MRI reconstruction with joint global regularization and transform learning

A. Korhan Tanc, Ender M. Eksioglu*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)

Abstract

Sparsity based regularization has been a popular approach to remedy the measurement scarcity in image reconstruction. Recently, sparsifying transforms learned from image patches have been utilized as an effective regularizer for the Magnetic Resonance Imaging (MRI) reconstruction. Here, we infuse additional global regularization terms to the patch-based transform learning. We develop an algorithm to solve the resulting novel cost function, which includes both patchwise and global regularization terms. Extensive simulation results indicate that the introduced mixed approach has improved MRI reconstruction performance, when compared to the algorithms which use either of the patchwise transform learning or global regularization terms alone.

Original languageEnglish
Pages (from-to)1-8
Number of pages8
JournalComputerized Medical Imaging and Graphics
Volume53
DOIs
Publication statusPublished - 1 Oct 2016

Bibliographical note

Publisher Copyright:
© 2016 Elsevier Ltd

Funding

http://mr.usc.edu/download/data (funded by NSF grant CCF-1350563 ).

FundersFunder number
National Science FoundationCCF-1350563

    Keywords

    • Global regularization
    • Image reconstruction
    • Magnetic resonance
    • Sparsity
    • Transform learning

    Fingerprint

    Dive into the research topics of 'MRI reconstruction with joint global regularization and transform learning'. Together they form a unique fingerprint.

    Cite this