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

Functional characterization of fungal endophytes with antagonistic and plant growth-promoting activities in maize.

Scientific reports·2026
Same author

Deep learning-based chemical shift-artifact correction of ZTE MRI for enhanced bone depiction of the lumbar spine.

Skeletal radiology·2026
Same author

Development and evaluation of a deep learning-assisted diagnostic support system for radiographer preliminary clinical evaluation of intracranial hemorrhage.

PeerJ·2026
Same author

Development and evaluation of AI model with deep learning for segmentation of extraocular muscles in thyroid eye disease.

PloS one·2026
Same author

Zero-TE MRI-based attenuation correction for bone components on chest [<sup>18</sup>F] FDG PET/MRI: accuracy, repeatability, and external validation of an unsupervised deep learning approach using unpaired PET/CT data.

Annals of nuclear medicine·2026
Same author

q3-MuPa: Quick, quiet, quantitative multi-parametric MRI using physics-informed diffusion models.

Magnetic resonance imaging·2026

Related Experiment Video

Updated: Sep 6, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

490

Unsupervised-learning-based method for chest MRI-CT transformation using structure constrained unsupervised

Hidetoshi Matsuo1, Mizuho Nishio2, Munenobu Nogami2

  • 1Department of Radiology, Kobe University Graduate School of Medicine, Kobe, Japan. yukikaze.jp@gmail.com.

Scientific Reports
|June 30, 2022
PubMed
Summary

This study introduces a novel method to synthesize CT images from MRI scans for PET/MRI attenuation correction. The technique enhances quantitative PET imaging in the chest by overcoming motion and anatomical challenges.

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K
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

675

Related Experiment Videos

Last Updated: Sep 6, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

490
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K
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

675

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • Integrated positron emission tomography/magnetic resonance imaging (PET/MRI) offers simultaneous metabolic and morphological data acquisition.
  • Quantitative PET evaluation requires accurate attenuation correction, which is challenging using MRI-derived data, especially in the chest due to motion and complex anatomy.
  • Current MRI-based methods struggle with attenuation correction in the chest region.

Purpose of the Study:

  • To develop an advanced method for synthesizing computed tomography (CT) images from chest MRI data.
  • To enable accurate attenuation correction for quantitative PET imaging within PET/MRI systems.
  • To overcome the limitations of existing methods in handling respiratory/cardiac motion and complex chest anatomy.

Main Methods:

  • Utilized unsupervised generative attentional networks with adaptive layer-instance normalization (U-GAT-IT) for unpaired image-to-image translation.
  • Incorporated modality-independent neighbourhood descriptor (MIND) into the U-GAT-IT loss function to ensure anatomical consistency.
  • Focused on generating synthetic CT images from chest MRI data without human annotation.

Main Results:

  • Successfully synthesized CT images of the chest from MRI data.
  • The proposed method demonstrated superior performance compared to existing approaches.
  • Achieved minimal changes in anatomical structures during image transformation, ensuring clinical acceptability.

Conclusions:

  • The developed U-GAT-IT method with MIND effectively synthesizes clinically acceptable CT images from chest MRI.
  • This approach offers a viable solution for accurate PET attenuation correction in PET/MRI, particularly for the chest region.
  • The findings suggest a promising non-invasive technique for improving quantitative PET imaging without manual segmentation.