Abstract
Generalized Auto-calibrating Partially Parallel Acquisitions (GRAPPA) has been widely used to reduce imaging time in Magnetic Resonance Imaging. GRAPPA synthesizes missing data by using a linear interpolation of neighboring measured data over all coils, thus accuracy of the interpolation weights fitting to the auto-calibrating signal data is crucial for the GRAPPA reconstruction. Conventional GRAPPA algorithms fitting the interpolation weights with a least squares solution are sensitive to interpolation window size. MKGRAPPA that estimates the interpolation weights with support vector machine reduces the sensitivity of the k-space reconstruction to interpolation window size, whereas it is computationally expensive. In this study, a robust GRAPPA reconstruction method is proposed that applies an extended proximal support vector regression (PSVR) to fit the interpolation weights with wavelet kernel mapping. Experimental results on in vivo MRI data show that the proposed PSVR-GRAPPA method visually improves overall quality compared to conventional GRAPPA methods, while it has faster reconstruction speed compared to MKGRAPPA.
Highlights
Generalized Auto-calibrating Partially Parallel Acquisitions (GRAPPA) reconstruction accuracy strongly depends on the selection of interpolation window
MKGRAPPA15 reformulated estimating the optimal interpolation weights as a multi-kernel learning problem that can reduce the sensitivity of the k-space reconstruction to interpolation windows
The rest of this paper is organized as follow: Section 2 reviews the theory of GRAPPA algorithm and structure risk minimization (SRM), describes the details of proposed method which applies an extended proximal support vector machine (PSVR) to fit the interpolation weights with wavelet kernel mapping; Section 3 applies the proposed method in vivo experiments; Section 4 gives the conclusions and future work to be done
Summary
GRAPPA reconstruction accuracy strongly depends on the selection of interpolation window. Nana et al.[12] utilized the shift-invariance of interpolation weights in k-space to approximate the predication error by calculating the difference between acquired signals and their estimates obtained based on the interpolation of the missing data. This method can determine the optimal interpolation window, time-exhausted reconstruction of all acquired k-space data for each possible interpolation window limits its application on large number of coils data. The rest of this paper is organized as follow: Section 2 reviews the theory of GRAPPA algorithm and SRM, describes the details of proposed method which applies an extended PSVR to fit the interpolation weights with wavelet kernel mapping; Section 3 applies the proposed method in vivo experiments; Section 4 gives the conclusions and future work to be done
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
