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: Jun 27, 2026

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

3DAD: Super-Resolution Image Synthesis from Anisotropic CT Images Using a Three-Dimensional Adversarial Diffusion

Jianliang Lu1, Ho Ming Cheng1, Benjamin Xin Hao Fang2

  • 1Department of Medicine, School of Clinical Medicine, The University of Hong Kong, Hong Kong.

Bioengineering (Basel, Switzerland)
|June 26, 2026
PubMed
Summary

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

Chronic kidney disease in cirrhosis: a study of inpatients from a global perspective.

Gut·2026
Same author

Lack of Association Between Rifaximin and Drug-resistant Infections: A global multicenter inpatient cirrhosis cohort.

Clinical and molecular hepatology·2026
Same author

Intravascular ultrasound guidance in superior vena cava stenting for malignant superior vena cava obstruction: solving the landing zone dilemma.

Diagnostic and interventional radiology (Ankara, Turkey)·2026
Same author

Machine Learning Models Using Hospital Admission Characteristics Do Not Optimally Predict Nosocomial Infection Development in a Global Cirrhosis Cohort.

The American journal of gastroenterology·2026
Same author

GLP-1 receptor agonist-SGLT-2 inhibitor combination and risk of major adverse liver and cardiovascular outcomes in adults with MASLD and type 2 diabetes.

Hepatology (Baltimore, Md.)·2026
Same author

[Construction of recombinant <i>Lactococcus lactis</i> strains expressing classical swine fever virus E2 antigen and evaluation of their immunogenicity in murine models].

Sheng wu gong cheng xue bao = Chinese journal of biotechnology·2026
Same journal

Correction: Komatsu et al. Three-Dimensional Visualization and Detection of the Pulmonary Venous-Left Atrium Connection Using Artificial Intelligence in Fetal Cardiac Ultrasound Screening. <i>Bioengineering</i> 2026, <i>13</i>, 100.

Bioengineering (Basel, Switzerland)·2026
Same journal

Comparison of CO<sub>2</sub> Laser and Microdebrider in the Surgical Treatment of Pediatric Recurrent Respiratory Papillomatosis: A Retrospective Analysis.

Bioengineering (Basel, Switzerland)·2026
Same journal

Toward More Translational Tumor Models: Breast dECM-Based 3D Systems Capture Native Microenvironmental Cues.

Bioengineering (Basel, Switzerland)·2026
Same journal

Postural Stability Changes During the 4 Phases of the Half Squat: Kinematics Profile of the Center of Pressure and Center of Mass in High-Performance Weightlifters-A Pilot Study.

Bioengineering (Basel, Switzerland)·2026
Same journal

Definite Implant Position as Novel Readout for Effectiveness of Ridge Preservation Indicates to Beneficial Effect of Combined Treatment with Platelet-Rich Fibrin (PRF) and Xenogenic Biomaterial in Bone Regeneration.

Bioengineering (Basel, Switzerland)·2026
Same journal

Trueness and Precision of Intraoral Scanners for 3D-Printed Orthodontic Models with Attachments: An In Vitro Comparative Study.

Bioengineering (Basel, Switzerland)·2026
See all related articles
This summary is machine-generated.

This study introduces a 3D adversarial diffusion model (3DAD) to reconstruct high-resolution thin-slice CT images from compressed thick-slice CT data. The model shows promise for improving medical diagnosis, particularly in HCC detection.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • High-resolution thin-slice computed tomography (CT) images are often compressed to lower-quality thick-slice images for storage.
  • This compression necessitates image synthesis for accurate medical diagnosis.

Purpose of the Study:

  • To propose and evaluate a novel 3D adversarial diffusion model (3DAD) for high-fidelity synthesis of thin-slice CT from compressed thick-slice CT.
  • To assess the utility of synthesized thin-slice CT images in Hepatocellular Carcinoma (HCC) diagnosis.

Main Methods:

  • Developed a 3D adversarial diffusion model (3DAD) comprising a generator and a discriminator.
  • Trained models on abdominal CT data across two- to six-slice scenarios, using compressed thick-slice CT as source images.
Keywords:
computed tomography (CT)diffusion modelsyntheticthick slicethin slice

More Related Videos

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

Three-Dimensional Printing of a Complex Aortic Anomaly
03:40

Three-Dimensional Printing of a Complex Aortic Anomaly

Published on: November 1, 2018

Related Experiment Videos

Last Updated: Jun 27, 2026

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

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

Three-Dimensional Printing of a Complex Aortic Anomaly
03:40

Three-Dimensional Printing of a Complex Aortic Anomaly

Published on: November 1, 2018

  • Evaluated 3DAD using real and synthetic thin-slice CT for HCC diagnosis at observation and patient levels, comparing Receiver Operating Characteristic (ROC) curves using DeLong's test.

    • Main Results:

    • Achieved high image quality metrics (MSE: 81.374, PSNR: 29.478, SSIM: 0.916 for five-slice scenarios).
    • Demonstrated comparable diagnostic performance: AUCs of 0.896 (synthetic) vs. 0.889 (real) at observation level (p=0.028) and 0.854 vs. 0.846 at patient level (p=0.055).
    • Radiologist evaluations confirmed high synthetic image quality, with no significant difference from real images in most cases.

    Conclusions:

    • The 3DAD model effectively synthesizes high-resolution thin-slice CT images from compressed thick-slice CT.
    • The synthesized images maintain diagnostic accuracy for HCC detection, facilitating high-fidelity volume image applications.
    • This approach offers a viable solution for medical diagnosis using stored, lower-quality CT data.