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

Chan, KL; Henning, A

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Poster

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

MPS-Authors

/persons/resource/persons84402

Henning, A
Research Group MR Spectroscopy and Ultra-High Field Methodology, Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource

https://submissions.mirasmart.com/ISMRM2022/Itinerary/ConferenceMatrixEventDetail.aspx?ses=D-52
(Abstract)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

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.

Cite as: https://hdl.handle.net/21.11116/0000-000A-5C3D-C

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.