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

A standardized workflow for the development and manufacturing of tissue-equivalent anthropomorphic phantoms for radiotherapy using 3D-printing.

Physics in medicine and biology·2026
Same author

Uncertainty-Aware Explainable AI for Pancreatic Cysts: Identifying Deep Learning Vulnerabilities and Ensuring Safe Clinical Triage in IPMN Management.

Research square·2026
Same author

Assessing dosimetric uncertainties in Papillon+ contact x-ray brachytherapy for rectal cancer: impact of beam quality and tumour geometry.

Physics in medicine and biology·2026
Same author

Evaluation of proton range differences in photon-counting and dual-energy computed tomography across imaging doses and anthropomorphic phantom sizes.

Physics in medicine and biology·2026
Same author

Evaluation of radiological properties and anisotropy with air channels analysis in 3D-printed flexible lung-mimicking materials for radiotherapy.

Physics in medicine and biology·2026
Same author

Gaze-Guided Medical Image Segmentation: A Training-Free Approach using SAM Foundation Model.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025

Related Experiment Video

Updated: Jun 18, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K

Turning the attention to time-resolved EPID-images: treatment error classification with transformer multiple instance

Viacheslav Iarkin1, Evelyn E C de Jong1, Rutger Hendrix2

  • 1Department of Radiation Oncology (Maastro), GROW Research Institute for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, The Netherlands.

Physics in Medicine and Biology
|July 31, 2024
PubMed
Summary

This study introduces an AI-powered method for real-time radiotherapy dosimetry using time-resolved data. The new approach accurately classifies treatment errors, improving external beam radiation therapy quality.

Keywords:
EPID dosimetrymultiple instance learningradiotherapytransformertreatment verification

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

381
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K

Related Experiment Videos

Last Updated: Jun 18, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

381
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K

Area of Science:

  • Medical Physics
  • Artificial Intelligence in Healthcare
  • Radiation Oncology

Background:

  • Current radiotherapy error classification methods using thresholding may miss errors due to data compression.
  • Time-integrated (TI) analysis of electronic portal imaging device (EPID) data shows promise but can obscure errors during dynamic treatments.
  • Manual analysis of complex, large time-resolved (TR) dose data is impractical for clinical decision-making.

Purpose of the Study:

  • To develop an artificial intelligence-assisted in vivo dosimetry method using time-resolved (TR) dose verification data.
  • To improve the quality and accuracy of external beam radiotherapy through enhanced error detection.
  • To overcome limitations of TI data analysis by utilizing TR gamma maps for more precise error classification.

Main Methods:

  • Developed a transformer-based multiple instance learning approach inspired by weakly supervised methods.
  • Utilized transfer learning, adapting models from TI to TR gamma maps.
  • Simulated TR gamma maps for each volumetric modulated arc radiotherapy angle to detect complex treatment errors.

Main Results:

  • The AI model achieved high accuracy in classifying treatment errors.
  • Achieved up to 0.94 accuracy for 11 error types and 0.81 accuracy for 22 error magnitude classes in the test set.
  • Demonstrated superior performance compared to models using TI data for error classification.

Conclusions:

  • The developed AI model efficiently handles complex TR dose data, significantly improving treatment error classification.
  • This TR dosimetry method enhances decision-making in radiotherapy delivery.
  • The approach offers a viable solution for the impracticality of manual analysis of large TR datasets.