Cancer is the leading cause of death in the world, with lung cancer having the greatest mortality rates since 1985. Recognizing with higher accuracy and predicting the type of Lung Cancer at the earliest possible stage will help patients have a better chance of surviving. This paper compares various automated algorithmic method for detecting lung cancer at an early stage using computed tomography (CT) images. CT Scan is the most effective imaging approach as compared to other diagnostic techniques because it may reveal every suspected and unsuspected lung cancer nodule and provides an exhaustive image of the tumour in the body. Lung cancer datasets such as LIDC Dataset, ELCAP Public Lung Image Dataset, LUNA-16 Challenge Kaggle Dataset, AAPM Dataset, etc. The process of detection followed as per our research follows Image Pre-Processing, Image Segmentation, Feature Extraction, and Neural System identification. This paper majorly focuses on a comparative analysis of various approaches for detecting lung cancer and analysing the recent best technique. Resnet-50 transfer learning model when used for lung cancer detection might increase the accuracy of lung cancer detection as it has given impressive accuracy when used with covid-19 detection, breast cancer detection and several other similar systems. It might also help in the prediction of the cancer at an early stage making it easier for patients to diagnose and treat the lung cancer disease.