Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Modified restricted Boltzmann machine (mRBM) for denoising of motion artifact-induced MRI scans

Modified restricted Boltzmann machine (mRBM) for denoising of motion artifact-induced MRI scans Motion artifacts in magnetic resonance imaging (MRI) are one of the issues that can affect diagnosis. To remove this motion artifact from MRI, we propose a modified restricted Boltzmann machine (mRBM). mRBM can train itself using probability distribution over a set of input images and generate artifact-free images. We proposed a feedback network to the existing RBM for denoising motion artifact-induced MRI data. In mRBM, the number of weights and biases that must be tuned is confined to the size of the image and hence mRBM is significantly fast. For a 256 × 256-pixel image, mRBM output can be achieved within 2 s post-training. The proposed method has a root mean squared error (RMSE) of 0.0034. Since with the help of mRBM, we do not need MRI to be repeated; thus, the speed of diagnosis is significantly improved. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Research on Biomedical Engineering Springer Journals

Modified restricted Boltzmann machine (mRBM) for denoising of motion artifact-induced MRI scans

Download PDF
11 pages

Loading next page...
 
/lp/springer-journals/modified-restricted-boltzmann-machine-mrbm-for-denoising-of-motion-gh0LcDnYJV

References (36)

Publisher
Springer Journals
Copyright
Copyright © The Author(s), under exclusive licence to The Brazilian Society of Biomedical Engineering 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
ISSN
2446-4732
eISSN
2446-4740
DOI
10.1007/s42600-022-00252-w
Publisher site
See Article on Publisher Site

Abstract

Motion artifacts in magnetic resonance imaging (MRI) are one of the issues that can affect diagnosis. To remove this motion artifact from MRI, we propose a modified restricted Boltzmann machine (mRBM). mRBM can train itself using probability distribution over a set of input images and generate artifact-free images. We proposed a feedback network to the existing RBM for denoising motion artifact-induced MRI data. In mRBM, the number of weights and biases that must be tuned is confined to the size of the image and hence mRBM is significantly fast. For a 256 × 256-pixel image, mRBM output can be achieved within 2 s post-training. The proposed method has a root mean squared error (RMSE) of 0.0034. Since with the help of mRBM, we do not need MRI to be repeated; thus, the speed of diagnosis is significantly improved.

Journal

Research on Biomedical Engineering – Springer Journals

Published: Mar 1, 2023

Keywords: MRI; mRBM; Motion artifact

There are no references for this article.