Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Super-resolution Fluorescence Microscopy

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...

You might also read

Related Articles

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

Sort by

Same author

Resveratrol-activated PI3K/AKT/mTOR signaling pathway attenuates ferroptosis by promoting NRF2/GPX4 metabolic pathway to mitigate IFN-gamma-mediated aplastic anemia.

Chinese medicine·2026

Same author

Renal Complement C3 Deposition is Associated with Glomerular Prothrombotic Milieu in Patients with IgA Nephropathy.

Journal of inflammation research·2026

Same author

Chronic kidney disease in women: Global trends and metabolic-cardiovascular associations.

Chinese medical journal·2026

Same author

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026

Same author

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026

Same author

On the Identifiability of Hybrid Deep Generative Models: Meta-Learning as a Solution.

Advances in neural information processing systems·2026

Search research articles

Related Experiment Video

Updated: Oct 6, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Unsupervised arterial spin labeling image superresolution via multiscale generative adversarial network.

Jianan Cui^1,2, Kuang Gong^2,3, Paul Han³

¹The State Key Laboratory of Modern Optical Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China.

Medical Physics

|January 20, 2022

Summary

This study introduces an unsupervised superresolution method using generative adversarial networks to enhance Arterial Spin Labeling (ASL) MRI images. The novel approach improves both spatial resolution and signal-to-noise ratio, outperforming existing techniques.

Keywords:

arterial spin labeling generative adversarial network super-resolution unsupervised learning

More Related Videos

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

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

Published on: March 28, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Oct 6, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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

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

Published on: March 28, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Area of Science:

Medical Imaging
Artificial Intelligence

Background:

Arterial Spin Labeling (ASL) MRI offers noninvasive measurement of cerebral blood flow (CBF).
Conventional ASL MRI suffers from low signal-to-noise ratio (SNR) and poor spatial resolution, limiting its clinical utility.
A method is needed to enhance ASL image quality without contrast agents or radiation.

Purpose of the Study:

To develop an unsupervised superresolution (SR) method to simultaneously improve spatial resolution and SNR of ASL MRI images.
To leverage generative adversarial networks (GANs) for enhanced ASL image reconstruction.

Main Methods:

Proposed an unsupervised, multiscale generative adversarial network (GAN) framework for ASL superresolution.
Incorporated T1-weighted MRI as a second-channel input to provide high-resolution prior information.
Included a low-pass-filter loss term to suppress noise in ASL images.
Evaluated the method using simulation studies and in vivo data from healthy subjects, comparing it against interpolation methods and Deep Image Prior (DIP).

Main Results:

The proposed GAN-based SR method significantly outperformed nearest neighbor, trilinear, and B-spline interpolation, as well as DIP, in both simulation and real-patient studies.
Achieved higher Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) compared to existing methods.
Generated ASL images with clearer structure boundaries, reduced noise, and sharper details, closely resembling high-quality reference scans.
Demonstrated artifact removal capabilities during superresolution.

Conclusions:

The unsupervised multiscale GAN framework effectively enhances ASL MRI by simultaneously improving spatial resolution and reducing noise.
The method shows superior performance over conventional techniques for ASL image superresolution.
The inclusion of T1-weighted images and a low-pass-filter loss term are crucial for the method's success.