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 Experiment Video

Updated: Jun 19, 2026

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

Neural network dose models for knowledge-based planning in pancreatic SBRT.

Warren G Campbell1, Moyed Miften1, Lindsey Olsen2

  • 1Department of Radiation Oncology, University of Colorado School of Medicine, Aurora, CO, 80045, USA.

Medical Physics
|October 11, 2017
PubMed
Summary

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

Adjuvant Chemotherapy ± Chemoradiotherapy for Adenocarcinoma of the Pancreatic Head: Results of the Radiotherapy Random Assignment of NRG Oncology/RTOG 0848.

Journal of clinical oncology : official journal of the American Society of Clinical Oncology·2026
Same author

Moving beyond anatomy: the future of rectal cancer management is biologically-informed, response-adapted, and patient-centered.

Clinical and translational radiation oncology·2026
Same author

Dosimetric Predictors of Problematic Receptive Anal Intercourse After Prostate Radiation Therapy.

Advances in radiation oncology·2026
Same author

Does Radiation Boost Dose Affect Organ Preservation Rates? A Secondary Analysis of the Organ Preservation in Patients With Rectal Adenocarcinoma Trial.

International journal of radiation oncology, biology, physics·2026
Same author

The Impact of Lung and Heart Radiation Dose During Preoperative Chemoradiation on Overall Survival in Esophageal Cancer-A Post Hoc Analysis of CALGB 80803 (Alliance).

International journal of radiation oncology, biology, physics·2026
Same author

Dose-Volume Histogram Compendium of Dose Constraints for Treatment Planning: An ASTRO Consensus Paper.

Practical radiation oncology·2026

Artificial neural network dose models (ANN-DMs) accurately predict physician-approved stereotactic body radiation therapy (SBRT) plans for pancreatic cancer. Tailoring models to individual physician techniques significantly improved accuracy for SBRT delivery.

Area of Science:

  • Radiation Oncology
  • Medical Physics
  • Artificial Intelligence in Medicine

Background:

  • Stereotactic body radiation therapy (SBRT) for pancreatic cancer demands precise dose delivery to tumors while sparing critical organs like the duodenum and stomach.
  • Developing accurate predictive models for SBRT dose distributions is crucial for optimizing treatment planning and patient outcomes.

Purpose of the Study:

  • To develop and evaluate knowledge-based artificial neural network dose models (ANN-DMs) for predicting physician-approved dose distributions in pancreatic cancer SBRT.
  • To assess the impact of individual physician treatment variations on the accuracy of ANN-DMs.

Main Methods:

  • Arc-based SBRT plans for 43 pancreatic cancer patients were analyzed.
  • Physician-approved dose distributions from a commercial treatment planning system (TPS) were used to train ANN-DMs.
Keywords:
artificial neural networkdose-predictionknowledge-based planningpancreatic cancerstereotactic radiation therapy

More Related Videos

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Related Experiment Videos

Last Updated: Jun 19, 2026

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

  • Separate ANN-DMs were trained for each physician's distinct treatment approach to account for variations in planning parameters.

    • Main Results:

    • Training separate ANN-DMs for each physician significantly improved model accuracy, reducing mean absolute dose error from over 30% to under 5%.
    • Mean absolute dose errors remained below 10% across all distances from the planning target volume (PTV).
    • Model performance showed good accuracy above 25 Gy but larger errors at lower doses.

    Conclusions:

    • ANN-DMs demonstrate excellent agreement with TPS-generated dose distributions for pancreatic cancer SBRT.
    • Personalizing ANN-DMs to individual physician treatment styles substantially enhances predictive accuracy.
    • This approach enables the feasible development of ANN-DMs capable of predicting physician-specific desired dose distributions.