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

A ZDHHC3-USP5-PTRF axis links palmitoylation to ferroptosis-associated phenotypes in melanoma.

Cell death & disease·2026
Same author

Early Salivary Gland Shrinkage Is Associated With an Increased Risk of Acute Xerostomia in Head and Neck Cancer Radiation Therapy.

Advances in radiation oncology·2026
Same author

Correction to "Engineering Ene-Reductases for the Chemoenzymatic Synthesis of a Sacubitril Intermediate and Its Derivatives".

Organic letters·2026
Same author

In Situ Characterization Techniques for Investigating the Reaction Mechanisms of Lithium-Sulfur Batteries: Progress, Application, and Future.

Small methods·2026
Same author

Immune cell delivery platforms for tumor therapy: From empirical approaches to AI-integrated frameworks.

Journal of controlled release : official journal of the Controlled Release Society·2026
Same author

Concise Total Synthesis of (+)-Shearilicine: A Machine Learning-Assisted Strategy for Ligand Optimization of an Enantioselective Palladium-Catalyzed α-Arylation.

Journal of the American Chemical Society·2026

Related Experiment Video

Updated: Oct 29, 2025

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.3K

Multitask 3D CBCT-to-CT translation and organs-at-risk segmentation using physics-based data augmentation.

Navdeep Dahiya1, Sadegh R Alam2, Pengpeng Zhang2

  • 1Department of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA.

Medical Physics
|July 10, 2021
PubMed
Summary
This summary is machine-generated.

This study developed a deep learning method to enhance low-quality cone beam computed tomography (CBCT) images into high-quality synthetic CT images. This advancement enables adaptive radiotherapy and biomarker discovery using routine imaging, potentially improving patient outcomes.

Keywords:
3D CBCT-to-CT translationOARs segmentation

More Related Videos

Development and Evaluation of 3D-Printed Cardiovascular Phantoms for Interventional Planning and Training
09:57

Development and Evaluation of 3D-Printed Cardiovascular Phantoms for Interventional Planning and Training

Published on: January 18, 2021

4.3K
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

8.2K

Related Experiment Videos

Last Updated: Oct 29, 2025

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.3K
Development and Evaluation of 3D-Printed Cardiovascular Phantoms for Interventional Planning and Training
09:57

Development and Evaluation of 3D-Printed Cardiovascular Phantoms for Interventional Planning and Training

Published on: January 18, 2021

4.3K
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

8.2K

Area of Science:

  • Medical Imaging
  • Radiotherapy Physics
  • Artificial Intelligence in Medicine

Background:

  • Current radiotherapy relies on planning CT (pCT) for treatment, while weekly cone beam CT (CBCT) images are only used for patient setup due to noise and artifacts.
  • Adapting radiotherapy mid-treatment and deriving biomarkers for treatment response are limited by the poor quality of routine CBCT images.

Purpose of the Study:

  • To develop a method for improving the quality of weekly CBCT images and simultaneously segmenting organs-at-risk (OARs).
  • To enable adaptive radiotherapy and biomarker discovery using enhanced CBCT images.

Main Methods:

  • A novel physics-based data augmentation strategy was used to create a dataset of registered pCT and synthetic-CBCT pairs.
  • A multitask 3D deep learning framework was employed to simultaneously segment OARs and translate real CBCT images to pCT-like images.

Main Results:

  • Synthetic CT images showed a significant reduction in mean absolute error (MAE) from 162.77 HU to 29.31 HU compared to pCT.
  • High structural similarity (92%) was achieved between synthetic CT and pCT images.
  • The model achieved high average DICE scores for OAR segmentation: lungs (0.96), heart (0.88), spinal cord (0.83), and esophagus (0.66).

Conclusions:

  • A method was demonstrated to translate artifact-ridden CBCT images into high-quality synthetic CT images with simultaneous OAR segmentation.
  • This approach may allow for treatment plan adjustments using only routine CBCT images, potentially improving patient outcomes.
  • The developed code, data, and models are available via the Physics-ArX library.