Tags

Type your tag names separated by a space and hit enter

MR image reconstruction from highly undersampled k-space data by dictionary learning.
IEEE Trans Med Imaging. 2011 May; 30(5):1028-41.IT

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.

Authors+Show Affiliations

Department of Electrical and Computer Engineering and the Coordinated Science Laboratory, University of Illinois, Urbana-Champaign, IL 61801, USA. ravisha3@illinois.eduNo affiliation info available

Pub Type(s)

Journal Article
Research Support, U.S. Gov't, Non-P.H.S.

Language

eng

PubMed ID

21047708

Citation

Ravishankar, Saiprasad, and Yoram Bresler. "MR Image Reconstruction From Highly Undersampled K-space Data By Dictionary Learning." IEEE Transactions On Medical Imaging, vol. 30, no. 5, 2011, pp. 1028-41.
Ravishankar S, Bresler Y. MR image reconstruction from highly undersampled k-space data by dictionary learning. IEEE Trans Med Imaging. 2011;30(5):1028-41.
Ravishankar, S., & Bresler, Y. (2011). MR image reconstruction from highly undersampled k-space data by dictionary learning. IEEE Transactions On Medical Imaging, 30(5), 1028-41. https://doi.org/10.1109/TMI.2010.2090538
Ravishankar S, Bresler Y. MR Image Reconstruction From Highly Undersampled K-space Data By Dictionary Learning. IEEE Trans Med Imaging. 2011;30(5):1028-41. PubMed PMID: 21047708.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - MR image reconstruction from highly undersampled k-space data by dictionary learning. AU - Ravishankar,Saiprasad, AU - Bresler,Yoram, Y1 - 2010/11/01/ PY - 2010/11/5/entrez PY - 2010/11/5/pubmed PY - 2011/8/19/medline SP - 1028 EP - 41 JF - IEEE transactions on medical imaging JO - IEEE Trans Med Imaging VL - 30 IS - 5 N2 - 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. SN - 1558-254X UR - https://www.unboundmedicine.com/medline/citation/21047708/MR_image_reconstruction_from_highly_undersampled_k_space_data_by_dictionary_learning_ L2 - https://dx.doi.org/10.1109/TMI.2010.2090538 DB - PRIME DP - Unbound Medicine ER -