Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 3, 2026

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

FreeTune4D: Anatomy-Aware 4D-MRI Motion Reconstruction Benchmark and Free Fine-Tuning Framework.

Peilin Wang, Fan Zhang, Chenyang Liu

    IEEE Journal of Biomedical and Health Informatics
    |June 1, 2026
    PubMed
    Summary

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    The integrative role of the microbiome in systemic immuno-inflammatory aberrations.

    Folia microbiologica·2026
    Same author

    TurboID-Based Proximity Labeling Map Reveals the Protein Interaction Network and Anti-Viral Mechanism Against Influenza A H1N1.

    FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2026
    Same author

    Roles of m<sup>6</sup>A erasers FTO and ALKBH5 in drug resistance of hepatocellular carcinoma: mechanisms and clinical implications.

    Gene·2026
    Same author

    AADFNet: An adaptive asymmetric dual-branch fusion network for background-robust grasping.

    Neural networks : the official journal of the International Neural Network Society·2026
    Same author

    Solvent- and Hydrogen-Free Upcycling of Polystyrene by Layered Double Oxides.

    Small (Weinheim an der Bergstrasse, Germany)·2026
    Same author

    Gut microbiota dysbiosis and osteoporosis: pathogenesis and novel intervention strategies.

    Future microbiology·2026
    Same journal

    An Ultra-Lightweight Cross-scale Attention Mamba Network for Accurate Skin Lesion Segmentation.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    Explanation-Guided Reconstruction of Missing Clinical Features for Survival Prediction in Pancreatic Cancer.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    stDGCN: A dual-augmentation graph convolutional network for identifying spatial domains with attention mechanism.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    Patient-specific Biomechanical Investigation of Percutaneous Pulmonary Valves: Towards the Integration of Routinely Acquired Clinical Data and Fluid-structure Interaction Simulations.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    Cross-subject fMRI-to-Image with Visual-cortex 2D Representation and Pre-Training.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    PGCASurv: A Prior-Guided Cross-Attention Framework for Dynamic Survival Model with Longitudinal Data.

    IEEE journal of biomedical and health informatics·2026
    See all related articles
    This summary is machine-generated.

    Researchers developed FreeTune4D, an anatomy-aware framework for abdominal four-dimensional magnetic resonance imaging (4D MRI) motion reconstruction. New large-scale digital phantom datasets improve model generalizability and performance, outperforming existing methods in clinical validation.

    Area of Science:

    • Medical Imaging
    • Machine Learning
    • Biomedical Engineering

    Background:

    • Deep learning and cross-modality methods have improved abdominal 4D MRI acquisition speed and reduced artifacts.
    • Limited datasets and lack of anatomical awareness hinder generalizable training and evaluation of 4D MRI motion reconstruction models.
    • Existing methods struggle with performance on unseen datasets exhibiting varying pixel distributions.

    Purpose of the Study:

    • To address limitations in 4D MRI motion reconstruction by creating large-scale, diverse, and anatomically labeled digital phantom datasets.
    • To develop and validate an anatomy-aware deep learning framework for robust and generalizable 4D MRI motion reconstruction.
    • To improve organ-level motion accuracy and structural consistency in abdominal 4D MRI.

    Main Methods:

    More Related Videos

    Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
    10:44

    Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

    Published on: June 21, 2024

    Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
    06:56

    Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

    Published on: January 7, 2021

    Related Experiment Videos

    Last Updated: Jun 3, 2026

    Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
    05:05

    Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

    Published on: November 23, 2019

    Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
    10:44

    Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

    Published on: June 21, 2024

    Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
    06:56

    Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

    Published on: January 7, 2021

    • Established Digital4D-1M (1 million samples) and Digital4D-900 (900 samples) datasets with diverse physiological parameters and anatomical labels.
    • Proposed FreeTune4D, an anatomy-aware 4D MRI motion reconstruction framework integrating vertebral stability and organ-level anatomical priors.
    • Employed a free fine-tuning strategy for training the affine-to-deformable framework.

    Main Results:

    • FreeTune4D, trained on large-scale digital phantoms, surpassed state-of-the-art (SOTA) methods on the Digital4D-900 benchmark for affine and deformable motion reconstruction.
    • In a real patient cohort (133 cases), FreeTune4D demonstrated consistent superiority over SOTA methods across metrics and modalities.
    • Achieved superior organ-level motion accuracy and structural consistency in clinical validation.

    Conclusions:

    • The developed datasets and FreeTune4D framework significantly advance generalizable 4D MRI motion reconstruction.
    • FreeTune4D exhibits robustness and clinical potential, outperforming existing methods in both phantom and real-world patient data.
    • The study provides valuable resources (datasets, code, model) for future research in 4D MRI motion reconstruction.