Tags

Type your tag names separated by a space and hit enter

Three-dimensional dictionary-learning reconstruction of (23)Na MRI data.
Magn Reson Med. 2016 Apr; 75(4):1605-16.MR

Abstract

PURPOSE

To reduce noise and artifacts in (23)Na MRI with a Compressed Sensing reconstruction and a learned dictionary as sparsifying transform.

METHODS

A three-dimensional dictionary-learning compressed sensing reconstruction algorithm (3D-DLCS) for the reconstruction of undersampled 3D radial (23)Na data is presented. The dictionary used as the sparsifying transform is learned with a K-singular-value-decomposition (K-SVD) algorithm. The reconstruction parameters are optimized on simulated data, and the quality of the reconstructions is assessed with peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The performance of the algorithm is evaluated in phantom and in vivo (23)Na MRI data of seven volunteers and compared with nonuniform fast Fourier transform (NUFFT) and other Compressed Sensing reconstructions.

RESULTS

The reconstructions of simulated data have maximal PSNR and SSIM for an undersampling factor (USF) of 10 with numbers of averages equal to the USF. For 10-fold undersampling, the PSNR is increased by 5.1 dB compared with the NUFFT reconstruction, and the SSIM by 24%. These results are confirmed by phantom and in vivo (23)Na measurements in the volunteers that show markedly reduced noise and undersampling artifacts in the case of 3D-DLCS reconstructions.

CONCLUSION

The 3D-DLCS algorithm enables precise reconstruction of undersampled (23)Na MRI data with markedly reduced noise and artifact levels compared with NUFFT reconstruction. Small structures are well preserved.

Authors+Show Affiliations

Department of Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany.Department of Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany.Department of Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany.Department of Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany.Department of Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany.

Pub Type(s)

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

Language

eng

PubMed ID

25989746

Citation

Behl, Nicolas G R., et al. "Three-dimensional Dictionary-learning Reconstruction of (23)Na MRI Data." Magnetic Resonance in Medicine, vol. 75, no. 4, 2016, pp. 1605-16.
Behl NG, Gnahm C, Bachert P, et al. Three-dimensional dictionary-learning reconstruction of (23)Na MRI data. Magn Reson Med. 2016;75(4):1605-16.
Behl, N. G., Gnahm, C., Bachert, P., Ladd, M. E., & Nagel, A. M. (2016). Three-dimensional dictionary-learning reconstruction of (23)Na MRI data. Magnetic Resonance in Medicine, 75(4), 1605-16. https://doi.org/10.1002/mrm.25759
Behl NG, et al. Three-dimensional Dictionary-learning Reconstruction of (23)Na MRI Data. Magn Reson Med. 2016;75(4):1605-16. PubMed PMID: 25989746.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Three-dimensional dictionary-learning reconstruction of (23)Na MRI data. AU - Behl,Nicolas G R, AU - Gnahm,Christine, AU - Bachert,Peter, AU - Ladd,Mark E, AU - Nagel,Armin M, Y1 - 2015/05/19/ PY - 2014/11/26/received PY - 2015/04/02/revised PY - 2015/04/13/accepted PY - 2015/5/21/entrez PY - 2015/5/21/pubmed PY - 2016/12/15/medline KW - compressed sensing KW - dictionary learning KW - iterative reconstruction KW - nonproton MRI KW - projection reconstruction KW - sodium MRI SP - 1605 EP - 16 JF - Magnetic resonance in medicine JO - Magn Reson Med VL - 75 IS - 4 N2 - PURPOSE: To reduce noise and artifacts in (23)Na MRI with a Compressed Sensing reconstruction and a learned dictionary as sparsifying transform. METHODS: A three-dimensional dictionary-learning compressed sensing reconstruction algorithm (3D-DLCS) for the reconstruction of undersampled 3D radial (23)Na data is presented. The dictionary used as the sparsifying transform is learned with a K-singular-value-decomposition (K-SVD) algorithm. The reconstruction parameters are optimized on simulated data, and the quality of the reconstructions is assessed with peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The performance of the algorithm is evaluated in phantom and in vivo (23)Na MRI data of seven volunteers and compared with nonuniform fast Fourier transform (NUFFT) and other Compressed Sensing reconstructions. RESULTS: The reconstructions of simulated data have maximal PSNR and SSIM for an undersampling factor (USF) of 10 with numbers of averages equal to the USF. For 10-fold undersampling, the PSNR is increased by 5.1 dB compared with the NUFFT reconstruction, and the SSIM by 24%. These results are confirmed by phantom and in vivo (23)Na measurements in the volunteers that show markedly reduced noise and undersampling artifacts in the case of 3D-DLCS reconstructions. CONCLUSION: The 3D-DLCS algorithm enables precise reconstruction of undersampled (23)Na MRI data with markedly reduced noise and artifact levels compared with NUFFT reconstruction. Small structures are well preserved. SN - 1522-2594 UR - https://www.unboundmedicine.com/medline/citation/25989746/Three_dimensional_dictionary_learning_reconstruction_of__23_Na_MRI_data_ L2 - https://doi.org/10.1002/mrm.25759 DB - PRIME DP - Unbound Medicine ER -