Lung cancer is one of the world's major causes of death. Lung cancer detection and diagnosis are critical for optimal therapy and patient survival. Deep learning methods for the automatic diagnosis and categorization of lung cancer based on medical pictures have gained popularity in recent years. The purpose of this research is to compare the performance of various algorithms for lung cancer classification using chest CT scan pictures. The collection includes CT scan images of four cancer types: adenocarcinoma, large cell carcinoma, squamous cell carcinoma, and normal. Convolutional neural network (CNN), ResNet50, VGG16, and Inception-v3 are among the algorithms employed in this project. The accuracy of each model in categorizing photos into their appropriate classes is used to evaluate its performance, with ResNet50 having the highest accuracy of 84.76%. The findings of this study could shed light on the efficacy of various deep learning algorithms for lung cancer classification and contribute to the creation of more accurate and efficient lung cancer diagnosis tools.