MRI reconstruction with joint global regularization and transform learning. (October 2016)

• Record Type: Journal Article
• Authors: Tanc, A. Korhan; Eksioglu, Ender M.
• Is Part Of: Computerized medical imaging and graphics. Volume 53(2016)
• Page Start: 1
• Page End: 8
• Publication Date: 2016-10
• Subjects: Global regularization -- Image reconstruction -- Magnetic resonance -- Sparsity -- Transform learning; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2016.06.004
• Languages: English
• ISSNs: 0895-6111

Abstract

Abstract : Highlights: We address the problem of MRI reconstruction from highly undersampled measurements. We propose a cost function, with both global and patch-based penalty terms. We develop JGT-MRI algorithm for the minimization of our composite cost function. The results show that JGT-MRI has performance exceeding the competing algorithms. 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.