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 Experiment Video

Updated: Dec 19, 2025

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

3.2K

Neural networks-based regularization for large-scale medical image reconstruction.

A Kofler1, M Haltmeier, T Schaeffter

  • 1Department of Radiology, Charité - Universitätsmedizin Berlin, Berlin, Germany.

Physics in Medicine and Biology
|June 4, 2020
PubMed
Summary
This summary is machine-generated.

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

Image quality of opportunistic breast examinations in photon-counting computed tomography: A phantom study.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2024
Same author

Joint reconstruction and segmentation in undersampled 3D knee MRI combining shape knowledge and deep learning.

Physics in medicine and biology·2024
Same author

Computed tomographic angiography measures of coronary plaque in clinical trials: <i>opportunities and considerations to accelerate drug translation</i>.

Frontiers in cardiovascular medicine·2024
Same author

Relevance of CT for the detection of septic foci: diagnostic performance in a retrospective cohort of medical intensive care patients.

Clinical radiology·2021
Same author

Solution of Heliospheric Propagation: Unveiling the Local Interstellar Spectra of Cosmic-ray Species.

The Astrophysical journal·2021
Same author

Cosmic-ray antinuclei as messengers of new physics: status and outlook for the new decade.

Journal of cosmology and astroparticle physics·2021
Same journal

Impact of apertures on the out-of-field secondary neutron dose in collimated proton pencil-beam scanning.

Physics in medicine and biology·2026
Same journal

Quantifying cardiac deformable image registration accuracy and its dosimetric variability for 4D dose accumulation in stereotactic arrhythmia radioablation.

Physics in medicine and biology·2026
Same journal

Probabilistic modelling of bilateral lymphatic spread in oral cavity squamous cell carcinoma for personalised elective nodal treatment.

Physics in medicine and biology·2026
Same journal

A Monte Carlo simulation tool to analyze breast cancer trial outcomes: application to FAST-Forward trial.

Physics in medicine and biology·2026
Same journal

Effective contrast-enhanced preprocessing for intracranial artery segmentation in digital subtraction angiography.

Physics in medicine and biology·2026
Same journal

Improving Plan Quality in Adaptive Proton Therapy Using an Interactive Dose Modification Tool.

Physics in medicine and biology·2026
See all related articles

This study introduces a novel deep learning method for medical image reconstruction, significantly improving image quality and reconstruction speed for large-scale inverse problems. The approach enhances diagnostic accuracy by efficiently processing complex imaging data.

Area of Science:

  • Medical Imaging
  • Computational Science
  • Artificial Intelligence

Background:

  • Deep learning methods, including iterative and cascaded neural networks (NNs), have shown promise in medical image reconstruction.
  • Current deep learning approaches often require processing entire images or volumes, posing computational challenges for large-scale problems.

Purpose of the Study:

  • To develop a generalized deep learning-based approach for solving ill-posed, large-scale inverse problems in medical image reconstruction.
  • To overcome the computational limitations of existing iterative deep learning methods.

Main Methods:

  • A novel reconstruction strategy separating neural network (NN) application, solution regularization, and data consistency.
  • Utilizing an image prior from a trained NN within a Tikhonov regularization framework.

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

692

Related Experiment Videos

Last Updated: Dec 19, 2025

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

3.2K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

692
  • Processing images/volumes in patches or slices to manage computational complexity for large-scale problems.

    • Main Results:

    • The proposed method demonstrated superior performance across quantitative measures (PSNR, NRMSE, SSIM) compared to traditional and dictionary-based methods.
    • Achieved significant acceleration (several orders of magnitude) in the regularization step.
    • Successfully applied to 3D cone-beam low-dose CT and undersampled 2D radial cine MRI.

    Conclusions:

    • The generalized deep learning approach offers a more computationally feasible and effective solution for medical image reconstruction.
    • This method enables the use of more complex NN architectures for artifact and noise reduction.
    • The approach significantly advances the field by improving both image quality and reconstruction efficiency.