Literature DB >> 31403219

Unsupervised learning of a deep neural network for metal artifact correction using dual-polarity readout gradients.

Kinam Kwon1, Dongchan Kim2, Byungjai Kim1, HyunWook Park1.   

Abstract

PURPOSE: A new unsupervised learning method was developed to correct metal artifacts in MRI using 2 distorted images obtained with dual-polarity readout gradients.
METHODS: An unsupervised learning method is proposed for a deep neural network architecture consisting of a deep neural network and an MR image generation module. The architecture is trained as an end-to-end process without the use of distortion-free images or off-resonance frequency maps. The deep neural network estimates frequency-shift maps between 2 distorted images that are obtained using dual-polarity readout gradients. From the estimated frequency-shift maps and 2 distorted input images, distortion-corrected images are obtained with the MR image generation module. Experiments using synthetic data and actual MR data were performed to compare images corrected by several metal-artifact-correction methods.
RESULTS: The proposed method resolved the ripple and pile-up artifacts in the reconstructed images from synthetic data and actual MR data. The results from the proposed method were comparable to those from supervised-learning methods and superior to the compared model-based method. The proposed unsupervised learning method enabled the network to be trained without labels and to be more robust than supervised learning methods, for which overfitting problems can arise when using small training data sets.
CONCLUSION: Metal artifacts in the MR image were drastically corrected by the proposed unsupervised learning method. Two distorted images obtained with dual-polarity readout gradients are used as the input of the deep neural network. The proposed method can train networks without labels and does not overfit the network, even with small training data sets.
© 2019 International Society for Magnetic Resonance in Medicine.

Entities:  

Keywords:  MR image reconstruction; deep neural network; metal artifact correction; unsupervised learning

Year:  2019        PMID: 31403219     DOI: 10.1002/mrm.27917

Source DB:  PubMed          Journal:  Magn Reson Med        ISSN: 0740-3194            Impact factor:   4.668


  3 in total

1.  Performance of PROPELLER FSE T2WI in reducing metal artifacts of material porcelain fused to metal crown: a clinical preliminary study.

Authors:  Wenjin Li; Jing Shi; Wenjin Bian; Jianting Li; Xiaoqing Chen; Juan Feng; Jiali Yu; Jun Wang; Jinliang Niu
Journal:  Sci Rep       Date:  2022-05-19       Impact factor: 4.996

2.  Contemporary approaches to high-field magnetic resonance imaging with large field inhomogeneity.

Authors:  Michael Mullen; Michael Garwood
Journal:  Prog Nucl Magn Reson Spectrosc       Date:  2020-08-16       Impact factor: 9.795

3.  Suppression of artifact-generating echoes in cine DENSE using deep learning.

Authors:  Mohamad Abdi; Xue Feng; Changyu Sun; Kenneth C Bilchick; Craig H Meyer; Frederick H Epstein
Journal:  Magn Reson Med       Date:  2021-05-22       Impact factor: 3.737

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.