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

¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)01:20

¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)

1.3K
When proton-coupled carbon-13 spectra are simplified by a broadband proton decoupling technique, structural information about the coupled protons is lost. Distortionless enhancement by polarization transfer (DEPT) is a technique that provides information on the number of hydrogens attached to each carbon in a molecule. While the DEPT experiment utilizes complex pulse sequences, the pulse delay and flip angle are specifically manipulated. The resulting signals have different phases depending on...
1.3K

You might also read

Related Articles

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

Sort by
Same author

Trends of HIV, hepatitis C virus and syphilis seroprevalence among injection and non-injection drug users in southwestern China, 2010-2017.

AIDS care·2020
Same author

Chandler-Loop surveyed blood compatibility and dynamic blood triggered degradation behavior of Zn-4Cu alloy and Zn.

Materials science & engineering. C, Materials for biological applications·2020
Same author

Knockdown of Parkinson's disease-related gene ATP13A2 reduces tumorigenesis via blocking autophagic flux in colon cancer.

Cell & bioscience·2020
Same author

Diagnostics of skin features through 3D skin mapping based on electro-controlled deposition of conducting polymers onto metal-sebum modified surfaces and their possible applications in skin treatment.

Analytica chimica acta·2020
Same author

Spongy <i>p</i>-Toluenesulfonic Acid-doped Polypyrrole with Extraordinary Rate Performance as Durable Anodes of Sodium-Ion Batteries at Different Temperatures.

Langmuir : the ACS journal of surfaces and colloids·2020
Same author

NOD1/RIP2 signalling enhances the microglia-driven inflammatory response and undergoes crosstalk with inflammatory cytokines to exacerbate brain damage following intracerebral haemorrhage in mice.

Journal of neuroinflammation·2020

Related Experiment Video

Updated: May 3, 2026

Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking
14:21

Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking

Published on: August 6, 2013

18.2K

Multimodal feature-guided diffusion model for low-count PET image denoising.

Gengjia Lin1, Yuxi Jin2, Zhenxing Huang2

  • 1College of Computer Science and Engineering, Northeastern University, Shenyang, China.

Medical Physics
|March 18, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces MFG-Diff, a novel deep learning model that enhances low-count Positron Emission Tomography (LPET) images using Magnetic Resonance Imaging (MRI) data. The method effectively denoises LPET images, producing high-quality standard-count PET (SPET) images with improved accuracy and consistency.

Keywords:
Low‐count PET denoisingmultimodal feature‐guided diffusionphysical degradation simulation

More Related Videos

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
09:33

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

28.2K
Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images
09:21

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

12.1K

Related Experiment Videos

Last Updated: May 3, 2026

Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking
14:21

Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking

Published on: August 6, 2013

18.2K
Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
09:33

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

28.2K
Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images
09:21

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

12.1K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • Minimizing radiation exposure in Positron Emission Tomography (PET) imaging is crucial for patient safety.
  • Existing deep learning methods for low-count PET (LPET) image enhancement often fail to fully leverage complementary information from Magnetic Resonance Imaging (MRI).
  • Current multimodal fusion strategies in deep learning for PET image enhancement are limited in exploiting cross-modal information effectively.

Purpose of the Study:

  • To introduce MFG-Diff, a novel multimodal feature-guided diffusion model for denoising LPET images.
  • To fully utilize complementary information from MRI in the process of LPET image enhancement.
  • To improve the quality of PET images while minimizing radiation dose.

Main Methods:

  • MFG-Diff utilizes LPET images as the initial input, replacing random Gaussian noise in a diffusion model.
  • A novel degradation operator simulates the physical processes of PET imaging.
  • A cross-modal guided restoration network with multimodal feature fusion, cross-attention, and positional encoding is employed to integrate LPET and MRI features.

Main Results:

  • MFG-Diff demonstrated superior performance in qualitative, quantitative, and statistical evaluations compared to existing networks across various low-count scenarios (2.5% to 25%).
  • Generated PET images showed significant improvements: >20% increase in peak-signal-to-noise ratio, >16% increase in structural similarity index, and ~50% reduction in root mean square error at 2.5% count.
  • The generated PET images exhibited high correlation (Pearson coefficient 0.9924), consistency, and excellent quantitative agreement with standard-count PET (SPET) images.

Conclusions:

  • The proposed MFG-Diff method surpasses current state-of-the-art LPET denoising models.
  • MFG-Diff effectively generates high-quality SPET images from LPET data, maintaining correlation and consistency.
  • This approach offers a promising solution for radiation dose reduction in PET imaging without compromising image quality.