Image-based motion artifact reduction on liver dynamic contrast enhanced MRI

  • Yunan Wu
    Department of Electrical Computer Engineering, Northwestern University, 633 Clark Street, Evanston, IL 60208, USA

    Department of Diagnostic Radiology, Rush University Medical Center, 1653 W. Congress Pkwy, Jelke Ste 181, Chicago, IL 60612, USA
    Search for articles by this author
  • Junchi Liu
    Medical Imaging Research Center and Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL 60616, USA
    Search for articles by this author
  • Gregory M. White
    Department of Diagnostic Radiology, Rush University Medical Center, 1653 W. Congress Pkwy, Jelke Ste 181, Chicago, IL 60612, USA
    Search for articles by this author
  • Jie Deng
    Corresponding author at: Department of Radiation Oncology, UT Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390, USA.
    Department of Diagnostic Radiology, Rush University Medical Center, 1653 W. Congress Pkwy, Jelke Ste 181, Chicago, IL 60612, USA

    Department of Radiation Oncology, UT Southwestern Medical Center, 2280 Inwood Rd, Dallas, TX 75235, USA
    Search for articles by this author
Published:December 22, 2022DOI:


      • The Generative Adversarial Network to reduce motion artifacts on liver MRI.
      • Training with the perceptual loss to preserve anatomical structure details.
      • Multiple types and degrees of motion artifacts simulation in image and k-space.
      • Good generalization of the model evaluated on liver MRI images with real motion.


      Liver MRI images often suffer from degraded quality due to ghosting or blurring artifacts caused by patient respiratory or bulk motion. In this study, we developed a two-stage deep learning model to reduce motion artifact on dynamic contrast enhanced (DCE) liver MRIs. The stage-I network utilized a deep residual network with a densely connected multi-resolution block (DRN-DCMB) network to remove most motion artifacts. The stage-II network applied the generative adversarial network (GAN) and perceptual loss compensation to preserve image structural features. The stage-I network served as the generator of GAN and its pretrained parameters in stage-I were further updated via backpropagation during stage-II training. The stage-I network was trained using small image patches with simulated motion artifacts including image-space rotational and translational motion, and K-space based centric and interleaved linear motion, sinusoidal, and rotational motion to mimic liver motion patterns. The stage-II network training used full-size images with the same types of simulated motion. The liver DCE-MRI image volumes without obvious motion artifacts in 10 patients were used for the training process, of which 1020 images of 8 patients were used for training and 240 images of 2 patients for validation. Finally, the whole two-stage deep learning model was tested with simulated motion images (312 clean images from 5 test patients) and patient images with real motion artifacts (28 motion images from 12 patients). The resulted images after two-stage processing demonstrated reduced motion artifacts while preserved anatomic details without image blurriness, with SSIM of 0.935 ± 0.092, MSE of 60.7 ± 9.0 × 10-3, and PSNR of 32.054 ± 2.219.


      DCE-MRI (dynamic contrast enhanced magnetic resonance imaging), DRN-DCMB (deep residual network with densely connected multi-resolution block), CS (compressed sensing), CNNs (convolutional neural networks), DL (deep learning), 3D (three-dimensional), FFT (Fast Fourier Transform), BN (batch normalization), LeakyReLU (Leaky rectified linear unit), MSE (mean square error), SSIM (structural similarity index), TR (repetition time), TE (echo time), FA (flip angle), MARC (motion artifact reduction with convolution), GAN (generative adversarial network)


      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Physica Medica: European Journal of Medical Physics
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Albiin N.
        MRI of focal liver lesions.
        Curr Med Imaging Rev. 2012 May; 8: 107-116
        • Li Z.
        • Sun J.
        • Chen L.
        • Huang N.
        • Hu P.
        • Hu X.
        • et al.
        Assessment of liver fibrosis using pharmacokinetic parameters of dynamic contrast-enhanced magnetic resonance imaging.
        J Magn Reson Imaging. 2016 Jul; 44: 98-104
        • Ou H.-Y.
        • Bonekamp S.
        • Bonekamp D.
        • Corona-Villalobos C.P.
        • Torbenson M.S.
        • Geiger B.
        • et al.
        MRI arterial enhancement fraction in hepatic fibrosis and cirrhosis.
        Am J Roentgenol. 2013; 201: W596-W602
        • Chen B.-B.
        • Hsu C.-Y.
        • Yu C.-W.
        • Liang P.-C.
        • Hsu C.
        • Hsu C.-H.
        • et al.
        Dynamic Contrast-enhanced MR imaging of advanced hepatocellular carcinoma: comparison with the liver parenchyma and correlation with the survival of patients receiving systemic therapy.
        Radiology. 2016; 281: 454-464
      1. Balafar M. Review of noise reducing algorithms for brain MRI images. methods. 10:11.

        • Ali S.H.
        • Modic M.E.
        • Mahmoud S.Y.
        • Jones S.E.
        Reducing clinical MRI motion degradation using a prescan patient information pamphlet.
        Am J Roentgenol. 2013 Mar; 200: 630-634
        • Zhang T.
        • Chowdhury S.
        • Lustig M.
        • Barth R.A.
        • Alley M.T.
        • Grafendorfer T.
        • et al.
        Clinical performance of contrast enhanced abdominal pediatric MRI with fast combined parallel imaging compressed sensing reconstruction.
        J Magn Reson Imaging. 2014; 40: 13-25
        • Hollingsworth K.G.
        Reducing acquisition time in clinical MRI by data undersampling and compressed sensing reconstruction.
        Phys Med Biol. 2015; 60: R297-R322
        • Chandarana H.
        • Feng L.
        • Block T.K.
        • Rosenkrantz A.B.
        • Lim R.P.
        • Babb J.S.
        • et al.
        Free-breathing contrast-enhanced multiphase MRI of the liver using a combination of compressed sensing, parallel imaging, and golden-angle radial sampling.
        Investig. Radiol. 2013; 48: 10-16
        • Vasanawala S.S.
        • Alley M.T.
        • Hargreaves B.A.
        • Barth R.A.
        • Pauly J.M.
        • Lustig M.
        Improved pediatric MR imaging with compressed sensing.
        Radiology. 2010 Aug; 256: 607-616
        • Manco L.
        • Maffei N.
        • Strolin S.
        • Vichi S.
        • Bottazzi L.
        • Strigari L.
        Basic of machine learning and deep learning in imaging for medical physicists.
        Physica Medica: Eur J Med Phys. 2021; 1: 194-205
      2. Gjesteby L, Yang Q, Xi Y, Zhou Y, Zhang J, Wang G. Deep learning methods to guide CT image reconstruction and reduce metal artifacts. In: Medical Imaging 2017: Physics of Medical Imaging [Internet]. International Society for Optics and Photonics; 2017 [cited 2021 Jan 6]. p. 101322W.

        • Schlemper J.
        • Caballero J.
        • Hajnal J.V.
        • Price A.N.
        • Rueckert D.
        A deep cascade of convolutional neural networks for dynamic MR image reconstruction.
        IEEE Trans Med Imaging. 2018; 37: 491-503
      3. Oksuz I, Clough J, Ruijsink B, Puyol-Antón E, Bustin A, Cruz G, et al. Detection and Correction of Cardiac MRI Motion Artefacts During Reconstruction from k-space. In: Shen D, Liu T, Peters TM, Staib LH, Essert C, Zhou S, et al., editors. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019 [Internet]. Cham: Springer International Publishing; 2019 [cited 2021 Jan 6]. p. 695–703. (Lecture Notes in Computer Science; vol. 11767).

        • Sujit S.J.
        • Coronado I.
        • Kamali A.
        • Narayana P.A.
        • Gabr R.E.
        Automated image quality evaluation of structural brain MRI using an ensemble of deep learning networks.
        J Magn Reson Imaging. 2019; 50: 1260-1267
        • Ding Y.
        • Suffren S.
        • Bellec P.
        • Lodygensky G.A.
        Supervised machine learning quality control for magnetic resonance artifacts in neonatal data sets.
        Hum Brain Mapp. 2019; 40: 1290-1297
        • Cavedon C.
        Real-time control of respiratory motion: Beyond radiation therapy.
        Physica Medica: Eur J Medi Phys. 2019; 1: 104-112
        • Cusumano D.
        • Boldrini L.
        • Dhont J.
        • Fiorino C.
        • Green O.
        • Güngör G.
        • et al.
        Artificial Intelligence in magnetic Resonance guided Radiotherapy: Medical and physical considerations on state of art and future perspectives.
        Physica Medica: Eur J Med Phys. 2021; 1: 175-191
        • Liu J.
        • Kocak M.
        • Supanich M.
        • Deng J.
        Motion artifacts reduction in brain MRI by means of a deep residual network with densely connected multi-resolution blocks (DRN-DCMB).
        Magn Reson Imaging. 2020; 1: 69-79
        • Zhang Q.
        • Ruan G.
        • Yang W.
        • Liu Y.
        • Zhao K.
        • Feng Q.
        • et al.
        MRI Gibbs-ringing artifact reduction by means of machine learning using convolutional neural networks.
        Magn Reson Med. 2019; 82: 2133-2145
      4. Jiang W, Liu Z, Lee K-H, Chen S, Ng Y-L, Dou Q, et al. Respiratory motion correction in abdominal MRI using a densely connected U-Net with GAN-guided training. arXiv preprint arXiv:190609745. 2019;.

        • Tamada D.
        • Kromrey M.-L.
        • Ichikawa S.
        • Onishi H.
        • Motosugi U.
        Motion artifact reduction using a convolutional neural network for dynamic contrast enhanced MR imaging of the liver.
        Magn Reson Med Sci. 2019; 19: 64-76
        • Kromrey M.-L.
        • Tamada D.
        • Johno H.
        • Funayama S.
        • Nagata N.
        • Ichikawa S.
        • et al.
        Reduction of respiratory motion artifacts in gadoxetate-enhanced MR with a deep learning–based filter using convolutional neural network.
        Eur Radiol. 2020; 30: 5923-5932
      5. Jiang W, Liu Z, Lee K-H, Chen S, Ng Y-L, Dou Q, et al. Respiratory Motion Correction in Abdominal MRI using a Densely Connected U-Net with GAN-guided Training. :8.

      6. Yang Q, Yan P, Kalra MK, Wang G. CT Image Denoising with Perceptive Deep Neural Networks. arXiv:170207019 [cs] [Internet]. 2017 Feb 22 [cited 2021 Jan 3];.

        • Herbst M.
        • Maclaren J.
        • Lovell-Smith C.
        • Sostheim R.
        • Egger K.
        • Harloff A.
        • et al.
        Reproduction of motion artifacts for performance analysis of prospective motion correction in MRI.
        Magn Reson Med. 2014; 71: 182-190
        • Zaitsev M.
        • Julian M.
        • Herbst M.
        Motion artefacts in MRI: a complex problem with many partial solutions.
        J Magn Reson Imaging. 2015; 42: 887-901
      7. Johnson J, Alahi A, Fei-Fei L. Perceptual Losses for Real-Time Style Transfer and Super-Resolution. arXiv:160308155 [cs] [Internet]. 2016 Mar 26 [cited 2021 Jan 6];.

      8. Xu B, Wang N, Chen T, Li M. Empirical Evaluation of Rectified Activations in Convolutional Network. arXiv:150500853 [cs, stat] [Internet]. 2015 Nov 27 [cited 2021 Jan 6];.

      9. He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Internet]. Las Vegas, NV, USA: IEEE; 2016 [cited 2021 Jan 6]. p. 770–8.

        • Ledig C.
        • Theis L.
        • Huszár F.
        • Caballero J.
        • Cunningham A.
        • Acosta A.
        • et al.
        Photo-realistic single image super-resolution using a generative adversarial network.
        in: In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4681-4690
      10. Smith LB, Heise D. Perceptual Similarity and Conceptual Structure. In: Advances in Psychology [Internet]. Elsevier; 1992 [cited 2021 Jan 6]. p. 233–72.

        • Simonyan K.
        • Zisserman A.
        Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:14091556 [cs].
        [Internet]. 2015; (Apr 10 [cited 2021 Jan 6])
        • Krizhevsky A.
        • Sutskever I.
        • Hinton G.E.
        ImageNet classification with deep convolutional neural networks.
        Commun ACM. 2017; 60: 84-90
      11. Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980. 2014;.

        • Wang Z.
        • Bovik A.C.
        • Sheikh H.R.
        • Simoncelli E.P.
        Image quality assessment: from error visibility to structural similarity.
        IEEE Trans Image Process. 2004 Apr; 13: 600-612
        • Lorch B.
        • Vaillant G.
        • Baumgartner C.
        • Bai W.
        • Rueckert D.
        • Maier A.
        Automated Detection of Motion Artefacts in MR Imaging Using Decision Forests.
        Journal of Medical Engineering. 2017 Jun; 11: 1-9
        • Song H.K.
        • Dougherty L.
        k-Space weighted image contrast (KWIC) for contrast manipulation in projection reconstruction MRI.
        Magn Reson Med. 2000; 44: 825-832
      12. Yang Q, Yan P, Kalra MK, Wang G. CT Image Denoising with Perceptive Deep Neural Networks. arXiv:170207019 [cs] [Internet]. 2017 Feb 22 [cited 2021 Jan 6];.

      13. Ledig C, Theis L, Huszar F, Caballero J, Cunningham A, Acosta A, et al. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. arXiv:160904802 [cs, stat] [Internet]. 2017 May 25 [cited 2021 Jan 17];.

        • Nixon M.
        • Aguado A.
        Feature extraction and image processing for computer vision.
        Academic press, 2019
        • Zhang R.
        • Isola P.
        • Efros A.A.
        • Shechtman E.
        • Wang O.
        The unreasonable effectiveness of deep features as a perceptual metric.
        in: In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 586-595
        • Deng M.
        • Goy A.
        • Li S.
        • Arthur K.
        • Barbastathis G.
        Probing shallower: perceptual loss trained Phase Extraction Neural Network (PLT-PhENN) for artifact-free reconstruction at low photon budget.
        Opt Express. 2020; 28: 2511