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

Enhancing Underwater Light Field Images via Global Geometry-Aware Diffusion Process.

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

QMSANet: A quaternion multi-scale attention network for robust color image denoising.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

SMUPhantom: a 3D-printable modular CT perfusion phantom for quantitative evaluation of tissue-mimicking dynamic contrast behavior.

Biomedical physics & engineering express·2026
Same author

Gradient-based rigid motion correction in CBCT via Lie algebra-constrained registration.

Physics in medicine and biology·2026
Same author

AI-Powered Monitoring of the Acute: Chronic Workload Ratio: Interpretable Injury Risk Prediction in Soccer Players.

Sports health·2026
Same author

The evolution of high-order genome architecture revealed from 1,000 species.

Cell·2026

Related Experiment Video

Updated: Jul 2, 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

2.7K

Semi-supervised iterative adaptive network for low-dose CT sinogram recovery.

Lei Wang1,2, Mingqiang Meng2,3, Shixuan Chen2

  • 1School of Future Technology, Xi'an Jiaotong University, Xi'an 710049, People's Republic of China.

Physics in Medicine and Biology
|February 29, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces SIA-Net, a semi-supervised deep learning method for low-dose computed tomography (CT) imaging. SIA-Net effectively reduces image noise and artifacts without requiring large paired datasets, improving image quality in low-dose CT scans.

Keywords:
Semi-supervised iterative adaptive network for low-dose CT sinogram recoverylow-dose CTsemi-supervisedsinogramsupervisedunsupervised

More Related Videos

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

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

Published on: February 21, 2025

275
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.6K

Related Experiment Videos

Last Updated: Jul 2, 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

2.7K
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

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

Published on: February 21, 2025

275
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.6K

Area of Science:

  • Medical Imaging
  • Radiology
  • Artificial Intelligence

Background:

  • Medical computed tomography (CT) radiation poses a risk of carcinogenesis.
  • Reducing CT radiation dose can cause image noise and artifacts.
  • Deep learning (DL) shows promise for low-dose CT (LDCT) but requires extensive paired data.

Purpose of the Study:

  • To develop a novel semi-supervised learning framework for LDCT reconstruction.
  • To address the challenge of limited paired training data in clinical settings.
  • To improve image quality in LDCT by leveraging both labeled and unlabeled data.

Main Methods:

  • Introduced SIA-Net, a semi-supervised iterative adaptive network for LDCT.
  • Integrated supervised learning for feature extraction from paired sinograms.
  • Employed unsupervised learning on unlabeled sinograms with weighted least-squares regularization.
  • Developed adaptive feature transfer between supervised and unsupervised processes for high-fidelity sinogram refinement.

Main Results:

  • SIA-Net demonstrated competitive performance in noise reduction for LDCT.
  • The method effectively preserved crucial structural information in reconstructed images.
  • Experimental results on clinical datasets validated SIA-Net's efficacy compared to supervised methods.

Conclusions:

  • SIA-Net offers a robust solution for LDCT image reconstruction.
  • The semi-supervised approach overcomes limitations of data scarcity in DL-based CT imaging.
  • This method enhances image quality while mitigating radiation risks in CT scans.