This study investigates the classification of lung cancer, a major global cause of mortality. The accurate diagnosis and classification of lung cancer through CT-Scan images demand significant expertise, precision, and time to ensure appropriate treatment for patients. Transfer learning has emerged as a beneficial technology to aid in this process by effectively classifying lung cancer-related patterns in CT-Scan images. In this research, a dataset of 1,000 lung CT-Scan images, divided into four categories—Adenocarcinoma, Large Cell, Squamous, and Normal—was employed. The study evaluated several transfer learning models, including ResNet50, ResNet101, EfficientNetB1, EfficientNetB3, EfficientNetB5, and EfficientNetB7. The findings revealed that the EfficientNetB3 model outperformed the others, achieving an accuracy of 97.78%, a precision of 97.34%, a recall of 98.33%, and an F1-Score of 97.78%. These results demonstrate that the EfficientNetB3 model enhances the accuracy of lung cancer classification in CT-Scan images more effectively than other transfer learning models. This research underscores the significant potential of EfficientNetB3 in facilitating early diagnosis, advancing the integration of machine learning in medical practices, and providing critical insights for the selection of transfer learning models in clinical applications. The implications of these findings suggest a substantial impact on improving diagnostic processes and outcomes in lung cancer management.