Article Details
Review of Lung Cancer Detection Using Integrated Machine Learning, Deep Learning, And Optimization Methods
Publication Date : March 10, 2026
📄Author(s) :
Sowmiya R
Article Name :
Review of Lung Cancer Detection Using Integrated Machine Learning, Deep Learning, And Optimization Methods
Abstract :
Lung cancer has a substantial impact on survival rates and general health outcomes, making it one of the most common and fatal malignancies. Ensuring early and accurate identification is essential for lowering mortality and enhancing treatment outcomes. In the past, the diagnosis of lung cancer has relied on the lengthy and error-prone process of manually reviewing medical images, such as chest X-rays and Computed Tomography (CT) scans. Traditional machine learning techniques have been studied in the past to help diagnose lung cancer, but they are often not scalable and struggle to represent complex features. This study addresses these limitations by providing a comprehensive analysis of lung cancer detection using an integrated approach that incorporates supervised machine learning classifiers, deep learning models, and optimization techniques for hyperparameter tuning and performance enhancement. Through the integration of machine learning's (ML) analytical power, deep learning's (DL) feature extraction efficiency, and optimization techniques' performance enhancement, this coherent framework expands the potential of automated diagnostic systems.The proposed integrated framework showed significant performance improvements with corresponding F1-scores of 0.92, 0.97, and 0.994, with accuracies of 92.74% for WDELM, 96.85% for VGG-16, and 99.5% for PSbBO-Net. These results demonstrate the model's dependability in reducing physician burden and aiding in the early detection of lung cancer.