Early and accurate diagnosis, however, is still lacking for the most common form of lung cancer, and this remains one of the leading cancers leading to mortality. CT scans are widely used for lung cancer screening; however, their manual interpretation is time-consuming and prone to variability. This study introduces LungDxNet, a deep learning-based framework that integrates transfer learning to enhance diagnostic accuracy and efficiency. Using a large dataset of Low Dose CT (LDCT) scans, the system is built with fine-tuned pre-trained Convolutional Neural Networks (CNNs) such that feature extraction is reliable though minimal reducing radiation exposure. Consequently, LungDxNet involves the integration of component segmentation techniques that have been used to isolate the lung regions and discriminate the cancerous nodules from the malignant and benign cases. Very rigorous evaluations were performed on the model against both conventional machine learning and state of the art deep learning architectures. Results show that there is a substantial reduction of false positive and false negative resulting in a superior accuracy (98.88), sensitivity, and specificity. This design is to be scaled, robust and clinically applicable, making it a potential real world lung cancer diagnosis tool. Deep learning and transfer learning has excellent power to transform lung cancer detection, and this research brings awareness of how far we can optimise and integrate into clinical workflow. The model is enhanced for future work and adapted for real time diagnostic applications.