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 Videos

Enhancing Generative Models for Modality Imputation of 3-D MRIs via Consistency-Aware Refinement and Super-Resolution

Zhiyun Song, Xin Wang, Honglin Xiong

    IEEE Transactions on Neural Networks and Learning Systems
    |June 11, 2026
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    Super-resolution Fluorescence Microscopy01:37

    Super-resolution Fluorescence Microscopy

    Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been developed.

    You might also read

    Related Articles

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

    Sort by
    Same author

    Correction: Study of the effects and mechanism of allogeneic platelet-rich plasma gel on layered skin flaps.

    Scientific reports·2026
    Same author

    Quercetin attenuates skin inflammation and fibrosis in systemic sclerosis by targeting the RELA/c-Jun axis to suppress th17 cell responses.

    Frontiers in immunology·2026
    Same author

    Interface engineering constructs Co-O<sub>V</sub>-Ce/La interfacial sites with dual "capture-clear" functionality to enhance water-resistant CO oxidation performance of Co<sub>3</sub>O<sub>4</sub> catalysts.

    Journal of colloid and interface science·2026
    Same author

    A 2-GS/s 35.9-fJ/conv.-step Voltage-Time Hybrid Pipelined ADC with Digital Background Calibration in 28-nm CMOS.

    Micromachines·2026
    Same author

    CT-based subchondral bone microstructural analysis in knee osteoarthritis via MR-guided distillation learning.

    Frontiers in radiology·2026
    Same author

    A prediction model for the risk of developing HFpEF during hospitalization in patients with acute myocardial infarction.

    International journal of cardiology. Heart & vasculature·2026

    This study enhances 2-D generative models for 3-D magnetic resonance image (MRI) reconstruction. The novel method improves inter-slice consistency and resolution, overcoming limitations of current generative adversarial networks (GANs) and diffusion models (DFs).

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Computer Vision

    Background:

    • Reconstructing missing modalities in magnetic resonance images (MRIs) is challenging.
    • Current 2-D generative models (GANs, DFs) synthesize high-fidelity slices but struggle with 3-D consistency and resolution.
    • Varying inter-slice resolutions in 2-D datasets further degrade 3-D MRI reconstruction quality.

    Purpose of the Study:

    • To propose a novel fine-tuning strategy for enhancing 2-D generative models for 3-D MRI reconstruction.
    • To improve inter-slice consistency and resolution in synthesized 3-D MRI data.
    • To address limitations of existing generative approaches in medical imaging.

    Main Methods:

    • Developed a novel attention-based module to enhance contextual information across adjacent slices for generative models.

    Related Experiment Videos

  • Incorporated self-supervised super-resolution (SR) to address varying inter-slice resolutions.
  • Designed an uncertainty modulation strategy to optimize the use of super-resolved images for high-quality reconstruction.

    • Main Results:

    • The proposed fine-tuning strategy significantly enhances 3-D MRI reconstruction quality.
    • Attention-based module improves inter-slice consistency in generated 3-D images.
    • Uncertainty modulation with SR effectively improves inter-plane resolution and reduces artifacts.

    Conclusions:

    • The novel fine-tuning strategy offers a flexible and superior approach for 3-D multimodal MRI synthesis.
    • The method demonstrates effectiveness across different generative models (GANs, DFs) and synthesis tasks (supervised, unsupervised).
    • This work advances generative modeling for high-fidelity 3-D medical image reconstruction.