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: Oct 24, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

Domain knowledge augmentation of parallel MR image reconstruction using deep learning.

Kamlesh Pawar1, Gary F Egan2, Zhaolin Chen3

  • 1Monash Biomedical Imaging, Monash University, Melbourne, Australia; School of Psychological Sciences, Monash University, Melbourne, Australia.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|August 14, 2021
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

Population-based Brain Templates for Ultra-Low-Field MRI.

Scientific data·2026
Same author

PeFoMed: Parameter efficient fine-tuning of multimodal large language models for medical CXR.

Scientific reports·2026
Same author

Cyclic Self-Supervised Diffusion for Ultra Low-field to High-field MRI Synthesis.

IEEE transactions on medical imaging·2026
Same author

NUP85 Mediates Endoplasmic Reticulum Stress through the USP47/ASK1 Signaling Pathway to Regulate the Progression of Liver Fibrosis.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Identification of Biological Subtypes of Friedreich Ataxia with Structural MRI-based Machine Learning.

Radiology·2026
Same author

Synergistic action of human milk oligosaccharides and lactoferrin enhances neurodevelopment in piglets: evidence from MRS based metabolic profiling.

Nutritional neuroscience·2026
Same journal

Self-supervised isotropic reconstruction for abnormality detection in anisotropic MRI.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

WDBDM: Wavelet-based dual-branch diffusion model for low-dose CT and PET denoising.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

ScribSAM: A robust scribble-supervised framework for spatiotemporal segmentation of breast lesions in ultrasound videos.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

Anatomically and biochemically guided deep image prior for sodium MRI denoising.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

Segment Anything Model for medical image segmentation: A review.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

HiCAF-Net: A Hierarchical Cross-Attention Fusion framework for cross-cancer subtype classification using histopathological and genomic data.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
See all related articles
This summary is machine-generated.

This study introduces a deep learning (DL) method for faster magnetic resonance (MR) imaging. By integrating parallel imaging knowledge, it achieves accurate and stable MR image reconstruction without artifacts.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Accelerated magnetic resonance (MR) imaging is crucial for reducing scan times and improving patient comfort.
  • Current deep learning (DL) methods for MR image reconstruction face challenges in accuracy, stability, and artifact generation.
  • Integrating domain knowledge into DL models offers a promising approach to enhance reconstruction quality.

Purpose of the Study:

  • To develop and validate a novel deep learning method for accelerated MR imaging reconstruction.
  • To improve the accuracy, stability, and artifact-free nature of MR images reconstructed from undersampled data.
  • To leverage domain knowledge from parallel imaging within DL networks for enhanced performance.

Main Methods:

  • A deep learning (DL) model was developed incorporating parallel imaging domain knowledge.
Keywords:
Convolutional neural networkDeep learning image reconstructionImage processingMR image reconstructionParallel MRI

More Related Videos

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

335

Related Experiment Videos

Last Updated: Oct 24, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

335
  • A novel loss function combining mean absolute error, structural similarity, and Sobel edge loss was employed.
  • The DL model utilized both raw MR measurements and parallel imaging reconstructions as inputs.

    • Main Results:

    • The proposed DL method significantly outperformed state-of-the-art methods across six MRI contrasts in structural similarity, peak signal-to-noise ratio, and normalized mean squared error.
    • Validation on unseen data demonstrated artifact-free image reconstruction.
    • Stability analysis confirmed robustness against input perturbations and varying undersampling ratios.

    Conclusions:

    • Incorporating parallel imaging domain knowledge into DL effectively regularizes MR image reconstruction.
    • The proposed method achieves accurate, stable, and artifact-free accelerated MR imaging.
    • This approach represents a significant advancement in DL-based medical image enhancement.