Lung cancer continues to be a leading cause of global mortality, with escalating death rates since 1985. Early and precise detection is imperative for enhancing patient survival prospects. This study undertakes a comprehensive examination of automated algorithms for identifying respiratory tumors in their initial stages using CT imagery. CT scans are favored for their efficacy in detecting lung cancer nodules. The investigation assesses diverse methodologies, leveraging datasets such as LIDC, ELCAP, LUNA-16, and AAPM. Segmentation, Feature Extraction, Neural Network Identification, and Image Pre-Processing constitute integral stages in the detection process. By prioritizing ResNet-50 transfer learning models, which have exhibited notable accuracy in detecting COVID-19 and breast cancer, there exists potential to enhance precision and facilitate early-stage cancer prognosis. This review article has the potential to transform lung cancer diagnosis and treatment, potentially providing patients with an easier and more effective path to recovery.