Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Positron Emission Tomography

Positron Emission Tomography

Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Development of a spatially indexed dose-volume histogram for treatment plan evaluation.

Journal of radiation research·2026

Same author

Multi-modality brain tumor segmentation using dual-attention generative adversarial network.

Reports of practical oncology and radiotherapy : journal of Greatpoland Cancer Center in Poznan and Polish Society of Radiation Oncology·2026

Same author

Latent density discrepancies in commercial lung-equivalent inserts and their clinical dosimetric impact.

Journal of applied clinical medical physics·2026

Same author

[Multicenter Online Evaluation of IGRT Irradiation Position Accuracy Using an EPID-based End-to-end Postal Audit].

Nihon Hoshasen Gijutsu Gakkai zasshi·2026

Same author

[Impact of the Number of Subfields in an Automatic Field-in-field Technique on Dose Distribution and Delivery Efficiency in Tangential Whole-breast Irradiation].

Nihon Hoshasen Gijutsu Gakkai zasshi·2026

Same author

Credentialing of small-field dosimetry for the lung SBRT in Japan Clinical Oncology Group clinical trial.

Journal of applied clinical medical physics·2026

Search research articles

Related Experiment Video

Updated: Aug 15, 2025

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

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

A synthesized gamma distribution-based patient-specific VMAT QA using a generative adversarial network.

Takaaki Matsuura^1,2, Daisuke Kawahara², Akito Saito³

¹Hiroshima High-Precision Radiotherapy Cancer Center, Hiroshima, Japan.

Medical Physics

|January 7, 2023

Summary

This study introduces a novel artificial intelligence system using a generative adversarial network (GAN) to predict failing points in volumetric modulated arc therapy (VMAT) quality assurance (QA). The AI system accurately identifies dose discrepancies, enhancing patient-specific radiotherapy.

Keywords:

GAN deep learning gamma distribution gamma passing rate

More Related Videos

Construction of a Preclinical Multimodality Phantom Using Tissue-mimicking Materials for Quality Assurance in Tumor Size Measurement

Construction of a Preclinical Multimodality Phantom Using Tissue-mimicking Materials for Quality Assurance in Tumor Size Measurement

Published on: July 29, 2013

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy

Published on: June 7, 2015

Related Experiment Videos

Last Updated: Aug 15, 2025

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

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

Construction of a Preclinical Multimodality Phantom Using Tissue-mimicking Materials for Quality Assurance in Tumor Size Measurement

Construction of a Preclinical Multimodality Phantom Using Tissue-mimicking Materials for Quality Assurance in Tumor Size Measurement

Published on: July 29, 2013

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy

Published on: June 7, 2015

Area of Science:

Radiotherapy Physics
Medical Imaging
Artificial Intelligence in Medicine

Background:

Artificial intelligence (AI)-based gamma passing rate (GPR) prediction offers a time-efficient method for patient-specific quality assurance (QA) in volumetric modulated arc therapy (VMAT).
A key limitation of current AI methods is the loss of locational information regarding dose accuracy within the GPR value.

Purpose of the Study:

To develop a deep convolutional generative adversarial network (GAN) capable of predicting failing points within the gamma distribution and the GPR for VMAT QA.
To synthesize gamma distributions for VMAT QA using a GAN to overcome the limitations of existing prediction methods.

Main Methods:

Measured fluence maps from 270 VMAT prostate cancer treatment beams using an electronic portal imaging device.
Analyzed gamma distributions with varying tolerances (3%/2-mm, 2%/1-mm, 1%/1-mm, 1%/0.5-mm) and utilized a GAN to create an image prediction network for synthesizing gamma distributions.
Evaluated the sensitivity, specificity, and accuracy of detecting failing points and compared measured GPR (mGPR) with predicted GPR (pGPR) from synthesized distributions.

Main Results:

Root mean squared errors between mGPR and pGPR ranged from 1.0% to 3.6% across different tolerances.
Accuracies for detecting failing points were high, ranging from 93.7% to 98.9%.
Optimal sensitivity (82.7%) and specificity (99.6%) were achieved with the 1%/0.5-mm and 3%/2-mm tolerances, respectively.

Conclusions:

A novel GAN-based system was developed for patient-specific VMAT QA using synthesized gamma distributions.
The system demonstrates high performance in detecting failing points, indicating its promise for improving radiotherapy quality assurance.
This AI-driven approach enhances the precision and reliability of VMAT QA by providing locational dose accuracy information.