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 27, 2026

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

Feature Selection and Machine Learning Strategies for CT Radiomics-Based Survival Prediction in Non-Small Cell Lung

Mohan Huang1, Ashley Hui1, Ching Wai Leung1

  • 1School of Medical and Health Sciences, Tung Wah College, Homantin, Hong Kong SAR, China.

Diagnostics (Basel, Switzerland)
|June 26, 2026
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

TOPS-CRISPR: Thermally-regulated and oligonucleotide-mediated one-pot CRISPR-Cas12a assay for ultra-sensitive and rapid on-site diagnostics.

Biosensors & bioelectronics·2026
Same author

Clinical efficacy of immunotherapy in combination of locoregional therapies for advanced hepatocellular carcinoma: a systematic review and meta-analysis.

Frontiers in immunology·2026
Same author

Keratinases: microbial sources, mechanisms, and industrial applications in waste valorization.

Frontiers in microbiology·2026
Same author

Machine Learning-Based Prognosis Prediction in Glioblastoma Multiforme Patients by Integrating Clinical Data with Multimodal Radiomics.

Diagnostics (Basel, Switzerland)·2026
Same author

Integrating static angle ports and dynamic collimator rotation in volumetric modulated arc therapy for hypofractionated whole breast irradiation in Chinese females: a single-centre dosimetric study.

Radiation oncology (London, England)·2026
Same author

Radiomics-Driven Tumor Prognosis Prediction Across Imaging Modalities: Advances in Sampling, Feature Selection, and Multi-Omics Integration.

Cancers·2025

Logistic regression offers stable performance for computed tomography (CT) radiomics in non-small cell lung cancer (NSCLC) prognosis. Least absolute shrinkage and selection operator (LASSO) excels in survival risk stratification for NSCLC patients.

Area of Science:

  • Radiomics
  • Medical Imaging
  • Oncology

Background:

  • Computed tomography (CT)-based radiomics shows potential for predicting non-small cell lung cancer (NSCLC) prognosis.
  • Model performance in CT radiomics for NSCLC varies significantly based on feature selection and machine learning (ML) strategies.
  • Optimal combinations of feature selection and ML algorithms for NSCLC prognosis remain unclear.

Purpose of the Study:

  • To systematically compare different feature selection methods and ML algorithms for predicting 12-month overall survival in NSCLC patients using CT radiomics.
  • To identify the most effective strategies for CT radiomics-based prognostic modeling in NSCLC.

Main Methods:

  • Analysis of 385 NSCLC patients from The Cancer Imaging Archive (TCIA) dataset.
  • Combination of radiomic features from primary tumors with clinical variables.
Keywords:
computed tomographyfeature selectionmachine learningnon-small cell lung cancerprognosisradiomicssurvival prediction

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

Related Experiment Videos

Last Updated: Jun 27, 2026

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

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

  • Comparison of three feature selection methods (SFS, mRMR, LASSO) with five classifiers (KNN, SVM, RF, LR, GBC).
  • Performance evaluation using AUC and accuracy; survival risk stratification via Cox regression and Kaplan-Meier analyses.

    • Main Results:

    • Logistic regression (LR) demonstrated stable classification performance across feature selection methods (test AUC 0.60-0.65, accuracy 0.72-0.73).
    • The mRMR-LR model achieved the highest AUC (0.65), while LASSO-LR yielded the highest accuracy (0.73).
    • LASSO-based Cox modeling provided superior survival risk stratification, showing significant separation between high- and low-risk groups (p = 0.0095).

    Conclusions:

    • Simpler models like logistic regression offer robust performance in CT radiomics for NSCLC.
    • Least absolute shrinkage and selection operator (LASSO) is effective for survival risk stratification in NSCLC.
    • Findings provide methodological insights but clinical applicability is limited due to single-dataset validation.