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

Directional dark field for nanoscale full-field transmission X-ray microscopy.

Light, science & applications·2026
Same author

Extending the Field of View in Modulation-Based X-Ray Phase Microtomography.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Comparative study on 3D morphologies of delignified, single tracheids and fibers of five wood species.

Beilstein journal of nanotechnology·2026
Same author

Quantitative Stain Mapping in X-Ray Virtual Histology.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Follicle-like niches outside the cortex? 3D phase-contrast µCT revealed medullary B cell nodules in mucosa-draining lymph nodes.

Frontiers in immunology·2025
Same author

Cardiopulmonary and Immune Alterations in the Ts65Dn Mouse Model of Down Syndrome and Modulation by Epigallocatechin-3-Gallate-Enriched Green Tea Extract.

Pharmaceutics·2025

Related Experiment Video

Updated: May 7, 2025

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography
07:01

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

Published on: October 24, 2019

9.7K

Self-supervised denoising of grating-based phase-contrast computed tomography.

Sami Wirtensohn1,2,3,4, Clemens Schmid5,6,7, Daniel Berthe5,6

  • 1Research Group Biomedical Imaging Physics, Department of Physics, TUM School of Natural Sciences, Technical University of Munich, 85748, Garching, Germany. sami.wirtensohn@tum.de.

Scientific Reports
|December 31, 2024
PubMed
Summary

Self-supervised deep learning, Noise2Inverse, enhances grating-based phase-contrast CT (gbPC-CT) denoising. This improves soft-tissue contrast and resolution at lower radiation doses, advancing medical imaging applications.

Keywords:
Computed tomographyNoise reductionPhase contrastSelf-supervised learningX-ray imaging

More Related Videos

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography
09:00

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Published on: September 29, 2019

13.2K
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:31

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

172

Related Experiment Videos

Last Updated: May 7, 2025

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography
07:01

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

Published on: October 24, 2019

9.7K
Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography
09:00

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Published on: September 29, 2019

13.2K
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:31

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

172

Area of Science:

  • Medical Imaging
  • Computational Imaging
  • Artificial Intelligence

Background:

  • Grating-based phase-contrast computed tomography (gbPC-CT) offers superior soft-tissue contrast compared to conventional CT.
  • However, gbPC-CT's resolution-dose dependency limits its clinical application, often requiring higher radiation doses for effective contrast.
  • Existing denoising methods struggle to balance resolution enhancement with dose reduction in gbPC-CT.

Purpose of the Study:

  • To introduce and evaluate the self-supervised deep learning network Noise2Inverse for denoising in gbPC-CT.
  • To assess the impact of Noise2Inverse parameters on phase-contrast imaging results.
  • To compare the performance of Noise2Inverse against traditional denoising techniques.

Main Methods:

  • Implementation of the Noise2Inverse deep learning network for gbPC-CT image reconstruction.
  • Systematic evaluation of Noise2Inverse parameter effects on phase-contrast signals.
  • Comparative analysis of Noise2Inverse with Statistical Iterative Reconstruction, Block Matching 3D, and Patchwise Phase Retrieval algorithms.

Main Results:

  • Noise2Inverse demonstrated superior denoising performance across key image quality metrics compared to other methods.
  • The application of Noise2Inverse enabled increased image resolution while maintaining low radiation doses.
  • Deep learning-based denoising significantly improved the dose-normalized image quality of gbPC-CT.

Conclusions:

  • Self-supervised deep learning, exemplified by Noise2Inverse, effectively addresses the resolution-dose trade-off in gbPC-CT.
  • Machine learning-based denoising enhances gbPC-CT's potential for clinical use by improving image quality at reduced radiation levels.
  • This advancement brings gbPC-CT closer to widespread medical adoption.