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

Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

7.1K
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...
7.1K

You might also read

Related Articles

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

Sort by
Same author

Bridging the phenotype-target gap for molecular generation via multi-objective reinforcement learning.

Bioinformatics (Oxford, England)·2026
Same author

Highly accurate calibration of particle number portable emissions measurement systems (PN-PEMS) via actual soot charging probability correction.

Journal of environmental sciences (China)·2026
Same author

Dual-parameter ultrasonic guided wave packet characterization for ice thickness prediction and excitation signal optimization.

Ultrasonics·2026
Same author

Photocatalytic proximity labeling in primary samples.

Current opinion in chemical biology·2026
Same author

Testing Weismann's germ plasm theory in Arabidopsis.

Current biology : CB·2026
Same author

Fabrication of Wear-Resistant and Anti-Reflection Surfaces Based on Armor-Protected Nanocone Structures.

Micromachines·2026

Related Experiment Video

Updated: Aug 7, 2025

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
17:06

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Published on: November 8, 2012

26.3K

Semi-supervised super-resolution of diffusion-weighted images based on multiple references.

Haotian Guo1, Lihui Wang1, Yulong Gu1

  • 1Medical College, Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, College of Computer Science and Technology, State Key Laboratory of Public Big Data, Guizhou University, Guiyang, China.

NMR in Biomedicine
|March 13, 2023
PubMed
Summary

This study introduces a novel semi-supervised method for reconstructing high-resolution diffusion tensor images, improving image quality and diffusion metrics even with limited matched data.

Keywords:
CycleGANdiffusion tensor imagingdiffusion-weighted imagingmultiple referencessemi-supervised learningsuper-resolution reconstruction

More Related Videos

Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy
07:26

Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy

Published on: March 28, 2025

482
Diffusion Imaging in the Rat Cervical Spinal Cord
10:46

Diffusion Imaging in the Rat Cervical Spinal Cord

Published on: April 7, 2015

11.8K

Related Experiment Videos

Last Updated: Aug 7, 2025

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
17:06

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Published on: November 8, 2012

26.3K
Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy
07:26

Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy

Published on: March 28, 2025

482
Diffusion Imaging in the Rat Cervical Spinal Cord
10:46

Diffusion Imaging in the Rat Cervical Spinal Cord

Published on: April 7, 2015

11.8K

Area of Science:

  • Medical Imaging
  • Neuroimaging
  • Computational Neuroscience

Background:

  • Diffusion tensor imaging (DTI) spatial resolution is often reduced for faster acquisition.
  • Supervised deep learning methods for DTI super-resolution (SR) require matched low-resolution (LR) and high-resolution (HR) image pairs, which are difficult to obtain.
  • Existing unsupervised methods may not fully leverage available prior information.

Purpose of the Study:

  • To develop a semi-supervised super-resolution (SR) method for diffusion-weighted (DW) images that overcomes the scarcity of matched LR-HR training data.
  • To improve the spatial resolution of DTI scans for enhanced visualization and quantitative analysis.
  • To leverage multi-subject reference data for more robust SR reconstruction.

Main Methods:

  • Proposed a multiple-reference SR (MRSR) method utilizing a residual-like network to incorporate prior information from multiple HR reference images.
  • Employed a CycleGAN-based semi-supervised strategy to train the network using 30% matched and 70% unmatched LR-HR image pairs.
  • Evaluated performance against state-of-the-art (SOTA) methods on the Human Connectome Project (HCP) dataset.

Main Results:

  • MRSR significantly improved the mean Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) of DW images compared to SOTA methods.
  • Achieved improvements of at least 14.3%/28.8% (PSNR/SSIM) over unsupervised methods and 1%/1.4% over supervised methods.
  • Demonstrated accurate reconstruction of diffusion metrics, with fiber orientations deviating by ~6.28° and Root Mean Square Errors (RMSEs) for key diffusion metrics below 5.7% relative to ground truth.

Conclusions:

  • The proposed MRSR method effectively reconstructs high-resolution diffusion tensor images using a limited number of matched image pairs.
  • The combination of multiple reference images and CycleGAN-based semi-supervised learning is crucial for the method's success.
  • This approach offers a viable solution for enhancing DTI spatial resolution in clinical and research settings.