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

Magnetic Resonance Imaging

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...

Positron Emission Tomography

Positron Emission Tomography

Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body being...

You might also read

Related Articles

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

Sort by

Same author

A server-based solution for misregistration correction in PET/CT using limited-coverage and data-driven gated CT.

Medical physics·2026

Same author

LDM-Morph: Latent diffusion model guided deformable image registration.

Pattern recognition·2026

Same author

Landmark matching and B-spline implicit neural representations for diffusion-weighted imaging distortion correction.

Physics in medicine and biology·2026

Same author

'See' through the surface: surface-derived three-dimensional AI-driven real-time imaging solution for intra-treatment image guidance.

Machine Learning. Health·2026

Same author

Artificial intelligence (AI)-based multi-organ contour quality assurance with uncertainty estimation for online adaptive radiotherapy (oART).

Machine Learning. Health·2026

Same author

Band-limited implicit neural representations for diffusion-weighted imaging denoising.

Physics in medicine and biology·2025

Search research articles

Related Experiment Video

Updated: Jun 21, 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

Dynamic CBCT imaging using prior model-free spatiotemporal implicit neural representation (PMF-STINR).

Hua-Chieh Shao¹, Tielige Mengke¹, Tinsu Pan²

¹The Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX 75390, United States of America.

Physics in Medicine and Biology

|May 2, 2024

Summary

We developed a novel machine learning method for dynamic cone-beam computed tomography (CBCT) reconstruction, enabling accurate motion monitoring in radiotherapy. This approach reconstructs time-varying images from limited projections without prior models.

Keywords:

data-driven motion modeling deformable registration dynamic CBCT image reconstruction implicit neural representation

More Related Videos

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

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

Published on: August 12, 2018

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Related Experiment Videos

Last Updated: Jun 21, 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

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

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

Published on: August 12, 2018

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Area of Science:

Medical Imaging
Radiotherapy Physics
Machine Learning in Healthcare

Background:

Dynamic cone-beam computed tomography (CBCT) is crucial for real-time motion monitoring in radiotherapy, but its reconstruction is challenging due to under-sampled spatiotemporal data.
Existing methods struggle with fast anatomical motion and require prior knowledge or complex data sorting, limiting their clinical applicability.

Purpose of the Study:

To develop and evaluate a novel machine learning technique, prior-model-free spatiotemporal implicit neural representation (PMF-STINR), for reconstructing dynamic CBCTs from limited x-ray projections.
To enable accurate intra-scan motion reconstruction without relying on patient-specific prior models or motion sorting.

Main Methods:

Developed PMF-STINR, a joint image reconstruction and registration approach utilizing spatial and temporal implicit neural representations (INRs).
Employed a learning-based B-spline motion model coupled with temporal INR to capture deformable motion during reconstruction.
All components (spatial INR, temporal INR, B-spline model) are learned on-the-fly in a one-shot manner, eliminating the need for prior information.

Main Results:

PMF-STINR accurately and robustly reconstructed dynamic CBCTs across diverse datasets, including digital phantoms, physical phantoms, and multi-institutional patient data.
The method successfully captured highly irregular motion with high temporal resolution (approximately 0.1 s) and sub-millimeter accuracy.
Performance was validated across various imaging protocols, demonstrating robustness and generalizability.

Conclusions:

PMF-STINR effectively reconstructs dynamic CBCTs and resolves intra-scan motion from conventional 3D CBCT scans without prior anatomical or motion models.
This one-shot learning approach offers a promising tool for advanced motion management in radiotherapy, providing richer motion information than traditional 4D-CBCT.