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

You might also read

Related Articles

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

Sort by
Same author

[Reirradiation: A new therapeutic paradigm in oncology].

Bulletin du cancer·2026
Same author

Study Protocol of OLIGOPELVIS 2-GETUG P12: A Randomized Phase 3 Study Comparing Intermittent Androgen-deprivation Therapy with or Without Salvage High-dose Intensity-modulated Radiotherapy to Oligorecurrent Pelvic and Para-aortic Lymph Nodes in Patients with Biochemically Relapsing Prostate Cancer.

European urology oncology·2026
Same author

Predicting gene essentiality and drug response from preclinical perturbation screens with layered ensemble of autoencoders and predictors.

Scientific reports·2026
Same author

Magnetic resonance imaging-guided radiotherapy for prostate cancer: A systematic review of the literature.

Cancer radiotherapie : journal de la Societe francaise de radiotherapie oncologique·2026
Same author

Quantitative accuracy of <sup>177</sup>Lu SPECT/CT imaging using ring-shaped CZT versus dual-head NaI systems.

EJNMMI physics·2026
Same author

Monte Carlo calculated beam quality correction factors for light ions used in particle therapy.

Physics in medicine and biology·2026

Related Experiment Video

Updated: Dec 28, 2025

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

932

MR to CT synthesis with multicenter data in the pelvic area using a conditional generative adversarial network.

Kévin N D Brou Boni1,2,3, John Klein2, Ludovic Vanquin1

  • 1Department of Medical Physics, Centre Oscar Lambret, Lille, France.

Physics in Medicine and Biology
|February 14, 2020
PubMed
Summary

This study introduces a fast and accurate method for generating synthetic CT (sCT) images from MRI data using a conditional Generative Adversarial Network (cGAN). This advancement supports MRI-only radiotherapy workflows by enabling precise dose calculations across multiple institutions.

More Related Videos

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.6K
MR Molecular Imaging of Prostate Cancer with a Small Molecular CLT1 Peptide Targeted Contrast Agent
06:54

MR Molecular Imaging of Prostate Cancer with a Small Molecular CLT1 Peptide Targeted Contrast Agent

Published on: September 3, 2013

11.6K

Related Experiment Videos

Last Updated: Dec 28, 2025

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

932
Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.6K
MR Molecular Imaging of Prostate Cancer with a Small Molecular CLT1 Peptide Targeted Contrast Agent
06:54

MR Molecular Imaging of Prostate Cancer with a Small Molecular CLT1 Peptide Targeted Contrast Agent

Published on: September 3, 2013

11.6K

Area of Science:

  • Medical Imaging
  • Radiotherapy Physics
  • Artificial Intelligence in Medicine

Background:

  • MRI-only workflows in radiotherapy require accurate synthetic CT (sCT) for dose calculation.
  • Generative Adversarial Networks (GANs) have been explored for fast sCT generation to streamline clinical workflows and reduce uncertainties.

Purpose of the Study:

  • To develop and validate a robust conditional Generative Adversarial Network (cGAN) model (pix2pixHD) for generating accurate sCT images from multicenter MRI data.
  • To assess the dosimetric accuracy of radiotherapy plans optimized on cGAN-generated sCT images compared to those on actual CT images.

Main Methods:

  • A pix2pixHD cGAN framework was trained on T2-weighted MR and CT images from 11 patients across two institutions.
  • The trained model generated sCT images for 8 independent patients from a third institution.
  • Mean Absolute Error (MAE) was calculated between synthetic and real CT images; radiotherapy plans were evaluated for dose distribution accuracy.

Main Results:

  • The cGAN model achieved an average MAE of 48.5 ± 6 HU between synthetic and real CT images within the body contour.
  • Radiotherapy plan recalculation on real CTs showed a maximum dose difference to the target of 1.3%.
  • Complete sCT generation for a patient (88 slices) averaged [Formula: see text] on a GPU.

Conclusions:

  • The developed cGAN method enables accurate and fast sCT generation in a multicenter setting, supporting MRI-only radiotherapy.
  • The approach requires fewer pre-processing steps and demonstrates high accuracy for dose calculation.
  • This study validates the feasibility of multicenter sCT generation for radiotherapy applications.