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

Deep learning based 3D brain metastasis synthesis with configurable parameters for 3D data augmentation.

Scientific reports·2026
Same author

Modality-agnostic, patient-specific digital twins modeling temporally varying digestive motion.

Physics in medicine and biology·2025
Same author

Extended nnU-Net for Brain Metastasis Detection and Segmentation in Contrast-Enhanced Magnetic Resonance Imaging With a Large Multi-Institutional Data Set.

International journal of radiation oncology, biology, physics·2024
Same author

Does Vascular Collapse Occur After Treatment of Hepatocellular Cancer With Stereotactic Body Radiation Therapy?

International journal of radiation oncology, biology, physics·2023
Same author

Contrastive self-supervised learning from 100 million medical images with optional supervision.

Journal of medical imaging (Bellingham, Wash.)·2022
Same author

Gender-Based Discrimination and Sexual Harassment in Medical Physics.

International journal of radiation oncology, biology, physics·2022

Related Experiment Video

Updated: Jul 9, 2025

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
10:06

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

12.9K

Volumetric MRI with sparse sampling for MR-guided 3D motion tracking via sparse prior-augmented implicit neural

Lianli Liu1, Liyue Shen2, Adam Johansson3,4,5

  • 1Department of Radiation Oncology, Stanford University, Palo Alto, California, USA.

Medical Physics
|November 28, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces a novel method for reconstructing 3D MRI using sparse data, improving motion tracking for radiation therapy. The approach simplifies workflows by reducing the need for extensive training datasets.

Keywords:
MR‐guided radiotherapydeep learningimage reconstructionmotion management

More Related Videos

Profiling Maternal Behavior Responses During Whole-Brain Imaging
07:12

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Published on: January 24, 2025

739
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

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

Published on: June 30, 2018

11.7K

Related Experiment Videos

Last Updated: Jul 9, 2025

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
10:06

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

12.9K
Profiling Maternal Behavior Responses During Whole-Brain Imaging
07:12

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Published on: January 24, 2025

739
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

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

Published on: June 30, 2018

11.7K

Area of Science:

  • Medical Imaging
  • Radiotherapy
  • Machine Learning

Background:

  • Volumetric MRI reconstruction from sparse samples is crucial for 3D motion tracking in MR-guided radiation therapy.
  • Current data-driven methods require large, time-consuming training datasets, posing clinical challenges.

Purpose of the Study:

  • To investigate volumetric MRI reconstruction from sparse orthogonal slices using implicit neural representation (NeRP) learning.
  • To leverage sparse priors from static 3D MRI for enhanced 3D motion tracking in radiotherapy.

Main Methods:

  • Trained a multi-layer perceptron network to parameterize a patient-specific NeRP model using voxel intensities and motion states.
  • Embedded breathing motion priors into network weights using two static 3D MRI scans (inhale/exhale).
  • Augmented priors to 31 motion states and trained the network with sparse orthogonal MRI slices for volumetric reconstruction.

Main Results:

  • Achieved high image quality with peak signal-to-noise ratio of 38.02 ± 2.60 dB and SSIM of 0.98 ± 0.01.
  • Demonstrated consistent gross tumor volume (GTV) motion tracking with Hausdorff distance < voxel dimension.
  • Reported mean GTV centroid position difference < 1 mm in all directions.

Conclusions:

  • Developed a prior-augmented NeRP model for volumetric MRI reconstruction from sparse cine slices.
  • Requires only one inhale and one exhale 3D MRI for training, simplifying prior motion learning.
  • Potential to improve MR-guided radiotherapy precision and streamline clinical workflows by eliminating large datasets.