Additive manufacturing has emerged as a transformative technology for producing biomedical metals and implants, offering the potential to revolutionize patient care and treatment outcomes. This article reviews the recent advances in additive manufacturing (AM) of biomedical metal implants, especially load-bearing biomedical alloys, biodegradable alloys, novel metals, and 4D printing, whose properties are systematically assessed to facilitate material selection for specific medical applications. The applications of the most cutting-edge artificial intelligence in AM and surface functional modification are also presented. This article also explores the application of AM in various medical specialties, such as orthopedics, dentistry, cardiology, and neurosurgery, demonstrating its potential to solve complex clinical challenges and advance patient-centered healthcare solutions. Furthermore, it highlights the critical roles of AM in shaping the future of medical implant manufacturing. The optimistic outlook on the bright future of AM in medical metals delivers personalized, high-performance medical implants that improve patient treatment outcomes and well-being.

Bioprinting is an emerging additive manufacturing technology that has enormous potential in bone implantation and repair. The insufficient accuracy of the shape of bioprinted parts is a primary clinical barrier that prevents widespread utilization of bioprinting, especially for bone design with high-resolution requirements. During the last five years, the use of computer vision for process control has been widely practiced in the manufacturing field. Computer vision can improve the performance of bioprinting for bone research with respect to various aspects, including accuracy, resolution, and cell survival rate. Hence, computer vision plays a substantial role in addressing the current defect problem in bioprinting for bone research. In this review, recent advances in the application of computer vision in bioprinting for bone research are summarized and categorized into three groups based on different defect types: bone scaffold process control, deep learning, and cell viability models. The collection of printing parameters, data processing, and feedback of bioprinting information, which ultimately improves printing capabilities, are further discussed. We envision that computer vision may offer opportunities to accelerate bioprinting development and provide a new perception for bone research.