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: Jun 26, 2026

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy
08:17

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy

Published on: June 7, 2015

Automatic beam angle optimization in brain tumor radiotherapy using deep reinforcement learning.

Han Guo1, Zhiqing Xiao1, Huandi Zhou2

  • 1Department of radiation oncology, the Second Hospital of Hebei Medical University, Heping west road, Shijiazhuang, 050000, Asia, China.

Physica Medica : PM : an International Journal Devoted to the Applications of Physics to Medicine and Biology : Official Journal of the Italian Association of Biomedical Physics (AIFB)
|June 24, 2026
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

Advances in Ammonium Ion Supercapacitors Based on Two-Dimensional Electrode Materials: A Comprehensive Review.

Chemical record (New York, N.Y.)·2026
Same author

Grade-Dependent Prognostic Value of Classical Clinicopathological Factors in Glioma: A Single-Center Retrospective Study.

Journal of clinical medicine·2026
Same author

Study on luminescence properties of GaN photonic crystal resonators based on nanopore confinement.

Optics express·2026
Same author

IL-33/TGF-β/IL-4-induced bone marrow-derived DC9 subset promotes Th9 differentiation and allergic airway inflammation.

Cell reports·2026
Same author

SMC3 Is Highly Expressed in Gliomas and Is Associated With Favorable Prognosis and B Cell-Related Immune Features.

Technology in cancer research & treatment·2026
Same author

The multilevel exploration test, a novel paradigm to measure exploratory behavior in depression animal models and the involvement of the PL-ZI circuit.

Acta pharmacologica Sinica·2026
Same journal

Proton RBE for in vivo model systems: LET and dose dependencies for early and late biological endpoints.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2026
Same journal

AI-augmented thyroid scintigraphy for robust classification of disease.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2026
Same journal

Updating national diagnostic reference levels for adult cardiac interventional procedures in Switzerland.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2026
Same journal

Adoption of AI-driven automation and adaptive radiotherapy in clinical practice: results from a national survey.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2026
Same journal

Sivan Unit (SU) for standardization of voxel intensity in CBCT: A multi-vendor, multi-centric validation study.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2026
Same journal

VIT-MBRT, a GPU accelerated Monte Carlo tool for investigations on preclinical minibeam radiation therapy.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2026
See all related articles
This summary is machine-generated.

Deep reinforcement learning (DRL) shows promise in radiotherapy, developing an automatic beam arrangement algorithm that improved plan scores in brain tumor cases. This DRL framework offers potential value for beam angle optimization in clinical settings.

Area of Science:

  • Medical Physics
  • Radiotherapy Optimization
  • Artificial Intelligence in Medicine

Background:

  • Radiotherapy planning involves complex beam arrangement for optimal dose delivery.
  • Current methods can be time-consuming and may not always achieve ideal configurations.
  • Exploring advanced computational techniques is crucial for improving treatment planning efficiency and effectiveness.

Purpose of the Study:

  • To develop and evaluate a deep reinforcement learning (DRL) algorithm for automatic beam arrangement in radiotherapy.
  • To assess the clinical potential of DRL in optimizing beam angle selection for brain tumor treatments.
  • To compare the performance of DRL-generated plans against traditional methods.

Main Methods:

  • The Soft Actor-Critic (SAC) algorithm, a DRL approach, was implemented using patient data from brain tumor cases.
Keywords:
Automatic beam angle optimizationDeep reinforcement learningMulti-agent parallel samplingSAC algorithm

More Related Videos

Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation
06:32

Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation

Published on: July 14, 2023

Related Experiment Videos

Last Updated: Jun 26, 2026

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy
08:17

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy

Published on: June 7, 2015

Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation
06:32

Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation

Published on: July 14, 2023

  • Input data included three-dimensional dose distributions, target areas, and isocenters.
  • The Eclipse planning system was integrated via ESAPI scripts, utilizing multi-agent parallel sampling for efficient plan generation.

    • Main Results:

    • The DRL model achieved a higher plan score (73.48±23.17) on the validation set compared to initial plans (66.16±26.76).
    • In training set comparisons, DRL-generated plans (83.33±25.18) significantly outperformed initial plans (64.43±24.37).
    • A comparison with manual arrangements showed DRL plans scoring higher (87.25±16.67) than manual plans (79.94±20.02), with P < 0.05.

    Conclusions:

    • The developed DRL framework demonstrates feasibility and potential for improving beam arrangement in radiotherapy for brain tumors.
    • The algorithm generated plans with superior scores, indicating its value for beam angle optimization.
    • This study supports the exploration of DRL for enhancing radiotherapy treatment planning processes.