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

X-ray Imaging01:24

X-ray Imaging

5.2K
German physicist Wilhelm Röntgen (1845–1923) was experimenting with electrical current when he discovered that a mysterious and invisible "ray" would pass through his flesh but leave an outline of his bones on a screen coated with a metal compound. In 1895, Röntgen made the first durable record of the internal parts of a living human: an "X-ray" image (as it came to be called) of his wife’s hand. Scientists worldwide quickly began their own experiments with...
5.2K

You might also read

Related Articles

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

Sort by
Same author

Wide-tuning-range Littman-type external-cavity diode laser for spectroscopy of GaAs band-edge and impurity-level transitions.

Applied optics·2026
Same author

Reverse Spin-Transition-Like Behavior in a Single-Molecule Organic Diradical.

The journal of physical chemistry letters·2026
Same author

Backbone-integrated triplet radicals in linear 2p-3d-4f heterometallic chains and magnetic hysteresis.

Chemical communications (Cambridge, England)·2026
Same author

[3. Data Literacy (1): Data Types, Central Values, and Variability].

Nihon Hoshasen Gijutsu Gakkai zasshi·2026
Same author

[Mechanism of action and clinical trial results of a new drug for amyotrophic lateral sclerosis (ALS), Mecobalamin (Rozebalamin<sup>®</sup>) for intramuscular injection, 25 mg].

Nihon yakurigaku zasshi. Folia pharmacologica Japonica·2026
Same author

Response to letter to the editor "Comment on: Clinical safety of ultra-high-dose methylcobalamin in patients with amyotrophic lateral sclerosis: Open-label extension of a phase 2/3 randomized controlled study".

Journal of the neurological sciences·2026

Related Experiment Video

Updated: May 9, 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

496

Deep Learning on Misaligned Dual-Energy Chest X-ray Images Using Paired Cycle-Consistent Generative Adversarial

Yasuyuki Ueda1, Misato Niu2, Riko Shimazaki2

  • 1Division of Health Sciences, Graduate School of Medicine, The University of Osaka, 1 - 7 Yamadaoka, Suita, Osaka, 565 - 0871, Japan. ueda.y.sahs.med@osaka-u.ac.jp.

Journal of Imaging Informatics in Medicine
|May 5, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel AI framework to enhance dual-energy subtraction chest X-ray images by removing motion artifacts and noise. The new method significantly improves image quality for clearer medical diagnoses.

Keywords:
Chest X-rayCycle-consistent generative adversarial networksDeep learningDual-energy subtractionGenerative adversarial networksMotion artifacts

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

318

Related Experiment Videos

Last Updated: May 9, 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

496
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

318

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Image Processing

Background:

  • Dual-energy subtraction (DES) chest X-ray images (CXRs) are prone to motion artifacts and signal insufficiency in low-energy (LE) images.
  • Existing image processing techniques struggle to adequately address these artifacts and noise in DES-CXRs.
  • Novel algorithms for artifact and noise removal in DES-CXRs remain largely unexplored.

Purpose of the Study:

  • To propose and evaluate a novel framework for effectively removing motion artifacts and statistical noise from DES-CXRs.
  • To enhance the diagnostic quality of DES-CXRs using advanced generative adversarial networks.

Main Methods:

  • A framework based on paired cycle-consistency adversarial generative networks was developed.
  • The method incorporates ensemble discriminators, differentiable augmentation, anti-aliased convolution layers, and an 8-layer U-Net generator.
  • The framework was trained and validated on a clinical dataset of 600 DES-CXRs using sixfold cross-validation.

Main Results:

  • Demonstrated significant improvement in motion artifact suppression, with enhanced full width at 10-percent maximum in lung regions.
  • Outperformed previous methods in peak signal-to-noise ratio (50.7 ± 3.68) and structural similarity index (0.997 ± 0.0152) for LE images.
  • Achieved a competitive Fréchet inception distance (85.0 ± 3.52) for bone-suppressed DES images, indicating high-quality image generation.

Conclusions:

  • The proposed AI framework significantly outperforms existing techniques for motion artifact and statistical noise removal in DES-CXRs.
  • The method shows strong potential for clinical application, improving the reliability and diagnostic accuracy of chest X-ray imaging.