Title :
MR Image Reconstruction From Highly Undersampled k-Space Data by Dictionary Learning
Author :
Ravishankar, Saiprasad ; Bresler, Yoram
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Illinois, Urbana, IL, USA
fDate :
5/1/2011 12:00:00 AM
Abstract :
Compressed sensing (CS) utilizes the sparsity of magnetic resonance (MR) images to enable accurate reconstruction from undersampled k-space data. Recent CS methods have employed analytical sparsifying transforms such as wavelets, curvelets, and finite differences. In this paper, we propose a novel framework for adaptively learning the sparsifying transform (dictionary), and reconstructing the image simultaneously from highly undersampled k-space data. The sparsity in this framework is enforced on overlapping image patches emphasizing local structure. Moreover, the dictionary is adapted to the particular image instance thereby favoring better sparsities and consequently much higher undersampling rates. The proposed alternating reconstruction algorithm learns the sparsifying dictionary, and uses it to remove aliasing and noise in one step, and subsequently restores and fills-in the k-space data in the other step. Numerical experiments are conducted on MR images and on real MR data of several anatomies with a variety of sampling schemes. The results demonstrate dramatic improvements on the order of 4-18 dB in reconstruction error and doubling of the acceptable undersampling factor using the proposed adaptive dictionary as compared to previous CS methods. These improvements persist over a wide range of practical data signal-to-noise ratios, without any parameter tuning.
Keywords :
biomedical MRI; finite difference methods; image reconstruction; learning (artificial intelligence); medical image processing; sampling methods; wavelet transforms; MR image reconstruction; alternating reconstruction algorithm; analytical sparsifying transform; compressed sensing; curvelet transforms; dictionary learning; finite difference transforms; highly undersampled k-space data; learning framework; numerical experiments; signal-noise ratios; sparsifying dictionary; wavelet transforms; Dictionaries; Image reconstruction; Magnetic resonance imaging; Noise; Pixel; Wavelet transforms; Compressed sensing (CS); dictionary learning; image reconstruction; magnetic resonance imaging (MRI); reduced encoding; sparse representation; Algorithms; Artificial Intelligence; Brain; Databases, Factual; Humans; Image Processing, Computer-Assisted; Lumbosacral Region; Magnetic Resonance Imaging; Models, Theoretical;
Journal_Title :
Medical Imaging, IEEE Transactions on
DOI :
10.1109/TMI.2010.2090538