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

Dual-scan conformal cone-beam CT for targeted image-quality improvement using dynamic collimation.

Journal of applied clinical medical physics·2026
Same author

Multi-level osmoadaptation strategies of filamentous cyanobacteria within oxygenic photogranules under high salinity stress.

Water research·2026
Same author

Gut microbial metabolites in colorectal cancer: dual roles in tumorigenesis, immune crosstalk, and therapeutic innovation.

Frontiers in cellular and infection microbiology·2026
Same author

Global spotlight editorial: Advancing treatment planning to promote equity through AI and automation in clinical medical physics.

Journal of applied clinical medical physics·2026
Same author

Microbial selective response to photogenerated electrons stabilizes nitrogen removal in oxygenic photogranules under low C/N conditions.

Water research·2026
Same author

Artificial intelligence for real-time motion tracking in MRI-guided radiotherapy: A systematic review.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026

Related Experiment Video

Updated: May 22, 2025

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

An MR-only deep learning inference model-based dose estimation algorithm for MR-guided adaptive radiation therapy.

Zhiqiang Liu1, Kuo Men1, Weigang Hu2,3,4,5

  • 1Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.

Medical Physics
|March 16, 2025
PubMed
Summary
This summary is machine-generated.

This study developed a deep learning (DL) model for Magnetic Resonance-guided Adaptive Radiation Therapy (MRgART) dose calculations using only MR images. The novel MR-only approach significantly improves speed and accuracy for adaptive radiotherapy workflows.

Keywords:
MR‐guided adaptive radiation therapyMR‐only dose calculationdeep learning

More Related Videos

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
10:48

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

Published on: December 28, 2017

9.4K
Expedited Radiation Biodosimetry by Automated Dicentric Chromosome Identification ADCI and Dose Estimation
10:33

Expedited Radiation Biodosimetry by Automated Dicentric Chromosome Identification ADCI and Dose Estimation

Published on: September 4, 2017

15.6K

Related Experiment Videos

Last Updated: May 22, 2025

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
PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
10:48

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

Published on: December 28, 2017

9.4K
Expedited Radiation Biodosimetry by Automated Dicentric Chromosome Identification ADCI and Dose Estimation
10:33

Expedited Radiation Biodosimetry by Automated Dicentric Chromosome Identification ADCI and Dose Estimation

Published on: September 4, 2017

15.6K

Area of Science:

  • Medical Physics
  • Radiotherapy Technology
  • Artificial Intelligence in Medicine

Background:

  • Magnetic Resonance-guided Adaptive Radiation Therapy (MRgART) integrates MRI with LINAC for precise cancer treatment.
  • Real-time anatomical adjustments in MRgART necessitate rapid and accurate dose calculation algorithms.
  • Traditional CT-based methods and ray-tracing are too slow for online adaptive workflows, highlighting the need for advanced solutions like deep learning (DL).

Purpose of the Study:

  • To develop a DL-based dose calculation engine for MRgART that operates exclusively on MR images.
  • To eliminate the reliance on CT images and time-consuming ray-tracing processes in MRgART.
  • To provide accurate and rapid dose calculations essential for the MRgART workflow.

Main Methods:

  • A U-Net inspired deep residual network was employed to directly link distance-corrected conical (DCC) fluence maps to dose distributions.
  • The model was trained, validated, and tested using data from 30 prostate cancer patients undergoing Intensity-Modulated Radiation Therapy (IMRT) on an MR-guided LINAC.
  • Performance was evaluated against Monte Carlo (MC) methods using metrics like mean absolute error (MAE), 3D gamma analysis, and dose-volume histograms (DVHs).

Main Results:

  • The DL model achieved high accuracy, with median MAE of 1.2% (whole body), 1.9% (targets), and 1.1% (OARs).
  • Median 3D gamma passing rates (3%/3 mm) were 94.8% (whole body), 95.7% (targets), and 98.7% (OARs).
  • Dice similarity coefficients (DSC) for isodose lines averaged 0.94, and DL calculations were clinically equivalent to MC methods based on DVH and dosimetric indices.

Conclusions:

  • A novel MR-only dose calculation engine was successfully developed, removing the need for CT scans and ray-tracing.
  • The DL approach significantly enhances the efficiency and accuracy of MRgART, particularly for prostate cancer treatment.
  • This method shows promise for wider application across various cancer types and MR-linac systems, enabling streamlined radiation therapy planning.