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

Positron Emission Tomography01:29

Positron Emission Tomography

6.5K
Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
6.5K

You might also read

Related Articles

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

Sort by
Same author

An exploratory study of explainable deep learning for predicting bone mineral density using clavicle features on chest radiographs: A multi-task approach with regression and segmentation.

Journal of applied clinical medical physics·2025
Same author

Limited-angle SPECT image reconstruction using deep image prior.

Physics in medicine and biology·2025
Same author

Exploiting network optimization stability for enhanced PET image denoising using deep image prior.

Physics in medicine and biology·2025
Same author

Two-step optimization for accelerating deep image prior-based PET image reconstruction.

Radiological physics and technology·2024
Same author

ReconU-Net: a direct PET image reconstruction using U-Net architecture with back projection-induced skip connection.

Physics in medicine and biology·2024
Same author

Correction to: Deep learning-based PET image denoising and reconstruction: a review.

Radiological physics and technology·2024

Related Experiment Video

Updated: Nov 10, 2025

Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET
09:03

Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET

Published on: October 22, 2019

10.5K

Deep learning-based attenuation correction for brain PET with various radiotracers.

Fumio Hashimoto1, Masanori Ito2, Kibo Ote3

  • 1Central Research Laboratory, Hamamatsu Photonics K.K., Hamamatsu, 434-8601, Japan. fumio.hashimoto@crl.hpk.co.jp.

Annals of Nuclear Medicine
|April 3, 2021
PubMed
Summary

A novel deep learning framework synthesizes transmission computed tomography (TCT) images for attenuation correction (AC) in brain positron emission tomography (PET) imaging. This deep AC approach improves quantitative accuracy using a convolutional neural network (CNN) trained on diverse radiotracers.

Keywords:
Attenuation correctionConvolutional neural networksDeep learningPositron emission tomography (PET)

More Related Videos

A Dual Tracer PET-MRI Protocol for the Quantitative Measure of Regional Brain Energy Substrates Uptake in the Rat
15:10

A Dual Tracer PET-MRI Protocol for the Quantitative Measure of Regional Brain Energy Substrates Uptake in the Rat

Published on: December 28, 2013

7.2K
Studying Metabolic Brain Connectivity Using 2-Deoxy-2-[18F]Fluoro-D-Glucose Dynamic Positron Emission Tomography at the Single-subject Level
07:28

Studying Metabolic Brain Connectivity Using 2-Deoxy-2-[18F]Fluoro-D-Glucose Dynamic Positron Emission Tomography at the Single-subject Level

Published on: January 24, 2025

533

Related Experiment Videos

Last Updated: Nov 10, 2025

Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET
09:03

Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET

Published on: October 22, 2019

10.5K
A Dual Tracer PET-MRI Protocol for the Quantitative Measure of Regional Brain Energy Substrates Uptake in the Rat
15:10

A Dual Tracer PET-MRI Protocol for the Quantitative Measure of Regional Brain Energy Substrates Uptake in the Rat

Published on: December 28, 2013

7.2K
Studying Metabolic Brain Connectivity Using 2-Deoxy-2-[18F]Fluoro-D-Glucose Dynamic Positron Emission Tomography at the Single-subject Level
07:28

Studying Metabolic Brain Connectivity Using 2-Deoxy-2-[18F]Fluoro-D-Glucose Dynamic Positron Emission Tomography at the Single-subject Level

Published on: January 24, 2025

533

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiochemistry

Background:

  • Accurate attenuation correction (AC) is vital for quantitative positron emission tomography (PET) imaging.
  • Acquiring accurate μ-maps for AC in brain PET scanners lacking AC mechanisms is challenging.
  • Deep learning offers a potential solution for synthesizing AC data.

Purpose of the Study:

  • To develop a deep learning-based framework for PET AC (deep AC) by synthesizing transmission computed tomography (TCT) images from non-AC (NAC) PET images.
  • To evaluate the efficacy of a convolutional neural network (CNN) trained on a diverse dataset of radiotracers for brain PET AC.
  • To improve the quantitative accuracy of brain PET imaging without dedicated AC acquisition.

Main Methods:

  • A deep learning framework was developed, involving NAC PET image generation, synthetic TCT generation using CNN, and PET image reconstruction.
  • A CNN was trained on a mixed dataset of 1261 brain NAC PET and TCT images from six radiotracers ([18F]FDG, [18F]BCPP-EF, [11C]Racropride, [11C]PIB, [11C]DPA-713, and [11C]PBB3).
  • The model's performance was tested on both included and excluded radiotracers, including [11C]Methionine.

Main Results:

  • CNNs trained on mixed radiotracer datasets yielded superior synthetic TCT image quality compared to those trained on single-tracer datasets.
  • In [18F]FDG studies, deep AC demonstrated significantly lower mean relative PET bias (-5.69 ± 4.97) compared to emission-segmented AC (8.46 ± 5.24).
  • Deep AC PET and TCT AC PET images showed excellent correlation across seven radiotracers (R² = 0.912-0.982).

Conclusions:

  • The proposed deep AC framework effectively synthesizes TCT images from NAC PET data.
  • Training the CNN on a mixed dataset of PET tracers enhances quantitative accuracy compared to tracer-specific training.
  • This deep learning approach offers a promising solution for accurate quantitative brain PET imaging without AC acquisition mechanisms.