Limits...
Undersampled MR Image Reconstruction with Data-Driven Tight Frame.

Liu J, Wang S, Peng X, Liang D - Comput Math Methods Med (2015)

Bottom Line: By taking advantage of the efficiency and effectiveness of data-driven tight frame, DDTF-MRI trains an adaptive tight frame to sparsify the to-be-reconstructed MR image.Furthermore, a two-level Bregman iteration algorithm has been developed to solve the proposed model.The proposed method has been compared to two state-of-the-art methods on four datasets and encouraging performances have been achieved by DDTF-MRI.

View Article: PubMed Central - PubMed

Affiliation: Paul C. Lauterbur Research Centre for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China.

ABSTRACT
Undersampled magnetic resonance image reconstruction employing sparsity regularization has fascinated many researchers in recent years under the support of compressed sensing theory. Nevertheless, most existing sparsity-regularized reconstruction methods either lack adaptability to capture the structure information or suffer from high computational load. With the aim of further improving image reconstruction accuracy without introducing too much computation, this paper proposes a data-driven tight frame magnetic image reconstruction (DDTF-MRI) method. By taking advantage of the efficiency and effectiveness of data-driven tight frame, DDTF-MRI trains an adaptive tight frame to sparsify the to-be-reconstructed MR image. Furthermore, a two-level Bregman iteration algorithm has been developed to solve the proposed model. The proposed method has been compared to two state-of-the-art methods on four datasets and encouraging performances have been achieved by DDTF-MRI.

No MeSH data available.


Related in: MedlinePlus

(a) Original filters. (b) The corresponding learnt filters in the experiment of Figure 2.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4495234&req=5

fig1: (a) Original filters. (b) The corresponding learnt filters in the experiment of Figure 2.

Mentions: As shown in Figure 1(a), we employed the 3-level shift-invariant Haar wavelet filters (the size of each filter is 8 × 8) as the initialization of the tight frame in DDTF-MRI. As for the parameter settings, both CSMRI-TV and DLMRI were implemented with their default settings. For DDTF-MRI, we set M = 3, δb = 1, δc = 1, μ = 10, and λ = 10. The outer-level iteration of DDTF-MRI continues until k > 25. Furthermore, we used both the peak signal-to-noise ratio (PSNR) (the PSNR is defined as PSNR = 20log10255/RMSE, where the RMSE is the root mean error estimated between the ground truth and the reconstructed image), high-frequency error norm (HFEN) [5], and structural similarity (SSIM) index [29] for a quantitative comparison of recovered results.


Undersampled MR Image Reconstruction with Data-Driven Tight Frame.

Liu J, Wang S, Peng X, Liang D - Comput Math Methods Med (2015)

(a) Original filters. (b) The corresponding learnt filters in the experiment of Figure 2.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4495234&req=5

fig1: (a) Original filters. (b) The corresponding learnt filters in the experiment of Figure 2.
Mentions: As shown in Figure 1(a), we employed the 3-level shift-invariant Haar wavelet filters (the size of each filter is 8 × 8) as the initialization of the tight frame in DDTF-MRI. As for the parameter settings, both CSMRI-TV and DLMRI were implemented with their default settings. For DDTF-MRI, we set M = 3, δb = 1, δc = 1, μ = 10, and λ = 10. The outer-level iteration of DDTF-MRI continues until k > 25. Furthermore, we used both the peak signal-to-noise ratio (PSNR) (the PSNR is defined as PSNR = 20log10255/RMSE, where the RMSE is the root mean error estimated between the ground truth and the reconstructed image), high-frequency error norm (HFEN) [5], and structural similarity (SSIM) index [29] for a quantitative comparison of recovered results.

Bottom Line: By taking advantage of the efficiency and effectiveness of data-driven tight frame, DDTF-MRI trains an adaptive tight frame to sparsify the to-be-reconstructed MR image.Furthermore, a two-level Bregman iteration algorithm has been developed to solve the proposed model.The proposed method has been compared to two state-of-the-art methods on four datasets and encouraging performances have been achieved by DDTF-MRI.

View Article: PubMed Central - PubMed

Affiliation: Paul C. Lauterbur Research Centre for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China.

ABSTRACT
Undersampled magnetic resonance image reconstruction employing sparsity regularization has fascinated many researchers in recent years under the support of compressed sensing theory. Nevertheless, most existing sparsity-regularized reconstruction methods either lack adaptability to capture the structure information or suffer from high computational load. With the aim of further improving image reconstruction accuracy without introducing too much computation, this paper proposes a data-driven tight frame magnetic image reconstruction (DDTF-MRI) method. By taking advantage of the efficiency and effectiveness of data-driven tight frame, DDTF-MRI trains an adaptive tight frame to sparsify the to-be-reconstructed MR image. Furthermore, a two-level Bregman iteration algorithm has been developed to solve the proposed model. The proposed method has been compared to two state-of-the-art methods on four datasets and encouraging performances have been achieved by DDTF-MRI.

No MeSH data available.


Related in: MedlinePlus