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

Optimizing Cardiac Inpatient Flow and Resource Allocation in Low-Resource Settings Using Queuing Theory: Insights From a Tertiary Hospital in Bangladesh.

Public health challenges·2026
Same author

Short-term preservation techniques for zebrafish (Danio rerio) sperm.

Animal reproduction science·2026
Same author

Uncertainty-Aware Information Pursuit for Interpretable and Reliable Medical Image Analysis.

IEEE transactions on medical imaging·2026
Same author

Machine learning-based temperature prediction across diverse ecosystems for the Boro Season in Bangladesh.

Scientific reports·2026
Same author

Dual Fano-like resonances in a CMOS-compatible all-dielectric metasurface for refractive index sensing.

Applied optics·2026
Same author

Professionalism and e-Professionalism From Dentists' Perspective: A Multicenter Cross-Sectional Study.

International journal of dentistry·2026

Related Experiment Video

Updated: May 21, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K

Ensemble-based multiclass lung cancer classification using hybrid CNN-SVD feature extraction and selection method.

Md Sabbir Hossain1, Niloy Basak2, Md Aslam Mollah1

  • 1Department of Electronics & Telecommunication Engineering, Rajshahi University of Engineering & Technology, Rajshahi, Bangladesh.

Plos One
|March 19, 2025
PubMed
Summary

This study introduces an advanced artificial intelligence method for early lung cancer detection using CT scans. The hybrid CNN-SVD-Ensemble model achieves high accuracy, improving patient outcomes through precise classification.

More Related Videos

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

6.6K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

616

Related Experiment Videos

Last Updated: May 21, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K
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

6.6K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

616

Area of Science:

  • Medical Imaging and Artificial Intelligence
  • Oncology and Diagnostic Technologies
  • Computer Science and Machine Learning

Background:

  • Lung cancer (LC) is a major global health concern, necessitating improved early detection methods.
  • Current diagnostic approaches require enhancement for precision and efficiency in identifying early-stage lung cancer.
  • Artificial intelligence (AI) offers promising avenues for analyzing complex medical imaging data.

Purpose of the Study:

  • To develop and validate a novel AI-driven method for precise early-stage lung cancer detection and classification from CT scans.
  • To enhance the accuracy and reliability of lung cancer diagnosis through a hybrid deep learning approach.
  • To improve model transparency and clinical applicability using explainable AI (XAI) techniques.

Main Methods:

  • A hybrid Convolutional Neural Network-Singular Value Decomposition (CNN-SVD) model was developed for feature extraction and dimensionality reduction.
  • Contrast-limited adaptive histogram equalization (CLAHE) was used for image enhancement, improving feature visibility.
  • A voting ensemble approach combined with machine learning algorithms and Gradient-weighted Class Activation Mapping (Grad-CAM) for classification and interpretability.

Main Results:

  • The CNN-SVD-Ensemble model achieved exceptional performance, with an overall accuracy of 99.49% and AUC of 99.73%.
  • Binary classification tasks yielded perfect scores across all performance metrics (100%), demonstrating high diagnostic capability.
  • Explainable AI (Grad-CAM) provided transparent insights into the model's decision-making process, highlighting critical regions in CT scans.

Conclusions:

  • The proposed AI-based method significantly advances early lung cancer detection, offering superior accuracy and reliability.
  • The hybrid CNN-SVD-Ensemble approach with XAI integration sets a new benchmark for diagnostic performance in medical imaging.
  • This research provides robust tools for clinical applications, paving the way for future innovations in cancer diagnostics.