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

Additional Dose Reduction Potential of Vendor-Agnostic Deep Learning Model: A Phantom Study.

Journal of the Korean Society of Radiology·2026
Same author

AAV vectors for cancer gene therapy.

Advances in cancer research·2026
Same author

Abdominopelvic computed tomography during pregnancy and the risk of congenital malformations: protocol for a nationwide population-based cohort study in South Korea.

BMJ open·2026
Same author

Building a credibility-based framework for target discovery: Perspectives from tRNA synthetase-linked metabolic diseases.

Briefings in bioinformatics·2026
Same author

Image quality improvement of liver ultrasound using unsupervised deep learning.

PloS one·2026
Same author

Multicentre prospective trial of abbreviated MRI using gadoxetic acid versus CT for detection of late recurrent HCC (AMRICT): study protocol.

BMJ open·2026
Same journal

ESR Essentials: uterine cancers-practice recommendations by the European Society of Urogenital Radiology.

European radiology·2026
Same journal

Adjunctive quantification for more reproducible amyloid PET interpretation.

European radiology·2026
Same journal

APEX-NET: automated pancreatic evaluation network using early non-contrast CT.

European radiology·2026
Same journal

Temporal bone remodeling after venous stenting for pulsatile tinnitus: isolated dehiscence versus diverticulum.

European radiology·2026
Same journal

Do hepatic and biliary functional data from gadoxetate-enhanced MRI add value in predicting outcomes in primary sclerosing cholangitis (PSC)?

European radiology·2026
Same journal

Cardiovascular risk factors and carotid plaque components in a multi-ethnic cohort using 3 Tesla MRI: the HELIUS study.

European radiology·2026
See all related articles

Related Experiment Video

Updated: Nov 8, 2025

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

800

Deep learning-based denoising algorithm in comparison to iterative reconstruction and filtered back projection: a

Youngjune Kim1,2, Dong Yul Oh3, Won Chang4

  • 1Department of Radiology, Seoul National University Bundang Hospital, Seongnam, Republic of Korea.

European Radiology
|April 22, 2021
PubMed
Summary
This summary is machine-generated.

A new deep learning-based denoising algorithm (DLA) demonstrates non-inferior low-contrast detectability compared to ADMIRE and superior performance over FBP. This DLA enhances image quality while maintaining similar physical characteristics to advanced iterative reconstruction methods.

Keywords:
Artificial intelligenceDeep learningPhantoms, imagingRadiation dosageTomography, X-ray computed

More Related Videos

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

10.0K
Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research
08:33

Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research

Published on: January 5, 2024

1.4K

Related Experiment Videos

Last Updated: Nov 8, 2025

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

800
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

10.0K
Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research
08:33

Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research

Published on: January 5, 2024

1.4K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Radiology
  • Image Reconstruction

Background:

  • Traditional CT image reconstruction methods like Filtered Back Projection (FBP) often struggle with low-contrast object detection.
  • Advanced Iterative Reconstruction (AIR) algorithms, such as ADMIRE, improve image quality but can be computationally intensive.
  • Deep learning-based denoising algorithms (DLA) offer a potential alternative for enhancing CT image quality.

Purpose of the Study:

  • To compare the low-contrast detectability of a DLA against established methods (ADMIRE, FBP).
  • To evaluate image quality parameters of the DLA in comparison to reconstruction techniques from different CT vendors.
  • To assess the clinical utility of DLA for improving CT image analysis.

Main Methods:

  • A DLA was trained using abdominal CT images, with FBP images as input and ADMIRE images as ground truth.
  • Low-contrast detectability was assessed using phantom scans and evaluated by radiologists via Area Under the ROC Curve (AUC) analysis.
  • Image quality metrics including contrast-to-noise ratio and detectability index were computed for DLA, ADMIRE, IMR, and FBP.

Main Results:

  • The DLA achieved non-inferior low-contrast detectability compared to ADMIRE (AUC, p < .001) and superior detectability compared to FBP (AUC, p < .001).
  • The DLA demonstrated significant improvements in all physical image quality measurements over FBP reconstructions from both vendors.
  • Physical measurement profiles of the DLA were found to be similar to those of the ADMIRE algorithm.

Conclusions:

  • The proposed DLA offers comparable or superior low-contrast detectability to current standard and advanced reconstruction methods.
  • DLA effectively enhances CT image quality over FBP, presenting physical characteristics similar to ADMIRE.
  • This deep learning approach shows promise for improving diagnostic accuracy in CT imaging.