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

Computed Tomography01:10

Computed Tomography

4.1K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
4.1K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

An advanced automated pipeline for brain tumour segmentation on magnetic resonance imaging for gamma knife radiosurgery.

Physics and imaging in radiation oncology·2026
Same author

Current and bereaved caregivers' experiences of participating in the adapted Telehealth Making Sense of Brain Tumour program in the context of high-grade glioma.

Neuro-oncology practice·2026
Same author

Stereotactic Body Radiation Therapy for Non-Spine Bone Metastases: A Case-Based Radiosurgery Society Review.

Practical radiation oncology·2026
Same author

Second primary invasive cutaneous melanomas in Queensland over 4 decades.

The Journal of investigative dermatology·2026
Same author

Management of Adult Patients With Isocitrate Dehydrogenase-Mutant Gliomas in Australia: An Expert Position Statement From the Cooperative Trials Group for Neuro-Oncology.

Asia-Pacific journal of clinical oncology·2026
Same author

Exercise as a non-pharmacological intervention for the management of sleep disturbance in primary brain tumour survivors and their caregivers: A study protocol of a clinical trial.

JSAMS plus·2026

Related Experiment Video

Updated: May 10, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

743

Enhancing Gamma Knife Cone-beam Computed Tomography Image Quality Using Pix2pix Generative Adversarial Networks: A

Prabhakar Ramachandran1,2, Darcie Anderson2, Zachery Colbert1

  • 1Department of Radiation Oncology, Cancer Services, Princess Alexandra Hospital, Queensland, Australia.

Journal of Medical Physics
|April 21, 2025
PubMed
Summary

This study developed a deep learning model using Pix2Pix to enhance cone-beam computed tomography (CBCT) images, significantly improving image quality and reducing Hounsfield unit (HU) variations for better radiosurgery applications.

Keywords:
Computed tomographyPix2Pix modelcone-beam computed tomographydeep learninggamma knifesynthetic computed tomography

More Related Videos

Author Spotlight: Using Hyperpolarized Xenon-129 MRI to Study Lung Diseases
09:55

Author Spotlight: Using Hyperpolarized Xenon-129 MRI to Study Lung Diseases

Published on: January 5, 2024

1.1K
Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
07:57

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

2.7K

Related Experiment Videos

Last Updated: May 10, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

743
Author Spotlight: Using Hyperpolarized Xenon-129 MRI to Study Lung Diseases
09:55

Author Spotlight: Using Hyperpolarized Xenon-129 MRI to Study Lung Diseases

Published on: January 5, 2024

1.1K
Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
07:57

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

2.7K

Area of Science:

  • Medical Imaging
  • Radiosurgery
  • Artificial Intelligence

Background:

  • Cone-beam computed tomography (CBCT) is widely used in image-guided radiation therapy.
  • CBCT images often suffer from lower image quality and artifacts compared to conventional CT scans.
  • Improving CBCT image quality is crucial for accurate treatment planning and delivery.

Purpose of the Study:

  • To develop a modified Pix2Pix convolutional neural network (CNN) for enhancing CBCT image quality.
  • To reduce Hounsfield unit (HU) variations in CBCT images.
  • To generate synthetic CT (sCT) images that closely resemble ground truth CT scans.

Main Methods:

  • A deep learning model based on the Pix2Pix architecture was trained using paired CBCT and CT images from 40 patients.
  • The model was tested on data from 10 additional patients, processing 7484 slices of 512 × 512 pixels.
  • Image quality was quantitatively assessed using metrics like SSIM, MAE, RMSE, and PSNR.

Main Results:

  • The enhanced sCT images showed significant improvements in image quality compared to original CBCT images.
  • Structural Similarity Index (SSIM) increased from 0.85 ± 0.05 to 0.95 ± 0.03.
  • Mean Absolute Error (MAE) decreased from 77.37 ± 20.05 to 18.81 ± 7.22 (p < 0.0001).
  • Peak Signal-to-Noise Ratio (PSNR) and Root Mean Square Error (RMSE) also showed significant improvements.

Conclusions:

  • The developed deep learning framework effectively enhances CBCT image quality.
  • The generated sCT images exhibit reduced noise and artifacts, closely matching CT in HU values.
  • This approach holds significant potential for improving CBCT image fidelity in radiosurgery.