /><searchLink fieldCode="AR" term="%22Bilgic%2C+Berkin%22">Bilgic, Berkin</searchLink><br /><searchLink fieldCode="AR" term="%22Polimeni%2C+Jonathan+R%2E%22">Polimeni, Jonathan R.</searchLink><br /><searchLink fieldCode="AR" term="%22Huang%2C+Susie%22">Huang, Susie</searchLink><br /><searchLink fieldCode="AR" term="%22Tian%2C+Qiyuan%22">Tian, Qiyuan</searchLink>
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2022
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Electrical+Engineering+and+Systems+Science+-+Image+and+Video+Processing%22">Electrical Engineering and Systems Science - Image and Video Processing</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Neural network (NN) based approaches for super-resolution MRI typically require high-SNR high-resolution reference data acquired in many subjects, which is time consuming and a barrier to feasible and accessible implementation. We propose to train NNs for Super-Resolution using Noisy Reference data (SRNR), leveraging the mechanism of the classic NN-based denoising method Noise2Noise. We systematically demonstrate that results from NNs trained using noisy and high-SNR references are similar for both simulated and empirical data. SRNR suggests a smaller number of repetitions of high-resolution reference data can be used to simplify the training data preparation for super-resolution MRI.<br />Comment: 2 pages, 5 figures, submitted to ISMRM
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Working Paper
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2211.05360" linkWindow="_blank">http://arxiv.org/abs/2211.05360</link>
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsarx.2211.05360
PLink https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2211.05360
RecordInfo BibRecord:
  BibEntity:
    Subjects:
      – SubjectFull: Electrical Engineering and Systems Science - Image and Video Processing
        Type: general
    Titles:
      – TitleFull: SRNR: Training neural networks for Super-Resolution MRI using Noisy high-resolution Reference data
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Xiao, Jiaxin
      – PersonEntity:
          Name:
            NameFull: Li, Zihan
      – PersonEntity:
          Name:
            NameFull: Bilgic, Berkin
      – PersonEntity:
          Name:
            NameFull: Polimeni, Jonathan R.
      – PersonEntity:
          Name:
            NameFull: Huang, Susie
      – PersonEntity:
          Name:
            NameFull: Tian, Qiyuan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 10
              M: 11
              Type: published
              Y: 2022
ResultId 1