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

FLASH radiotherapy: Newsflash or flash in the pan?

Medical physics·2019
Same author

Spatiotemporal Distribution of Linear Microcracks and Diffuse Microdamage Following Daily Bouts of Fatigue Loading of Rat Ulnae.

Journal of orthopaedic research : official publication of the Orthopaedic Research Society·2019
Same author

Impact of short-term exposure to fine particulate matter air pollution on urinary metabolome: A randomized, double-blind, crossover trial.

Environment international·2019
Same author

Negative regulation of miR-1275 by H3K27me3 is critical for glial induction of glioblastoma cells.

Molecular oncology·2019
Same author

Copy number variations and polymorphisms in HSP90AB1 and risk of systemic lupus erythematosus and efficacy of glucocorticoids.

Journal of cellular and molecular medicine·2019
Same author

Ultra-large moiré-less autostereoscopic three-dimensional light-emitting-diode displays.

Optics express·2019

Related Experiment Video

Updated: Oct 6, 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

3.0K

Multiresolution residual deep neural network for improving pelvic CBCT image quality.

Wangjiang Wu1, Junda Qu2, Jing Cai3

  • 1Department of Radiation Oncology, Peking University Third Hospital, Beijing, China.

Medical Physics
|January 16, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a novel deep learning method to enhance cone-beam computed tomography (CBCT) images, significantly improving their accuracy and structural detail for radiation therapy. The improved synthetic CT (sCT) images aid in clinical applications like segmentation and dose calculation.

Keywords:
CT image quality evaluationcone-beam CTmultiresolution residual deep neural networksynthetic pelvic CT generation

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K
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

42.9K

Related Experiment Videos

Last Updated: Oct 6, 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

3.0K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K
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

42.9K

Area of Science:

  • Medical Imaging
  • Radiotherapy
  • Artificial Intelligence

Background:

  • Cone-beam computed tomography (CBCT) is crucial for image-guided radiation therapy.
  • Poor CBCT image quality limits its clinical utility, necessitating improvements in HU accuracy and structure preservation.

Purpose of the Study:

  • To develop a novel method for generating synthetic CT (sCT) images from CBCT images.
  • To enhance HU accuracy and structural fidelity of CBCT images for improved clinical applications.

Main Methods:

  • A multiresolution residual deep neural network (RDNN) was employed for image regression from CBCT to planning CT (pCT).
  • The RDNN model was trained using aligned pCT and CBCT image pairs from 153 prostate cancer patients, with a focus on multiresolution training for improved detail.
  • Five-fold cross-validation was used for hyperparameter tuning and model evaluation.

Main Results:

  • The proposed multiresolution RDNN model achieved a mean absolute error (MAE) of 52.18 HU between sCT and pCT images, an 85.20% reduction compared to CBCT (352.56 HU).
  • The average structural similarity index measure between sCT and CBCT was 19.64% higher than that between pCT and CBCT.

Conclusions:

  • The generated sCT images demonstrate superior HU accuracy and structural fidelity.
  • These enhanced sCT images hold potential for advancing CBCT applications in structure segmentation, dose calculation, and adaptive radiotherapy planning.