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: May 20, 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

Radiomic Feature Selection Using Gradient Loss of Deep Neural Network for Lung Cancer Stage Detection.

Hina Shakir1, Mohammad Mohatram2, Javeed Hussain3

  • 1Department of Software Engineering, Bahria University.

Journal of Visualized Experiments : Jove
|May 18, 2026
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

Accuracy of non-invasive electrocardiographic imaging in scar-dependent ventricular tachycardia: relationship to arrhythmogenic substrate and imaging defined scar.

Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology·2026
Same author

The Anthro-Thumb: a biomimetic hybrid soft robotic carpometacarpal saddle joint for the thumb.

Frontiers in robotics and AI·2025
Same author

Photocatalytic Degradation of Brilliant Blue Dye Under Solar Light Irradiation: An Insight Into Mechanistic, Kinetics, Mineralization and Scavenging Studies.

Journal of fluorescence·2025
Same author

The central role of multimodality cardiac imaging in the assessment and management of cardiac masses.

European heart journal. Case reports·2024
Same author

A deep learning-based cancer survival time classifier for small datasets.

Computers in biology and medicine·2023
Same author

Strengthening the Bridge Between Academic and the Industry Through the Academia-Industry Collaboration Plan Design Model.

Frontiers in psychology·2022
Same journal

Reliability of A Vibration-Based Elastography Protocol For Assessing Achilles Tendon Stiffness Across Multiple Joint Angles In Elite Athletes.

Journal of visualized experiments : JoVE·2026
Same journal

Associations of Inflammatory and Coagulation Biomarkers with Kidney Injury Across Chronic and Acute Clinical Settings.

Journal of visualized experiments : JoVE·2026
Same journal

Intelligent Recommender Systems for Chinese Super League Fan Consumption Behavior Prediction.

Journal of visualized experiments : JoVE·2026
Same journal

A Battery of Quantitative Binocular Vision Tests for Adults: Testing Protocols.

Journal of visualized experiments : JoVE·2026
Same journal

Efficacy Analysis of Paiteling in Treating Persistent High-Risk Human Papillomavirus after Cervical Cancer Surgery.

Journal of visualized experiments : JoVE·2026
Same journal

Clinical Efficacy of Tissue-Bone Homeostasis Manipulation on Soft Tissue Balance and Function in Knee Osteoarthritis.

Journal of visualized experiments : JoVE·2026
See all related articles

This study introduces a new method, gradient-loss recursive feature elimination (GL-RFE), for selecting important radiomic features in lung cancer detection. The GL-RFE framework effectively identifies key imaging biomarkers from CT scans, improving diagnostic accuracy.

Area of Science:

  • Radiomics and Medical Imaging Analysis
  • Computational Biology and Bioinformatics
  • Oncology and Cancer Diagnostics

Background:

  • Radiomics, extracting quantitative imaging biomarkers, is vital for computer-aided cancer diagnosis.
  • High-dimensional radiomics data with limited samples necessitate effective feature selection for reliable predictive models.
  • Accurate lung cancer staging is crucial for effective treatment planning and patient outcomes.

Purpose of the Study:

  • To propose and validate a novel Gradient-Loss Recursive Feature Elimination (GL-RFE) framework for identifying influential radiomic features.
  • To enhance the accuracy and reliability of lung cancer stage detection using quantitative imaging biomarkers.
  • To address the challenges of high-dimensionality and small sample sizes in radiomics datasets.

Main Methods:

Related Experiment Videos

Last Updated: May 20, 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

  • Extraction of 106 radiomic features from chest CT scans using PyRadiomics in 3D Slicer.
  • Implementation of GL-RFE integrating deep neural network gradient sensitivity analysis for feature importance evaluation.
  • Recursive elimination of features with minimal contribution based on network loss gradients.
  • Training a deep neural network classifier using the top 15 selected radiomic features for lung cancer staging.

Main Results:

  • The GL-RFE framework achieved high classification performance: 90.22% accuracy, 90.10% precision, 90.24% recall, and 90.16% F1-score.
  • Visualization analyses confirmed reduced feature redundancy and enhanced class separability.
  • The method effectively captured nonlinear feature interactions, outperforming conventional feature selection techniques.

Conclusions:

  • The proposed GL-RFE framework offers a reproducible and interpretable methodology for radiomics-based cancer stage detection.
  • GL-RFE is particularly suitable for high-dimensional, small-sample biomedical datasets, enhancing model generalization.
  • This approach has potential applications beyond lung cancer, including genomics and multimodal clinical analysis.