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: Jan 13, 2026

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

2.0K

Enriched lung cancer classification approach using an optimized hybrid deep learning approach.

M Naveenraj1, P Vijayakumar2

  • 1Department of Computer Science and Engineering (IOT and CS with BCT), SNS College of Engineering, Coimbatore, Tamilnadu, India. naveenrajm055@gmail.com.

Scientific Reports
|October 29, 2025
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

Morphometric evaluation and structural indices of Thuvarai cattle: insights into autochthonous draft cattle of southern India.

Tropical animal health and production·2026
Same author

Development of sensor system and data analytic framework for non-invasive blood glucose prediction.

Scientific reports·2024
Same author

Salvaging skin loss of free fibular osteo-cutaneous flaps in oral oncological reconstruction.

Oral oncology·2019
Same author

Characterization of a Novel POU1F1 Mutation Identified on Screening 160 Growth Hormone Deficiency Patients.

Hormone and metabolic research = Hormon- und Stoffwechselforschung = Hormones et metabolisme·2019
Same author

Spectroscopic investigation and computational studies on the interaction of Acriflavine with various estrogens.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2018
Same author

Genome-wide gene expression pattern underlying differential host response to high or low pathogenic H5N1 avian influenza virus in ducks.

Acta virologica·2017

This study introduces a deep learning framework for early lung cancer detection using CT scans. The model achieved 98.75% accuracy in classifying lung tissue, offering a promising non-invasive diagnostic aid.

Area of Science:

  • Medical Imaging and Diagnostics
  • Artificial Intelligence in Healthcare
  • Computational Biology

Background:

  • Lung cancer is a leading cause of death globally, necessitating early detection for improved survival rates.
  • Traditional diagnostic methods like CT scans and X-rays can be ambiguous due to visual similarities between benign and malignant nodules, requiring expert interpretation.
  • There is a critical need for automated frameworks to aid in accurate and early lung cancer classification.

Purpose of the Study:

  • To develop and validate an automated lung cancer classification framework utilizing deep learning (DL) methods.
  • To enhance the accuracy and efficiency of lung cancer diagnosis through advanced image processing and machine learning techniques.
  • To provide a non-invasive decision support tool for radiologists, facilitating earlier cancer detection.
Keywords:
ClassificationDeep learningHorse herd optimizationHybrid optimizationLion optimization algorithmLung CancerPre-ProcessingSegmentation

Related Experiment Videos

Last Updated: Jan 13, 2026

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

2.0K

Main Methods:

  • Image pre-processing using adaptive filters to reduce noise.
  • Lesion segmentation and feature refinement employing Hybrid Horse Herd Optimization (HHO) and Lion Optimization Algorithm (LOA).
  • Classification using a hybrid Deep Convolutional Neural Network and Long Short-Term Memory (DCNN+LSTM) model for enhanced feature extraction and temporal learning.

Main Results:

  • The proposed DL framework achieved a high accuracy of 98.75% on standard lung CT datasets.
  • The system effectively differentiates between normal and abnormal lung tissue.
  • The optimized feature extraction and classification model demonstrated significant performance in lung nodule analysis.

Conclusions:

  • The developed DL framework shows high efficacy in classifying lung cancer from CT images, offering a potential advancement in diagnostic accuracy.
  • While computational demands and CT performance present real-time usability limitations, the system serves as an intelligent, non-invasive aid for radiologists.
  • The framework supports earlier lung cancer diagnosis and assists in clinical decision-making, potentially improving patient outcomes.