Retrospective MoCo in Liver MRI via U-Net and GAN
Research Article
Open Access
CC BY

Retrospective MoCo in Liver MRI via U-Net and GAN

Yihan Che 1*
1 Oregon Episcopal School
*Corresponding author: leo_cheyihan@qq.com
Published on 2 October 2025
Journal Cover
TNS Vol.139
ISSN (Print): 2753-8826
ISSN (Online): 2753-8818
ISBN (Print): 978-1-80590-395-6
ISBN (Online): 978-1-80590-396-3
Download Cover

Abstract

Liver MRI plays a crucial role in diagnosing various diseases; however, motion artifacts caused by patient movement during scanning can significantly degrade image quality, leading to misdiagnoses and additional scanning costs. This study explores a deep learning based retrospective motion correction (MoCo) approach using U-Net and Generative Adversarial Networks (GANs) to reduce motion artifacts in liver MRI images. Motion artifacts—including regular moving motion, ghosting effects, and spiking distortions—are simulated using TorchIO to generate training and validation datasets. The proposed model integrates Fully Convolutional Networks (FCNs), U-Net, and Patch-GAN to enhance feature learning through adversarial training. Additionally, perceptual loss is incorporated to test to improve the model’s ability to retain high-level details. The performance of the models is evaluated using the Structural Similarity Index (SSIM) to quantify image quality improvements. The study aims to demonstrate that deep learning-based MoCo can enhance liver MRI interpretation accuracy, reduce the need for repeated scans, and improve diagnosing efficiency while minimizing costs associated with motion artifacts.

Keywords:

Liver MRI, Motion Artifacts, Deep Learning, U-Net & GANs, Structural Similarity Index (SSIM)

View PDF
Che,Y. (2025). Retrospective MoCo in Liver MRI via U-Net and GAN. Theoretical and Natural Science,139,40-48.

References

[1]. Journal of the American College of Radiology - Motion artifact statistics in liver MRI.

[2]. Health Imaging - Economic impact of motion artifacts in MRI.

[3]. Anesthesia Experts - Cost analysis of MRI re-scans.

[4]. MRI Master - Navigator sequence limitations.

[5]. AJR Online - Pediatric MRI motion challenges.

[6]. Pipe JG, et al. Periodically Rotated Overlapping Parallel Lines with Enhanced Reconstruction (PROPELLER): improved motion-corrected imaging of the upper abdomen. AJR 2008; 191: 188-197.

[7]. Feng L, et al. XD-GRASP: Golden-Angle Radial MRI with Reconstruction of Extra Motion Dimensions. Magn Reson Med 2016; 75: 775-788.

[8]. Zhu Y, et al. Stacked U-Nets with self-assisted priors toward robust correction of rigid motion artifacts in 3D brain MRI. NeuroImage 2022.

[9]. Jin K, et al. Two-stage dense residual network for motion artifact reduction on dynamic-contrast-enhanced liver MRI. Med Image Anal 2023.

[10]. Johnson PM, Drangova M. Conditional generative adversarial network for 3-D rigid-body motion correction in MRI (MoCo-cGAN). Magn Reson Med 2019; 82: 901-913.

[11]. Al-Haj Hemidi Z, et al. IM-MoCo: Self-supervised MRI Motion Correction using Motion-Guided Implicit Neural Representations. arXiv 2024.

[12]. Lin Y, et al. PI-MoCoNet: A Physics-Informed Deep Learning Model for MRI Brain Motion Correction. arXiv 2025.

[13]. Ebner M, et al. NiftyMIC: Motion Correction and Volumetric Image Reconstruction of 2-D Ultra-fast MRI. GitHub toolkit, 2018.

References

[1]. Journal of the American College of Radiology - Motion artifact statistics in liver MRI.

[2]. Health Imaging - Economic impact of motion artifacts in MRI.

[3]. Anesthesia Experts - Cost analysis of MRI re-scans.

[4]. MRI Master - Navigator sequence limitations.

[5]. AJR Online - Pediatric MRI motion challenges.

[6]. Pipe JG, et al. Periodically Rotated Overlapping Parallel Lines with Enhanced Reconstruction (PROPELLER): improved motion-corrected imaging of the upper abdomen. AJR 2008; 191: 188-197.

[7]. Feng L, et al. XD-GRASP: Golden-Angle Radial MRI with Reconstruction of Extra Motion Dimensions. Magn Reson Med 2016; 75: 775-788.

[8]. Zhu Y, et al. Stacked U-Nets with self-assisted priors toward robust correction of rigid motion artifacts in 3D brain MRI. NeuroImage 2022.

[9]. Jin K, et al. Two-stage dense residual network for motion artifact reduction on dynamic-contrast-enhanced liver MRI. Med Image Anal 2023.

[10]. Johnson PM, Drangova M. Conditional generative adversarial network for 3-D rigid-body motion correction in MRI (MoCo-cGAN). Magn Reson Med 2019; 82: 901-913.

[11]. Al-Haj Hemidi Z, et al. IM-MoCo: Self-supervised MRI Motion Correction using Motion-Guided Implicit Neural Representations. arXiv 2024.

[12]. Lin Y, et al. PI-MoCoNet: A Physics-Informed Deep Learning Model for MRI Brain Motion Correction. arXiv 2025.

[13]. Ebner M, et al. NiftyMIC: Motion Correction and Volumetric Image Reconstruction of 2-D Ultra-fast MRI. GitHub toolkit, 2018.

Cite this article

Che,Y. (2025). Retrospective MoCo in Liver MRI via U-Net and GAN. Theoretical and Natural Science,139,40-48.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

About volume

Volume title: Proceedings of ICBioMed 2025 Symposium: AI for Healthcare: Advanced Medical Data Analytics and Smart Rehabilitation

ISBN: 978-1-80590-395-6(Print) / 978-1-80590-396-3(Online)
Editor: Alan Wang
Conference website: https://2025.icbiomed.org/auckland.html
Conference date: 17 October 2025
Series: Theoretical and Natural Science
Volume number: Vol.139
ISSN: 2753-8818(Print) / 2753-8826(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:

1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.

2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.

3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).

For authors
For editors
For reviewers

Cookies are used by this site.
Copyright © 2024 EWA Publishing, its licensors, and contributors. All rights reserved, including text and data mining, AI training, and similar technologies.