Related Experiment Video
Updated: Jul 19, 2025
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
1.5K
Dung Beetle Optimization with Deep Feature Fusion Model for Lung Cancer Detection and Classification
Mohammad Alamgeer1, Nuha Alruwais2, Haya Mesfer Alshahrani3
1Department of Information Systems, College of Science & Art at Mahayil, King Khalid University, Abha 61421, Saudi Arabia.
Cancers
|August 12, 2023
Summary
This study introduces a new deep learning model for lung cancer detection and classification. The model uses feature fusion and optimization to improve accuracy in diagnosing lung cancer from medical images.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Lung cancer is a leading cause of cancer mortality worldwide, often due to late diagnosis and poor prediction.
- Deep learning (DL) offers advanced capabilities for medical image interpretation and disease analysis, crucial for early lung tumor detection and treatment monitoring.
- Various medical imaging modalities, including CT, CXR, MRI, and PET, are utilized for lung cancer detection.
Purpose of the Study:
- To present a novel dung beetle optimization modified deep feature fusion model for lung cancer detection and classification (DBOMDFF-LCC).
- To enhance the accuracy and efficiency of lung cancer diagnosis through advanced feature fusion and hyperparameter optimization techniques.
Main Methods:
- The DBOMDFF-LCC technique employs a feature fusion process integrating three deep learning models: Residual Network (ResNet), Densely Connected Network (DenseNet), and Inception-ResNet-v2.
- The Dung Beetle Optimization (DBO) algorithm is utilized for optimal hyperparameter selection of the integrated DL models.
- A Long Short-Term Memory (LSTM) approach is incorporated for the final lung cancer detection and classification.
Main Results:
- The DBOMDFF-LCC technique demonstrated improved performance in lung cancer classification based on simulation results from a medical dataset.
- Evaluation metrics confirmed the effectiveness of the proposed model in accurately detecting and classifying lung cancer.
- Comparative analysis highlighted the superiority of the DBOMDFF-LCC technique over existing methods.
Conclusions:
- The DBOMDFF-LCC technique offers a promising advancement in lung cancer detection and classification.
- The integration of deep feature fusion and DBO-based hyperparameter tuning significantly enhances diagnostic accuracy.
- This approach holds potential for improving patient outcomes through earlier and more precise lung cancer diagnosis.
