Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Computed Tomography

Computed Tomography

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...

You might also read

Related Articles

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

Sort by

Same author

Essential role of HDL on endothelial progenitor cell proliferation with PI3K/Akt/cyclin D1 as the signal pathway.

Experimental biology and medicine (Maywood, N.J.)·2010

Same author

Microfiberoptic measurement of extracellular space volume in brain and tumor slices based on fluorescent dye partitioning.

Biophysical journal·2010

Same author

Effect and mechanism of penetration enhancement of organic base and alcohol on glycyrrhetinic acid in vitro.

International journal of pharmaceutics·2010

Same author

[Adsorption of fluoride ions on a Ca-deficient hydroxyapatite].

Huan jing ke xue= Huanjing kexue·2010

Same author

Organocatalysis in cross-coupling: DMEDA-catalyzed direct C-H arylation of unactivated benzene.

Journal of the American Chemical Society·2010

Same author

[Prevention of hepatitis B virus vertical transmission: current situation and challenges.].

Zhonghua gan zang bing za zhi = Zhonghua ganzangbing zazhi = Chinese journal of hepatology·2010

Search research articles

Related Experiment Video

Updated: May 5, 2026

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

Spatiotemporal correlation enhanced real-time 4D-CBCT imaging using convolutional LSTM networks.

Hua Zhang^1,2, Kai Chen³, Xiaotong Xu^1,2

¹School of Biomedical Engineering, Southern Medical University, Guang Zhou, Guangdong, China.

Frontiers in Oncology

|August 20, 2024

Summary

This study introduces a novel method using spatiotemporal correlation to improve real-time four-dimensional cone beam CT (4D-CBCT) accuracy. The convolutional LSTM network effectively reconstructs 4D-CBCT, enhancing motion modeling for medical imaging.

Keywords:

4D-CBCT ConvLSTM PCA radiation therapy spatiotemporal

More Related Videos

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: May 5, 2026

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Medical Imaging
Radiological Physics
Computational Imaging

Background:

Real-time four-dimensional cone beam CT (4D-CBCT) is crucial for image-guided radiation therapy.
Accurate reconstruction of 4D-CBCT is challenging due to respiratory motion.
Existing methods often struggle to capture the complex spatiotemporal dynamics of breathing.

Purpose of the Study:

To enhance the accuracy of real-time 4D-CBCT imaging.
To incorporate spatiotemporal correlation from sequential projection images into 4D-CBCT estimation.
To develop a robust method for real-time respiratory motion modeling in CBCT.

Main Methods:

Derived 4D deformation vector fields (DVFs) from patient 4D-CT and used PCA for feature extraction.
Simulated extensive respiratory motion using PCA labels to generate 900 deformed CBCT volumes and corresponding DRRs.
Employed a convolutional LSTM (ConvLSTM) network trained on DRRs and PCA labels to estimate spatiotemporal correlations for real-time 4D-CBCT prediction.

Main Results:

The ConvLSTM network demonstrated superior performance over other networks in both phantom and clinical data.
Achieved high accuracy metrics: XCAT phantom (MAPE 0.0459, PSNR 64.6742, RMSE 0.0011) and patient data (MAPE 0.0934, PSNR 63.7294, RMSE 0.0019).
Quantification evaluation included MAE, NCC, SSIM, PSNR, RMSE, and MAPE, confirming the model's effectiveness.

Conclusions:

Spatiotemporal correlation-based respiration motion modeling offers a promising solution for accurate real-time 4D-CBCT reconstruction.
The proposed ConvLSTM approach significantly improves the quality and accuracy of 4D-CBCT.
This method has the potential to advance image-guided interventions requiring precise motion management.