English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  MultiNet CAIPIRINHA: accelerated 1H MRSI with 1-step neural network reconstruction based on augmented MRSI training data

Chan, K., & Henning, A. (2022). MultiNet CAIPIRINHA: accelerated 1H MRSI with 1-step neural network reconstruction based on augmented MRSI training data. Poster presented at Joint Annual Meeting ISMRM-ESMRMB & ISMRT 31st Annual Meeting (ISMRM 2022), London, UK.

Item is

Files

show Files

Creators

show
hide
 Creators:
Chan, KL, Author
Henning, A1, Author              
Affiliations:
1Research Group MR Spectroscopy and Ultra-High Field Methodology, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_2528692              

Content

show
hide
Free keywords: -
 Abstract: We have shown that MultiNet, a neural-network-based image reconstruction, can reconstruct variable-density k-space undersampling schemes to decrease MRSI acquisition times. This used a 4-step method where points are predicted by 4 successively-applied neural-networks off both acquired and previously predicted k-space points. Herein, a 1-step method where points are only predicted off acquired k-space points to reduce reconstruction error was explored. This method was trained using a new augmented MRSI training set and compared to the 4-step reconstruction of new CAIPIRINHA-based schemes and the original schemes. The new 1-step reconstruction method was found to increase SNR and improve metabolic maps.

Details

show
hide
Language(s):
 Dates: 2022-05
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: Joint Annual Meeting ISMRM-ESMRMB & ISMRT 31st Annual Meeting (ISMRM 2022)
Place of Event: London, UK
Start-/End Date: 2022-05-07 - 2022-05-12

Legal Case

show

Project information

show

Source 1

show
hide
Title: Joint Annual Meeting ISMRM-ESMRMB & ISMRT 31st Annual Meeting (ISMRM 2022)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: 1080 Start / End Page: - Identifier: -