Abstract
Cancer is a dangerous disease and has been a cause of substantial morbidity and fatality in the world. This chapter provides an exploration of ML and DL techniques used for lung cancer detection between 2019 and 2023. It provides a complete overview of the current methodology, the language used for model implementation, and the results of these models along with the advantages and disadvantages of the studies. It also provides information on the many datasets used to diagnose lung cancer and highlights the unresolved research gaps in the field which can inspire additional research. Furthermore, the chapter outlines futuristic directions, envisioning the integration of emerging technologies such as federated learning, explainable AI, and multimodal data fusion to address existing limitations and enhance the efficacy of lung cancer detection systems. By synthesizing current research findings and identifying key areas for advancement, this chapter serves as a valuable resource for researchers, clinicians, and stakeholders invested in leveraging ML and DL for combating lung cancer.