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 Videos

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

Jisu Kim, Won Chang, Jong Hyo Kim

    Journal of the Korean Society of Radiology
    |June 17, 2026
    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

    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

    Deep Learning-Based Augmented Contrast-Enhancement and Denoising for Reduced-Iodine and Low-Radiation 70-kVp Cerebral CT Angiography: A Prospective Study.

    Korean journal of radiology·2026
    Same author

    Improving prediction of ypT0-1N0 response in rectal cancer: the added value of gross tumor type to magnetic resonance tumor regression grade after chemoradiotherapy in a retrospective cohort study.

    Annals of surgical treatment and research·2026
    Same author

    Ultrasound Imaging Features Associated With Neoplastic Gallbladder Polyps: A Systematic Review and Meta-Analysis.

    Korean journal of radiology·2026
    Same author

    Diagnostic Performance and Clinical Implications of the "Probable Hepatocellular Carcinoma" Category in the Korean Liver Cancer Association-National Cancer Center Korea Guidelines v2022.

    Korean journal of radiology·2026
    Same author

    Body composition after treatment of intra-mucosal gastric cancer with endoscopic resection compared to gastrectomy.

    Communications medicine·2025
    Same journal

    Techniques and Clinical Outcomes of Catheter-Directed Sclerotherapy Using Ethanol for Ovarian Endometriomas.

    Journal of the Korean Society of Radiology·2026
    Same journal

    Primary Gastric Leiomyosarcoma Presenting as an Endoscopic Diagnostic Pitfall: A Case Report.

    Journal of the Korean Society of Radiology·2026
    Same journal

    Breast Imaging Reporting and Data System v2025: Key Updates in Mammography.

    Journal of the Korean Society of Radiology·2026
    Same journal

    Breast Imaging Reporting and Data System v2025: Key Updates in MRI.

    Journal of the Korean Society of Radiology·2026
    Same journal

    Massive Psoas Muscle Bleeding from the Contralateral Lumbar Artery Obscured by a Lumbar Vertebra Fracture: A Case Report.

    Journal of the Korean Society of Radiology·2026
    Same journal

    AI Solution for Identifying Actionable Abnormalities on Chest Radiographs: A Retrospective Case-Control Study.

    Journal of the Korean Society of Radiology·2026
    See all related articles

    A vendor-agnostic deep learning model (DLM) significantly reduces radiation dose in CT scans by up to 93.2% while maintaining image quality. This AI-driven approach enhances dose reduction potential across various iterative reconstruction methods and CT vendors.

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence in Radiology
    • Radiation Dose Reduction

    Background:

    • Iterative reconstruction (IR) techniques in computed tomography (CT) reduce image noise but have limitations in dose reduction.
    • Deep learning models (DLMs) show promise for enhancing image quality and reducing noise in medical imaging.
    • Vendor-agnostic DLMs offer potential for broad application across different CT systems.

    Purpose of the Study:

    • To evaluate the additional dose reduction potential (DRP) of a vendor-agnostic deep learning model (DLM) when applied to iterative reconstruction (IR) methods from two different CT vendors.
    • To assess the DLM's effectiveness in preserving image quality at reduced radiation doses.

    Main Methods:

    • CT images of a phantom were acquired at various dose levels using two vendors' scanners.
    Keywords:
    Computer-AssistedDeep LearningImage ProcessingRadiation DosageRadiographic Image EnhancementTomography, X-Ray Computed

    Related Experiment Videos

  • Images were reconstructed using three IR methods (ADMIRE, iDose4, IMR) at two strength levels.
  • A vendor-agnostic DLM was applied for denoising, and image quality was assessed using the detectability index (d') across different target sizes and contrast levels.

    • Main Results:

    • Mean DRPs achieved were 93.2% for ADMIRE, 90.0% for iDose4, and 87.2% for IMR.
    • Higher DRPs were observed for targets with higher contrast.
    • The DLM application also resulted in improvements in contrast-to-noise ratio (CNR).

    Conclusions:

    • A vendor-agnostic DLM significantly enhances radiation dose reduction potential in CT imaging.
    • The DLM effectively preserves image quality across different CT vendors and IR techniques.
    • This AI-driven approach offers a pathway to substantial dose savings in clinical CT practice.