Unsupervised learning of a deep neural network for metal artifact correction using dual‐polarity readout gradients
- 12 August 2019
- journal article
- research article
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 83 (1) , 124-138
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.Keywords
Funding Information
- Institute for Information & Communications Technology Planning & Evaluation (2017-0-01779)
This publication has 33 references indexed in Scilit:
- Efficient correction of inhomogeneous static magnetic field-induced distortion in Echo Planar ImagingNeuroImage, 2010
- SEMAC: Slice encoding for metal artifact correction in MRIMagnetic Resonance in Medicine, 2009
- A multispectral three‐dimensional acquisition technique for imaging near metal implantsMagnetic Resonance in Medicine, 2009
- Correction for geometric distortion and N/2 ghosting in EPI by phase labeling for additional coordinate encoding (PLACE)Magnetic Resonance in Medicine, 2007
- Rapid calculations of susceptibility-induced magnetostatic field perturbations forin vivomagnetic resonancePhysics in Medicine & Biology, 2006
- Correction of MR image distortions induced by metallic objects using a 3D cubic B‐spline basis set: Application to stereotactic surgical planningMagnetic Resonance in Medicine, 2005
- Generalized autocalibrating partially parallel acquisitions (GRAPPA)Magnetic Resonance in Medicine, 2002
- Correction for geometric distortion in echo planar images from B0 field variationsMagnetic Resonance in Medicine, 1995
- A technique for accurate magnetic resonance imaging in the presence of field inhomogeneitiesIEEE Transactions on Medical Imaging, 1992
- Homodyne detection in magnetic resonance imagingIEEE Transactions on Medical Imaging, 1991