A Next-Generation Computing Approach for Early and Accurate Lung Cancer Detection Using an Integrated Hybrid Deep Learning Framework

Lung cancer remains one of the most significant contributors to cancer-related mortality globally, highlighting the critical importance of early and precise diagnosis. This study proposes a hybrid machine learning framework that combines Convolutional Neural Networks (CNN), Generative Adversarial Networks (GAN), and Support Vector Machines (SVM) to improve the detection of lung cancer from medical imaging data. CNNs are utilized for effective feature extraction, capitalizing on their strength in image processing. GANs are introduced to generate realistic synthetic images, thereby addressing data scarcity and enhancing model training. SVMs serve as the final classification layer, known for their high accuracy in binary decision tasks. The proposed model outperforms conventional techniques by achieving superior sensitivity and specificity. These results demonstrate the promise of integrated deep learning strategies in advancing automated medical diagnostics and pave the way for future developments in lung cancer detection systems.