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

Intracellular Signaling Cascades01:24

Intracellular Signaling Cascades

53.5K
Once a ligand binds to a receptor, the signal is transmitted through the membrane and into the cytoplasm. The continuation of a signal in this manner is called signal transduction. Signal transduction only occurs with cell-surface receptors, which cannot interact with most components of the cell, such as DNA. Only internal receptors can interact directly with DNA in the nucleus to initiate protein synthesis. When a ligand binds to its receptor, conformational changes occur that affect the...
53.5K
Poisson's Ratio01:23

Poisson's Ratio

1.1K
Poisson's ratio is a material property that indicates their stress response. It explains the connection between the elongation or compression a material undergoes in the direction of an applied force and the contraction or expansion it experiences perpendicular to that force. When a slender bar is loaded axially, it stretches in the direction of the force and contracts laterally. Poisson's ratio is the negative ratio of this lateral contraction to the axial elongation. The negative sign...
1.1K
Odds Ratio01:09

Odds Ratio

1.9K
The odds ratio (OR) is a statistical measure used extensively in epidemiology and research to quantify the strength of association between exposure and outcome across different groups. Unlike relative risk, which compares the probabilities of an event occurring, the odds ratio compares the odds of an event occurring in the exposed group to the odds of it occurring in the unexposed group. The odds, in this context, are calculated as the probability of the event happening divided by the...
1.9K
Hazard Ratio01:12

Hazard Ratio

602
The hazard ratio (HR) is a widely used measure in clinical trials to compare the risk of events, such as death or disease recurrence, between two groups over time. It reflects the ratio of hazard rates—the instantaneous risk of the event occurring—between a treatment group and a control group. This measure provides valuable insights into the relative effectiveness of a treatment by assessing how the risk of an event differs between the two groups.
For example, in a clinical trial...
602
Normal Stress01:19

Normal Stress

1.4K
Normal stress is a type of stress that occurs when forces act perpendicular, or normal, to a material's cross-sectional area. This stress often arises in structures when subjected to axial loading, which is the application of force along the axis of an object. A practical example of this can be found in bridge truss members.
When a rod is under axial loading, the internal forces and corresponding stress are normal to the plane of the section, so it is termed normal stress. It's important to...
1.4K
Normal Distribution01:11

Normal Distribution

17.2K
The normal, a continuous distribution, is the most important of all the distributions. Its graph is a bell-shaped symmetrical curve, which is observed in almost all disciplines. Some of these include psychology, business, economics, the sciences, nursing, and, of course, mathematics. Some instructors may use the normal distribution to help determine students’ grades. Most IQ scores are normally distributed. Often real-estate prices fit a normal distribution. The normal distribution is...
17.2K

You might also read

Related Articles

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

Sort by
Same author

Comparison of deep learning and particle smoother EM methods for estimation of Rb-82 myocardial perfusion PET kinetic parameters.

Medical physics·2026
Same author

Harnessing the potential of γδ T cells through engineering and combination treatment for cancer therapies.

Nature communications·2026
Same author

Maximum likelihood estimation yields accurate line-of-response assignment for positron + prompt gamma ray events in multiplexed PET (mPET).

Biomedical physics & engineering express·2026
Same author

Influence of scintillation light confinement on depth-of-interaction measurement performance in a single-ended readout PET detector.

Physics in medicine and biology·2026
Same author

Intracranial meningioma at foramen magnum presenting as bow hunter's syndrome via V4 segment compression: illustrative case.

Journal of neurosurgery. Case lessons·2026
Same author

An Investigation into Planned Dose Preservation of Biology-guided Radiotherapy Under Various Radiopharmaceutical Uptake Conditions.

Technology in cancer research & treatment·2026

Related Experiment Video

Updated: Jan 30, 2026

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.9K

Generative deep learning synthesizes high signal-to-noise ratio sensitivity maps for PET from low count direct

Mojtaba Jafaritadi1, Andrew Groll1, Myungheon Chin1,2

  • 1Department of Radiology, Stanford University, Stanford, CA, United States of America.

Physics in Medicine and Biology
|January 28, 2026
PubMed
Summary

A novel deep learning framework significantly improves positron emission tomography (PET) image normalization. This method generates high signal-to-noise ratio (SNR) normalization factors from low-count data, enabling faster and more accurate PET scans.

Keywords:
direct normalizationgenerative adversarial networkimage reconstructionpositron emission tomography

More Related Videos

Quantifying X-Ray Fluorescence Data Using MAPS
14:58

Quantifying X-Ray Fluorescence Data Using MAPS

Published on: February 17, 2018

11.3K
A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

4.5K

Related Experiment Videos

Last Updated: Jan 30, 2026

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.9K
Quantifying X-Ray Fluorescence Data Using MAPS
14:58

Quantifying X-Ray Fluorescence Data Using MAPS

Published on: February 17, 2018

11.3K
A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

4.5K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Nuclear Medicine

Background:

  • Accurate normalization is crucial for positron emission tomography (PET) image quality, correcting for detector efficiency variations.
  • Conventional direct normalization requires extensive scan times due to low-activity sources and high counts per line of response (LOR).

Purpose of the Study:

  • To develop a deep learning framework for generating high signal-to-noise ratio (SNR) normalization factors and sensitivity maps from low-count PET data.
  • To improve the efficiency and accuracy of PET image normalization, particularly for PET inserts in MRI systems.

Main Methods:

  • An attention-guided Pix2Pix conditional generative adversarial network (cGAN) was developed to process low-count direct normalization data.
  • The framework generates synthetic normalization factors and sensitivity maps, aiming to maximize detector efficiencies and reduce artifacts.

Main Results:

  • The deep learning model successfully generated high SNR normalization factors from low-count data (1-15% of full scan).
  • PET images reconstructed using synthetic sensitivity maps from 15% count statistics closely matched those from high-count data (PSNR: 30.68±0.31, SSIM: 0.95±0.002).
  • Unprocessed low-count sensitivity maps resulted in significantly poorer image quality (PSNR: 15.93±0.426, SSIM: 0.54±0.013).

Conclusions:

  • Deep learning offers a fast and effective approach for high SNR direct normalization in PET imaging.
  • This method enables accurate PET image reconstruction using significantly reduced normalization scan times.
  • The framework effectively removes detector block patterns and ring artifacts, enhancing overall image quality.