Lung Cancer Detection by Harnessing the Power of Deep Learning with Convolutional Neural Networks

Cancer is a widespread fatal disease affecting a large portion of the global population. The medical research places significant importance on predicting cancer, aiming to identify individuals at a higher risk of developing the disease. Predictive models, including CNN algorithms, utilize patient data to detect patterns and forecast the likelihood of cancer development. The paper primarily focuses on lung, breast, and skin cancers, with particular emphasis on the crucial role of early detection in effectively treating lung cancer. The American Cancer Society's 2023 study reveals that approximately 238,340 individuals are affected by lung cancer, highlighting the rapidity of its impact. Detecting lung cancer early is critical in assessing the nature of lung cell proportions and their potential harm, as untreated cases can lead to fatal outcomes. The paper's primary objective is to classify lung nodules as either affected or in a normal state, using the CNN algorithm to elucidate malignant development in the lungs. The proposed technique extends CNN's capabilities to suppress identified dangerous or benign tumors in lung disease screening using tomography filters. By leveraging image data as input and direct classification as output, CNN technology plays a pivotal role in classifying various types of cancer cells, such as Adenocancer, large cell cancer, normal chest, and normal squamous cell cancer. This approach enhances classification procedures' reliability while preserving their beneficial aspects.