Lung cancer has experienced a significant increase in prevalence, leading to late diagnoses and putting pressure on health systems. This pathology affects the respiratory system through symptoms such as persistent cough, shortness of breath, chest pain, and other associated signs. The delay in diagnosis often results in advanced-stage detection, significantly reducing treatment options and survival rates. This research uses Artificial Intelligence algorithms to classify lung cancer through histopathological images, aiming to improve early detection. By leveraging advanced machine learning techniques, we seek to provide a more accurate and timely diagnosis. The public dataset “Lung and Colon Cancer Histopathological Images” was utilized for this research. Four convolutional neural network models were developed to classify lung cancer images into the three categories presented in the data: benign lung cancer, lung adenocarcinoma, and squamous cell lung cancer. In addition, an interface was designed for better result visualization, interpretation, and automation, allowing quicker decision-making by medical professionals. This AI-driven decision support system aims to reduce the disease detection stage, thereby increasing survival chances and enhancing the user experience for medical specialists and contributing to a more effective and efficient healthcare system, ultimately improving patient outcomes.