Paper Title
Lung Cancer Analysis using Deep Learning

Abstract
Lung cancer remains a primary cause of cancer-related mortality worldwide, largely due to latestage diagnosis and the inherent complexity of manual chest X-ray interpretation. This research presents a comparative analysis of several deep learning models designed to automate the detection and classification of lung cancer into Normal, Benign, and Malignant categories. The study evaluates the performance of AlexNet, VGG16, Inception-ResNet-V2, DenseNet, and U-Net within a unified and reproducible experimental framework. To ensure a fair comparison, all models are trained using standardized dataset splits, identical preprocessing techniques, and consistent data augmentation strategies. By leveraging these advanced convolutional neural networks, the project aims to improve diagnostic efficiency and reduce human error, directly supporting faster, more reliable pulmonary diagnostics. Keywords - Convolutional Neural Networks (CNN) Visual Geometry Group (VGG) Residual Network (ResNet) Densely Connected Network (DenseNet) Chest X-Rays (CXR) Computed Tomography (CT)