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

Water calorimetry-based beam quality correction factors for carbon and helium ion beams.

Physics in medicine and biology·2026
Same author

Perirectal spacers and endorectal balloons in external beam radiotherapy for prostate cancer: a review of prospective studies.

Strahlentherapie und Onkologie : Organ der Deutschen Rontgengesellschaft ... [et al]·2026
Same author

Prospective evaluation of acute side effects profiles in moderately hypofractionated whole-pelvic radiotherapy for prostate cancer.

Clinical and translational radiation oncology·2026
Same author

The dual gap ionization chamber: a novel ionization chamber design for reference dosimetry to automatically correct for recombination losses in emerging radiotherapy modalities.

Physics in medicine and biology·2026
Same author

Experimental determination of beam quality correction factors in scanned proton beams using water calorimetry.

Physics in medicine and biology·2026
Same author

Impact of the breathing motion prediction horizon on the performance of bidirectional classical recurrent neural and temporal Kolmogorov-Arnold networks.

Physics in medicine and biology·2025

Related Experiment Video

Updated: Jul 26, 2025

Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System
08:25

Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System

Published on: April 11, 2018

15.4K

Generating deliverable DICOM RT treatment plans for prostate VMAT by predicting MLC motion sequences with an

Gerd Heilemann1, Lukas Zimmermann1, Raphael Schotola1

  • 1Department of Radiation Oncology, Comprehensive Cancer Center Vienna, Medical University Vienna, Vienna, Austria.

Medical Physics
|June 14, 2023
PubMed
Summary

A deep learning model accurately predicts radiotherapy plans for prostate cancer, enabling direct use with linear accelerators and streamlining treatment planning. This advances autonomous radiotherapy workflows for improved efficiency.

Keywords:
MLC sequencingautomatic planningdeep learning

More Related Videos

Proton Therapy Delivery and Its Clinical Application in Select Solid Tumor Malignancies
08:34

Proton Therapy Delivery and Its Clinical Application in Select Solid Tumor Malignancies

Published on: February 6, 2019

20.4K
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

15.8K

Related Experiment Videos

Last Updated: Jul 26, 2025

Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System
08:25

Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System

Published on: April 11, 2018

15.4K
Proton Therapy Delivery and Its Clinical Application in Select Solid Tumor Malignancies
08:34

Proton Therapy Delivery and Its Clinical Application in Select Solid Tumor Malignancies

Published on: February 6, 2019

20.4K
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

15.8K

Area of Science:

  • Medical Physics
  • Radiotherapy
  • Artificial Intelligence

Background:

  • Deep learning is an active area of research for automated radiotherapy planning.
  • Current methods often still require a treatment planning system (TPS).

Purpose of the Study:

  • To develop and validate a deep learning model capable of generating deliverable DICOM RT treatment plans.
  • The model predicts multileaf collimator (MLC) motion sequences for prostate VMAT radiotherapy, directly usable by a linear accelerator (LINAC).

Main Methods:

  • An encoder-decoder network was trained on 465 prostate VMAT plans and validated on 77.
  • Performance was assessed on a separate test set of 77 plans.
  • Loss functions included leaf and jaw positions and monitor units, with leaf loss weighted heavily; plans were recalculated in a TPS for comparison.

Main Results:

  • Generated plans showed good agreement with original data (91.9% ± 7.1% gamma passing rate).
  • Slightly lower PTV coverage (D98% = 92.9% ± 2.6%) was observed compared to original plans (95.7% ± 2.2%).
  • No significant differences in mean bladder or rectal dose; minimal differences in maximum doses were noted.

Conclusions:

  • The deep learning model successfully predicts MLC motion sequences for prostate VMAT, removing the need for TPS sequencing.
  • This facilitates autonomous treatment planning and enables more efficient workflows for real-time or online adaptive radiotherapy.