Cancer is known to be one of the most dangerous health problems in the world and among it, lung cancer is known to be the most serious cancer with the smallest survival rate. The lung cancer risk population is also very high as compared to other deadly diseases, for example, cardiovascular diseases. Therefore, early detection of lung cancer is a must for survival. Nowadays, a lot of research has been done using Convolutional Neural Networks in the medical field. Image classification is one of the methods to detect cancer at early stages. First, the datasets for CT Scans are accessed from Kaggle. Images are refined with the pre-processing method. The image dataset will be trained on two different models namely~ Manual CNN and AlexNet. Further, the model producing the highest accuracy will be chosen and the processed images will be used to predict whether the CT scan image is malignant (cancerous), benign (non-cancerous), or normal.