In recent years, lung cancer has become more common. The lung is one of the most important organs in the human body. The right and left lungs are separated into two regions, and their function is to exchange gas, which is referred to as breathing or respiration. The condition of human lungs is gradually worsening as a result of today's modern lifestyle paired with environmental toxins. Diagnosing the various kinds of lung cancer is time-consuming and error-prone the majority of the time. Patients' treatment options and chances of survival can be improved by using Convolutional Neural Networks to identify and categorise lung cancer kinds more quickly and accurately. In this study, researchers looked at adenocarcinoma, squamous cell carcinoma, and other types of cancerous tissue. A Convolutional Neural Network is used to categorise lung tumours as malignant or benign (CNN). CNN achieves a 96 percent accuracy, which is more efficient than typical neural network systems. DCNNs (Deep Convolutional Neural Networks) have gained popularity as a technique of revolutionising computer vision research. In this paper, we employ a Deep Convolutional Neural Network to detect malignant and noncancerous lung nodules and analyse classification accuracy using CT scans from the lung cancer image dataset consortium (LIDC). It allows us to make accurate predictions by reducing the image to a form that is easier to analyse without compromising any information. By comparing data sets and input photos, we can identify whether a lung is cancerous or not. The suggested CNN model will be appropriate for the early identification and classification of CT scan images including nodules with an accuracy of 93.52 percent using domain knowledge of CT scan images of the lung in the field of medicine and Neural Network.

.