Lung cancer remains one of the leading causes of cancer-related deaths worldwide, underscoring the critical need for early and accurate detection methods to address this challenge. This study explores a comprehensive approach to lung cancer diagnosis using the LIDC dataset, integrating advanced image processing and bio-stimulation imaging systems. Initially, the input CT images are denoised using a Gabor filter to enhance image quality. Segmentation is performed using the Spherical Iterative Refinement Clustering (SIRC) technique, which efficiently identifies regions of interest. For feature extraction and classification, sophisticated methods such as the Contiguous Cross Propagation Neural Network (CCPNN) and excitation-based biological feature matching are applied. These techniques enable the identification of crucial patterns and characteristics associated with lung cancer. The performance of the classification model is evaluated using key metrics, including accuracy, precision, recall, and F-measure, to ensure its reliability and effectiveness. This study focuses on optimizing preprocessing, feature extraction, and machine learning techniques to create a robust and efficient framework for lung cancer diagnosis. By combining multiple advanced methodologies, it aims to enhance diagnostic precision and contribute to the development of more accurate and practical diagnostic tools for early lung cancer detection.