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 Concept Videos

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

5.1K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
5.1K

You might also read

Related Articles

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

Sort by
Same author

MoS<sub>2</sub>-loaded cholesteric liquid crystal microcapsules for NIR responsive thermochromism.

Lab on a chip·2026
Same author

QTL mapping of fruit sugar and acid traits in the F<sub>1</sub> generation of jujube (Ziziphus jujuba Mill.).

BMC plant biology·2026
Same author

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

IEEE transactions on neural networks and learning systems·2026
Same author

The T2T genome assembly of Ziziphus jujuba 'Huizao' and pan-genome analyses provide insights into fruit texture diversity in jujube.

Molecular horticulture·2026
Same author

Impact of Harvest Timing and Stir-Frying on the Bioactive Compounds, Bioactivities, and Flavor of <i>Ziziphi Spinosae Semen</i>: An Integrated Analysis via GC-IMS, Electronic Sensors, and <i>Caenorhabditis elegans</i> Model.

Plants (Basel, Switzerland)·2026
Same author

Dual regime of flowering time and pollination enhances pollen tube development in <i>Ziziphus</i>.

Horticulture research·2026

Related Experiment Video

Updated: Jun 29, 2025

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
10:06

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

12.9K

Spatial attention-based implicit neural representation for arbitrary reduction of MRI slice spacing.

Xin Wang1, Sheng Wang1, Honglin Xiong2

  • 1School of Biomedical Engineering, Shanghai Jiao Tong University, 200030, Shanghai, China.

Medical Image Analysis
|April 3, 2024
PubMed
Summary

This study introduces a Spatial Attention-based Implicit Neural Representation (SA-INR) network to improve through-plane resolution in magnetic resonance (MR) images. The novel method reconstructs MR images with arbitrary inter-slice spacing, enhancing visualization and diagnosis.

Keywords:
Arbitrary-scale super-resolutionImplicit representationMagnetic resonance imaging

More Related Videos

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.0K

Related Experiment Videos

Last Updated: Jun 29, 2025

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
10:06

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

12.9K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.0K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neuroscience

Background:

  • 2D Magnetic Resonance (MR) imaging protocols often feature large inter-slice spacing, leading to reduced through-plane resolution.
  • Super-resolution techniques can improve MR image resolution but typically require fixed scaling factors, limiting adaptability to varying clinical scan parameters.
  • Enhancing through-plane resolution is crucial for advanced visualization and computer-aided diagnosis in clinical MR imaging.

Purpose of the Study:

  • To develop a novel super-resolution method for Magnetic Resonance (MR) images that can handle arbitrary inter-slice spacing.
  • To improve the through-plane resolution of MR images for better visualization and computer-aided diagnosis.
  • To introduce a flexible and efficient deep learning approach for MR image super-resolution.

Main Methods:

  • Proposed a Spatial Attention-based Implicit Neural Representation (SA-INR) network to represent MR images as continuous functions of 3D coordinates.
  • Implemented a local-aware spatial attention mechanism to accurately model voxel relationships within a larger receptive field.
  • Introduced a gradient-guided gating mask to enhance computational efficiency by selectively applying attention mechanisms.

Main Results:

  • The SA-INR network demonstrated superior performance in reconstructing MR images with arbitrary inter-slice spacing compared to existing methods.
  • Evaluations on the HCP-1200 dataset and a clinical knee MR dataset confirmed the method's effectiveness.
  • The proposed approach successfully enhanced the through-plane resolution of MR images.

Conclusions:

  • The SA-INR network offers a flexible and effective solution for super-resolution in MR imaging, addressing limitations of fixed scaling factors.
  • The method shows significant potential for improving clinical MR image quality, aiding in downstream diagnostic tasks.
  • Implicit neural representations combined with spatial attention provide a powerful framework for arbitrary resolution enhancement in medical imaging.