Lung cancer spreads quickly and is often detected at an advanced stage, making it one of the leading causes of cancer-related deaths globally. The nodules are often small and difficult to see, making early detection very difficult. In this work, we propose a Deep Learning (DL) method for the early diagnosis and categorization of lung cancer that uses Convolutional Neural Networks (CNNs), Transfer Learning (TL), and VGG16. Using a lung cancer imaging dataset, DL models are utilized to categorize several tumor kinds, identify malignant areas, and estimate tumor attributes including size, shape, and location. Specifically, our approach leverages pre-trained models such as VGG16 as part of the TL technique to enhance feature extraction and classification performance. In order to enhance performance, the Python-based model integrates CNNs for image classification with Recurrent Neural Networks (RNN) and Feedforward Neural Networks (FNN). The proposed method provides a more accurate diagnosis and generates tumor features that allow for more intelligent clinical decision-making. This study also highlights how important it is to create rules for the ethical use of Artificial Intelligence (AI) in healthcare.