Safety cases provide clear, comprehensive, and reliable arguments which mean that a system’s operation under a specific environment meets acceptable safety levels. In safety-critical sectors subject to regulations such as automotive, aviation, and nuclear industries, certification authorities often require the system to undergo a rigorous safety assessment process and thus demonstrate that the system complies with one or more safety standards. The safety case utilization in system development is an emerging technical means to express the safety attributes of safety-critical systems in a structured and comprehensive way. This study briefly introduces the four basic steps of building a safety case, including determining the goal, gathering evidence, constructing arguments, and evaluating the case, and then focuses on the key step of constructing arguments. Meanwhile, eight existing forms of safety case expressions are introduced in detail, containing goal structuring notation (GSN), claim-argument-evidence (CAE), and structured assurance case metamodel (SACM), with their strengths and weaknesses analyzed. Given the significant complexity of the materials required for safety cases, software tools are often adopted as practical methods for constructing and evaluating safety cases. Additionally, seven tools for developing and evaluating safety cases are compared, including astah system safety, gsn2x, NOR-STA, Socrates, ASCE, D-Case Editor, and AdvoCATE. Furthermore, this study delves into multiple challenges in building safety cases. These challenges include data reliability and integrity, complexity and uncertainty management, inconsistencies in regulations and standards, human factor engineering, rapid technological advancements, and challenges in team and interdisciplinary collaboration. Finally, a prospect is provided for the future development of safety cases to reveal their potential utilization and relevant research problems.