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 15, 2026

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
07:57

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

Datamining approaches for modeling tumor control probability.

Issam El Naqa1, Joseph O Deasy, Yi Mu

  • 1Department of Radiation Oncology, Washington University School of Medicine, Saint Louis, MO 63110, USA. elnaqa@wustl.edu

Acta Oncologica (Stockholm, Sweden)
|March 3, 2010
PubMed
Summary
This summary is machine-generated.

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

Genetically proxied inhibition of cholesterol-lowering drug targets and survival in HPV-positive and non-HPV driven head and neck cancer: a multicentre MR study.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2026
Same author

Artificial intelligence for optimization of immunotherapy: current applications and transformative potential.

Frontiers in immunology·2026
Same author

AI-MIRACLE: Artificial Intelligence and MultIpaRAmetric MRI Predict CLinical OutcomEs to Neoadjuvant Immunotherapy in Patients with Muscle-invasive Bladder Cancer Undergoing Radical Cystectomy.

European urology oncology·2026
Same author

Simultaneous concurrent chemoradiation and SBRT in stage III NSCLC: Safety report of the phase I hybrid trial.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2026
Same author

Resource sharing and open-source software in radiation oncology: From challenges to opportunities for community-wide benefit.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2026
Same author

Imaging Biomarkers in Radiotherapy.

Cancers·2026
Same journal

Overall survival following palliative immune checkpoint inhibitor treatment according to ECOG performance status: a large registry-based study.

Acta oncologica (Stockholm, Sweden)·2026
Same journal

Pathological characteristics and prognosis of very young patients with early breast cancer: a comparative analysis with older patients.

Acta oncologica (Stockholm, Sweden)·2026
Same journal

Recent survival trends in the most fatal cancers in the Nordic countries: gains in some but not in all.

Acta oncologica (Stockholm, Sweden)·2026
Same journal

First-in-human quantitative [¹⁵O]H₂O PET imaging of tumour blood flow at rest and during exercise in lymphoma patients.

Acta oncologica (Stockholm, Sweden)·2026
Same journal

Starshot field configuration in the linac isocentre size determination: a comparison of film and electronic portal imaging device measurements.

Acta oncologica (Stockholm, Sweden)·2026
Same journal

Perspectives on artificial intelligence-generated chronic disease risk predictions in early breast cancer: an international survey among radiation oncologists.

Acta oncologica (Stockholm, Sweden)·2026
See all related articles

Datamining frameworks can predict radiotherapy tumor control probability (TCP) by uncovering complex variable interactions. Machine learning, specifically support vector machines, shows superior performance in predicting TCP for non-small cell lung cancer (NSCLC) patients.

Area of Science:

  • Radiation oncology
  • Medical physics
  • Computational biology

Background:

  • Tumor control probability (TCP) in radiotherapy is influenced by complex interactions among tumor biology, microenvironment, dosimetry, and patient factors.
  • Predictive modeling for clinical use is challenging due to the heterogeneity of these interacting variables.
  • A datamining framework is proposed to analyze higher-order relationships in dosimetric variables and radiobiological processes.

Purpose of the Study:

  • To develop and evaluate a datamining framework for predicting tumor control probability (TCP) in radiotherapy.
  • To identify key dosimetric prognostic variables for TCP prediction.
  • To compare the performance of various modeling techniques, including machine learning, for TCP prediction.

Main Methods:

More Related Videos

Non-Destructive Evaluation of Regional Cell Density Within Tumor Aggregates Following Drug Treatment
10:13

Non-Destructive Evaluation of Regional Cell Density Within Tumor Aggregates Following Drug Treatment

Published on: June 21, 2022

Related Experiment Videos

Last Updated: Jun 15, 2026

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
07:57

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

Non-Destructive Evaluation of Regional Cell Density Within Tumor Aggregates Following Drug Treatment
10:13

Non-Destructive Evaluation of Regional Cell Density Within Tumor Aggregates Following Drug Treatment

Published on: June 21, 2022

  • Exploration of datamining approaches including dose-volume metrics, equivalent uniform dose, and mechanistic Poisson models.
  • Application of statistical regression and machine learning techniques for model building.
  • Utilized institutional datasets of non-small cell lung cancer (NSCLC) patients, with performance evaluated using Spearman rank correlations (rs) and resampling methods to control over-fitting.

Main Results:

  • GTV volume and V75 were identified as the optimal parameters for predicting TCP in NSCLC patients using statistical resampling and a logistic model.
  • Support vector machine (SVM) kernel method demonstrated superior TCP prediction performance (rs=0.68) compared to logistic regression (rs=0.4), Poisson-based TCP (rs=0.33), and equivalent uniform dose models (rs=0.17).
  • The study analyzed 56 NSCLC patients and 23 candidate variables.

Conclusions:

  • Datamining approaches can enhance the prediction of radiotherapy treatment response by revealing complex, non-linear interactions among variables.
  • These models demonstrate the capacity for accurate prediction on unseen data, supporting prospective clinical applications.
  • Machine learning techniques, particularly SVM, offer a promising avenue for improving TCP prediction accuracy in clinical practice.