This research study regarding the applications of Convolutional Neural Networks (CNNs) based on medical imaging data for lung cancer diagnosis is presented here. People are usually diagnosed with lung cancer at advanced stages as the initial symptoms are not noticeable. It is critical to detect the cancer in the early stages because this improves the patients’ outcomes. The CNN is perfect for the mentioned tasks within medical image analysis for its feature learning capabilities - i.e., its ability to learn information automatically from raw data. Lung cancer is a kind of tumor in cases of the lung cells beginning from the lungs’ air passages, including the cells aligning the air passageways. It accounts for a large portion of global cancer-related deaths. In India, Lung cancers leave behind all the other cancer types to become the leading cause of mortality. The research in this study is made up of the positive roles and efficiency of multi-modal imaging in lung cancer detection and its classification process by employing CNN techniques. This research identifies how the positioning of an effective synergy between imaging modalities and updated CNN algorithms can increase diagnostic accuracy, sensitivity, specificity, Area Under the Curve, and the kappa score.