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: Jul 23, 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

2.8K

Adaptive scatter kernel deconvolution modeling for cone-beam CT scatter correction via deep reinforcement learning.

Zun Piao1, Wenxin Deng1, Shuang Huang1

  • 1School of Biomedical Engineering, Southern Medical University, Guangzhou, China.

Medical Physics
|July 17, 2023
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

COX-2 inhibition improves immune system homeostasis and decreases liver damage in septic rats.

The Journal of surgical research·2009
Same author

Mass spectral characterization of organophosphate-labeled, tyrosine-containing peptides: characteristic mass fragments and a new binding motif for organophosphates.

Journal of chromatography. B, Analytical technologies in the biomedical and life sciences·2009
Same author

3D-SURFER: software for high-throughput protein surface comparison and analysis.

Bioinformatics (Oxford, England)·2009
Same author

Total arch replacement with stented elephant trunk technique: a proposed treatment for complicated Stanford type B aortic dissection.

Journal of cardiac surgery·2009
Same author

Top-emitting white organic light-emitting devices with a one-dimensional metallic-dielectric photonic crystal anode.

Optics letters·2009
Same author

[Detection of tick and tick-borne pathogen in some ports of Inner Mongolia].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2009

This study introduces an intelligent scatter correction framework for cone-beam CT (CBCT) imaging. By integrating scatter kernel deconvolution (SKD) with deep reinforcement learning (DRL), the method significantly improves scatter estimation accuracy and CBCT image quality.

Area of Science:

  • Medical Imaging
  • Computational Imaging
  • Artificial Intelligence in Medical Devices

Background:

  • Photon scattering in cone-beam CT (CBCT) degrades image quality and CT value accuracy, limiting clinical applications.
  • Conventional scatter kernel deconvolution (SKD) requires Monte Carlo simulations for parameter determination, hindering accurate scatter estimation.
  • Existing methods lack intelligent optimization for scatter kernel parameters, impacting overall performance.

Purpose of the Study:

  • To develop an intelligent scatter correction framework for CBCT by integrating SKD with deep reinforcement learning (DRL).
  • To enhance scatter estimation accuracy within the SKD algorithm for improved CBCT image quality.
  • To enable adaptive parameter optimization for scatter kernel models.

Main Methods:

Keywords:
adaptive scatter kernel optimizationcone-beam CT scatter correctiondeep reinforcement learningscatter kernel deconvolution algorithm

More Related Videos

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

8.9K

Related Experiment Videos

Last Updated: Jul 23, 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

2.8K
Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

8.9K
  • A scatter kernel model was developed and iteratively convolved with raw CBCT projections.
  • A deep Q-network from DRL was employed for intelligent interaction and adaptive parameter optimization of the scatter kernel.
  • The framework was validated using CBCT head and pelvis simulation data and experimental measurement data, with U-net based scatter estimation used for comparison.

Main Results:

  • Simulation studies showed the proposed method achieved a Mean Absolute Percentage Error (MAPE) < 9.72% and Peak Signal-to-Noise Ratio (PSNR) > 23.90 dB, outperforming conventional SKD (MAPE min 17.92%, PSNR max 19.32 dB).
  • Experimental results demonstrated superior performance with MAPE < 17.79% and PSNR > 16.34 dB compared to a hardware-based beam stop array algorithm.
  • The intelligent framework significantly reduced scatter artifacts and improved CT value accuracy.

Conclusions:

  • An intelligent scatter correction framework combining a physical scatter kernel model with a DRL algorithm was successfully proposed.
  • The developed framework shows significant potential for improving the accuracy of clinical scatter correction methods.
  • This approach offers a pathway to achieve enhanced CBCT imaging quality for medical applications.