Learned Tensor Low-CP-Rank and Bloch response manifold priors for Non-Cartesian MRF Reconstruction

Simple item page
dc.cclicenceCC-BY-NCen
dc.contributor.authorLi, Peng
dc.contributor.authorLi, Xiaodi
dc.contributor.authorLu, Xin
dc.contributor.authorHu, Yue
dc.date.acceptance2023-02-15
dc.date.accessioned2023-02-22T12:32:41Z
dc.date.available2023-02-22T12:32:41Z
dc.date.issued2023-02-13
dc.description.abstractWe propose a deep unrolled network for non-Cartesian MRF reconstruction by unrolling the MRF reconstruction model regularized by the tensor low-rank and the Bloch resonance manifold priors. To avoid computationally burdensome singular value decomposition, we propose a learned CP decomposition module to exploit the tensor low-rank priors of MRF data. Inspired by the MRF imaging mechanism, we also propose a Bloch response manifold module to learn the mapping between reconstructed MRF data and the multiple parameter maps. Numerical experiments show that the proposed network can improve the reconstruction quality of MRF data and multi-parameter maps within significantly reduced computational time.en
dc.funderOther external funder (please detail below)en
dc.funder.otherNature Science Foundation of Chinaen
dc.funder.otherNatural Science Foundation of Heilongjiangen
dc.identifier.citationLi, P., Li, X., Lu, X. and Hu, Y. (2023) Learned Tensor Low-CP-Rank and Bloch response manifold priors for Non-Cartesian MRF Reconstruction. 2023 ISMRM & ISMRT Annual Meeting & Exhibition, Toronto, Canada, 03-08 Juneen
dc.identifier.urihttps://hdl.handle.net/2086/22520
dc.language.isoenen
dc.peerreviewedYesen
dc.projectidNSFC 61871159en
dc.projectidYQ2021F005en
dc.publisherISMRM & ISMRTen
dc.researchinstituteInstitute of Artificial Intelligence (IAI)en
dc.subjectImage Reconstructionen
dc.subjectMR Fingerprintingen
dc.subjectTensor Low-ranken
dc.subjectCP Decompositionen
dc.subjectBloch Response Manifolden
dc.subjectnon-Cartesianen
dc.titleLearned Tensor Low-CP-Rank and Bloch response manifold priors for Non-Cartesian MRF Reconstructionen
dc.typeConferenceen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ISMRM-2023-1885.pdf
Size:
963.04 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.2 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

School of Computer Science and Informatics