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

Search research articles

Related Experiment Video

Updated: Jun 6, 2026

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

A state-based probabilistic model for tumor respiratory motion prediction.

Alan Kalet¹, George Sandison, Huanmei Wu

¹Department of Radiation Oncology, University of Washington Medical Center, Box 356043 Seattle, WA 98195-6043, USA. amkalet@uw.edu

Physics in Medicine and Biology

|November 30, 2010

Summary

This study introduces a new probabilistic model using hidden Markov models (HMM) to predict lung tumor motion during radiation therapy. The model accurately predicts future tumor positions, improving accuracy for gated radiation therapy, especially with longer system delays.

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

Global patterns and risk factors of breast cancer in women under 35: a population-based study.

Breast (Edinburgh, Scotland)·2026

Same author

Uncovering geographic variations in HIV burden and prevention: a comparative analysis of AIDSVu data across three U.S. counties.

AIDS care·2026

Same author

Efficacy of raltegravir in achieving virological suppression at delivery in HIV-positive pregnant women: a systematic review and meta-analysis.

BMC pregnancy and childbirth·2025

Same author

Integrating Legal Aid into HIV Care: Evaluating the Impact of a Medical-Legal Partnership on Viral Suppression Outcomes.

AIDS and behavior·2025

Same author

Long-term trends in major amputations for the state of Pennsylvania.

Journal of vascular surgery·2025

Same author

Integrating Social Determinants of Health into Knowledge Graphs: Evaluating Prediction Bias and Fairness in Healthcare.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2025

Area of Science:

Medical Physics
Computational Biology
Radiotherapy Technology

Background:

Accurate prediction of tumor motion is crucial for effective gated radiation therapy.
Existing methods for predicting tumor motion have limitations, particularly with increased system latency.
Breathing-induced tumor motion introduces significant challenges in delivering precise radiation doses.

Purpose of the Study:

To develop and evaluate a novel probabilistic mathematical model for predicting tumor motion and position.
To assess the model's performance in gated radiation therapy scenarios with varying system delays.
To compare the proposed model's accuracy against established prediction methods.

Main Methods:

A finite state representation of breathing (inhale, exhale, end-exhale) was used.

More Related Videos

Management of Respiratory Motion Artefacts in 18F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm

Management of Respiratory Motion Artefacts in ¹⁸F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm

Published on: July 23, 2020

Related Experiment Videos

Last Updated: Jun 6, 2026

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

Management of Respiratory Motion Artefacts in 18F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm

Management of Respiratory Motion Artefacts in ¹⁸F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm

Published on: July 23, 2020

Hidden Markov Models (HMM) were employed to analyze breathing state sequences and predict future states and observables.

K-means clustering was utilized to associate states with observables, enabling velocity prediction.

A time-average model was computed for comparison.

The model was evaluated using tumor motion data from four lung cancer patients.

Main Results:

The HMM method achieved a 100% duty cycle at 33 ms latency and 91% at 200 ms latency.
At 1000 ms latency, the HMM method achieved approximately 40% duty cycle, outperforming linear and no-prediction methods.
Root-mean-square (RMS) errors for the HMM were lower than linear and no-prediction methods at 1000 ms latency.
The time-average HMM prediction outperformed other models for system latencies exceeding 400 ms.
Predicted state sequences correlated well with known data, approaching the theoretical HMM prediction limit.

Conclusions:

The proposed probabilistic HMM-based model offers accurate tumor motion prediction for gated radiation therapy.
The model demonstrates superior performance, particularly in scenarios with longer system latencies (>400 ms).
This approach has the potential to enhance treatment accuracy and efficacy in radiation oncology.