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

Technical note: real-time MLC control and latency measurement optimization with external verification.

Physics in medicine and biology·2026
Same author

Comparative evaluation of 4DCT and 4DCBCT for motion and volume measurement accuracy in a dynamic phantom.

Journal of applied clinical medical physics·2026
Same author

Development and validation of a TOPAS Monte Carlo model for a 0.5 T bi-planar Linac-MR.

Medical physics·2026
Same author

Towards robust deep learning-based autosegmentation in MRI-planned gynecological brachytherapy: Importance of scalable development and comprehensive evaluation.

Brachytherapy·2026
Same author

Retraction: Minimal skin dose increase in longitudinal rotating biplanar linac-MR systems: examination of radiation energy and flattening filter design (2016<i>Phys. Med. Biol.</i>61 3527).

Physics in medicine and biology·2025
Same author

Quality of Life of Stereotactic Versus Hypofractionated Radiation Therapy for Inoperable Stage I Non-Small Cell Lung Cancer: Results From the LUSTRE Trial.

International journal of radiation oncology, biology, physics·2025

Related Experiment Video

Updated: Apr 12, 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

16.3K

Neural-network based autocontouring algorithm for intrafractional lung-tumor tracking using Linac-MR.

Jihyun Yun1, Eugene Yip1, Zsolt Gabos2

  • 1Department of Oncology, Medical Physics Division, University of Alberta, 11560 University Avenue, Edmonton, Alberta T6G 1Z2, Canada.

Medical Physics
|May 17, 2015
PubMed
Summary

A new neural-network based autocontouring algorithm enables precise intrafractional lung tumor tracking using Linac-MR. This automated system demonstrates high accuracy in both phantom and in-vivo studies, paving the way for improved radiotherapy.

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.8K
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

1.4K

Related Experiment Videos

Last Updated: Apr 12, 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

16.3K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.8K
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

1.4K

Area of Science:

  • Medical Imaging
  • Radiotherapy
  • Artificial Intelligence

Background:

  • Accurate intrafractional tumor tracking is crucial for effective lung cancer radiotherapy.
  • Current manual contouring methods can be time-consuming and prone to inter-observer variability.
  • Linac-MR systems offer real-time imaging capabilities for adaptive radiotherapy.

Purpose of the Study:

  • To develop and evaluate a neural-network based autocontouring algorithm for intrafractional lung tumor tracking.
  • To assess the algorithm's performance using phantom and in-vivo MR images within a Linac-MR environment.
  • To enable automated, accurate tumor delineation during radiotherapy delivery.

Main Methods:

  • Developed a pulse-coupled neural network-based autocontouring algorithm for lung tumors.
  • Algorithm determines tumor shape and position from intrafractional MR images without user input during treatment.
  • Evaluated performance using a motion phantom and four lung cancer patients, simulating 0.5 T Linac-MR conditions.

Main Results:

  • The algorithm successfully contoured moving tumors in dynamic MR images acquired every 275 ms.
  • Phantom studies yielded high accuracy: mean Dice Similarity Index (DSI) of 0.95-0.96, Hausdorff Distance (HD) of 2.61-2.82 mm.
  • In-vivo studies showed promising results: mean DSI of 0.87-0.92, HD of 3.12-4.35 mm, and centroid accuracy of 1.03-1.35 mm.
  • Autocontouring speed was rapid, under 20 ms per image.

Conclusions:

  • A novel neural-network based autocontouring algorithm for intrafractional lung tumor tracking using Linac-MR has been successfully developed and validated.
  • The algorithm demonstrated significant accuracy and speed in both phantom and in-vivo evaluations.
  • Results indicate the feasibility and potential of this automated approach for enhancing lung cancer radiotherapy precision.