Auto-regularized Gradients of Adaptive Interpolation for MRI Super-Resolution

In this paper, a method for adaptive pure interpolation (PI) of magnetic resonance imaging (MRI) in the frequency domain, with gradient auto-regularization, is proposed. The input image is transformed into the frequency domain and convolved with the Fourier transform (FT) of a 2D sampling array (int...

Full description

Saved in:

Bibliographic Details
Published in:	Journal of signal processing systems Vol. 91; no. 8; pp. 885 - 898
Main Authors:	Delfin, Leandro Morera, Elias, Raul Pinto, de Jesús Ochoa Domínguez, Humberto, Villegas, Osslan Osiris Overgara
Format:	Journal Article
Language:	English
Published:	New York Springer US 15-08-2019 Springer Nature B.V
Subjects:	Algorithms Arrays Circuits and Systems Computer Imaging Electrical Engineering Engineering Fourier transforms Frequency domain analysis Image Processing and Computer Vision Image resolution Interpolation Kernels Magnetic resonance imaging NMR Noise levels Nuclear magnetic resonance Pattern Recognition Pattern Recognition and Graphics Regularization Regularization methods Sampling Signal to noise ratio Signal,Image and Speech Processing Vision Super-resolution Pure interpolation MRI Auto-regularized gradients
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	In this paper, a method for adaptive pure interpolation (PI) of magnetic resonance imaging (MRI) in the frequency domain, with gradient auto-regularization, is proposed. The input image is transformed into the frequency domain and convolved with the Fourier transform (FT) of a 2D sampling array (interpolation kernel) of initial L x M size. The inverse Fourier transform (IFT) is applied to the output coefficients and the edges are detected and counted. To get a denser kernel the sampling array is interpolated in the frequency domain and convolved again with the transform coefficients of the original MRI image of low resolution and transformed back into the spatial domain. The process is repeated until a maximum count of edges is reached in the output image, indicating that a local optimum magnification factor has been attained. Finally, the edges are sharpened by using an auto-regularization method. Our procedure is deterministic and independent of external information of large databases of other MRI images for obtain the high resolution output image. The proposed system improves the bi-cubic interpolation method by a mean of 3dB in peak of signal-to-noise ratio (PSNR) and until 6 dB in the best case. The structural similarity index measure (SSIM) is improved over bicubic interpolation with a mean of 0.04 and until 0.08 in the best case. It is a significant result respect to novel algorithms reported in the state of the art.
ISSN:	1939-8018 1939-8115
DOI:	10.1007/s11265-018-1408-1