Lung cancer remains one of the leading causes of cancer-related mortality worldwide, largely due to late-stage detection and diagnostic challenges associated with medical imaging. This study focuses on the Transit Search-Based Convolutional Neural Network (TS-CNN) for lung cancer identification using computed tomography (CT) scan images. The proposed model integrates convolutional neural networks with a transit search optimisation mechanism to enhance feature extraction, automate hyperparameter tuning, and improve classification performance. The system is designed within a Computer-Aided Diagnosis (CAD) framework, incorporating preprocessing, segmentation, feature learning, and classification stages. Experimental evaluation demonstrates that the improved TS-CNN model achieves higher accuracy, sensitivity, and specificity compared to conventional CNN models by reducing false positives and enhancing generalisation. The findings suggest that the integration of search-based optimisation techniques into deep learning architectures significantly improves the reliability and efficiency of lung cancer detection systems. This study contributes to the advancement of intelligent diagnostic tools and provides a foundation in optimised deep learning models for medical imaging.

Keywords: Transit search-based, convolutional neural network, lung cancer identification.