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

Multinomial Classification Certainty: a new uncertainty metric for multinomial outcome prediction.

Progress in artificial intelligence·2026
Same author

A preoperative Artificial Intelligence model to estimate cancer-specific mortality in nonmetastatic kidney cancer patients.

Nature communications·2026
Same author

The Effect of Mobile Health Intervention on Prelacteal Feeding Among Mothers in the First Month After Birth in South Ethiopia: A Cluster-Randomized Controlled Trial.

Nutrients·2026
Same author

Uncovering Topics in Dutch Patient Messages in Inflammatory Bowel Disease: A Comparative Study of Embedding Models for Neural Topic Modeling.

Studies in health technology and informatics·2026
Same author

LinkedDicom: Indexing DICOM Metadata Using Semantic Web Technologies.

Studies in health technology and informatics·2026
Same author

Correction: Cross-dataset adaptation of voxel-level deep radiomics for predicting survival in inoperable locally advanced NSCLC treated with immunotherapy.

Frontiers in immunology·2026

Related Experiment Video

Updated: Dec 27, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.3K

Machine learning helps identifying volume-confounding effects in radiomics.

Alberto Traverso1, Michal Kazmierski2, Ivan Zhovannik3

  • 1Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, The Netherlands; Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Canada.

Physica Medica : PM : an International Journal Devoted to the Applications of Physics to Medicine and Biology : Official Journal of the Italian Association of Biomedical Physics (AIFB)
|February 24, 2020
PubMed
Summary
This summary is machine-generated.

Radiomics models risk bias from tumor volume. Machine learning methods identified volume-confounding effects, showing clinical predictors outperform radiomics for patient risk stratification.

Keywords:
Head and neckLungMachine learningPredictionsRadiomics

More Related Videos

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

8.6K
Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics
10:17

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Published on: January 8, 2018

13.6K

Related Experiment Videos

Last Updated: Dec 27, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.3K
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

8.6K
Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics
10:17

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Published on: January 8, 2018

13.6K

Area of Science:

  • Radiomics
  • Medical Imaging Analysis
  • Machine Learning in Oncology

Background:

  • Radiomics models are increasingly used for clinical decision support.
  • Potential biases, such as volume-confounding effects, can impact model reliability.
  • Improving radiomics quality is crucial for clinical adoption.

Purpose of the Study:

  • To identify volume-confounding effects in radiomics features using machine learning.
  • To assess the prognostic power and robustness of radiomics features.
  • To propose methods for developing robust radiomics signatures.

Main Methods:

  • Extracted 841 radiomics features from public lung and head/neck cancer datasets.
  • Employed unsupervised hierarchical clustering and principal component analysis (PCA).
  • Utilized bootstrapping and logistic regression to validate feature prognostic power.

Main Results:

  • Over 80% of radiomics features showed high pairwise correlations.
  • Nearly 30% of features were strongly correlated with tumor volume.
  • Volume-independent features failed to stratify patient risk; clinical predictors were superior.

Conclusions:

  • Safeguards are essential to enhance radiomics study quality.
  • Machine learning-based methods can aid in developing robust radiomics signatures.
  • Addressing volume-confounding effects is critical for reliable radiomics models.