Literature DB >> 32464243

Correction of out-of-FOV motion artifacts using convolutional neural network.

Chengyan Wang1, Yucheng Liang2, Yuan Wu3, Siwei Zhao3, Yiping P Du4.   

Abstract

PURPOSE: Subject motion during MRI scan can result in severe degradation of image quality. Existing motion correction algorithms rely on the assumption that no information is missing during motions. However, this assumption does not hold when out-of-FOV motion happens. Currently available algorithms are not able to correct for image artifacts introduced by out-of-FOV motion. The purpose of this study is to demonstrate the feasibility of incorporating convolutional neural network (CNN) derived prior image into solving the out-of-FOV motion problem. METHODS AND MATERIALS: A modified U-net network was proposed to correct out-of-FOV motion artifacts by incorporating motion parameters into the loss function. A motion model based data fidelity term was applied in combination with the CNN prediction to further improve the motion correction performance. We trained the CNN on 1113 MPRAGE images with simulated oscillating and sudden motion trajectories, and compared our algorithm to a gradient-based autofocusing (AF) algorithm in both 2D and 3D images. Additional experiment was performed to demonstrate the feasibility of transferring the networks to different dataset. We also evaluated the robustness of this algorithm by adding Gaussian noise to the motion parameters. The motion correction performance was evaluated using mean square error (NMSE), peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM).
RESULTS: The proposed algorithm outperformed AF-based algorithm for both 2D (NMSE: 0.0066 ± 0.0009 vs 0.0141 ± 0.008, P < .01; PSNR: 29.60 ± 0.74 vs 21.71 ± 0.27, P < .01; SSIM: 0.89 ± 0.014 vs 0.73 ± 0.004, P < .01) and 3D imaging (NMSE: 0.0067 ± 0.0008 vs 0.070 ± 0.021, P < .01; PSNR: 32.40 ± 1.63 vs 22.32 ± 2.378, P < .01; SSIM: 0.89 ± 0.01 vs 0.62 ± 0.03, P < .01). Robust reconstruction was achieved with 20% data missed due to the out-of-FOV motion.
CONCLUSION: In conclusion, the proposed CNN-based motion correction algorithm can significantly reduce out-of-FOV motion artifacts and achieve better image quality compared to AF-based algorithm.
Copyright © 2020 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Convolutional neural networks; Machine learning; Motion correction; Out-of-FOV motion; Prior image

Mesh:

Year:  2020        PMID: 32464243     DOI: 10.1016/j.mri.2020.05.004

Source DB:  PubMed          Journal:  Magn Reson Imaging        ISSN: 0730-725X            Impact factor:   2.546


  2 in total

Review 1.  Recommendation for Cardiac Magnetic Resonance Imaging-Based Phenotypic Study: Imaging Part.

Authors:  Chengyan Wang; Yan Li; Jun Lv; Jianhua Jin; Xumei Hu; Xutong Kuang; Weibo Chen; He Wang
Journal:  Phenomics       Date:  2021-07-28

2.  PIC-GAN: A Parallel Imaging Coupled Generative Adversarial Network for Accelerated Multi-Channel MRI Reconstruction.

Authors:  Jun Lv; Chengyan Wang; Guang Yang
Journal:  Diagnostics (Basel)       Date:  2021-01-02
  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.