This paper proposes a biomechanical performance design method of joint prosthesis for medical rehabilitation via Generative Structure Optimization (GSO). Firstly, the 3D reconstruction of manifold structure involving hard bone and cartilage is sequentially and progressively implemented from heterogeneous medical images such as Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) via iteration. On the basis of reconstructed mesh structure, the finite element method (FEM) is hereby employed to verify the structure by evaluating the mechanical force distribution. The biomechanical performance design model for 3 D printing (3DP) is then built using multi-objective optimization (MOO) by considering adaptive layer thickness, infill patterns and infill trajectories, etc. The GSO outlets a generative data-driven system which covers various stages such as personalized CT, subsequent 3 D reconstruction, further finite element analysis (FEA) and even structural parameter optimization. The physical experiment of Additive manufacturing (AM) proves that, the relative density, surface topography and wear-resisting performance of joint prosthesis can be improved by GSO which helps to improve biomechanical performance, including kinematics and dynamics. The proposed method may arouse the huge attention in the prosthesis applications to promote patients' high-end customization well-being.
Keywords: 3D reconstruction; Biomechanical performance design; finite element analysis (FEA); generative structure optimization (GSO); joint prosthesis.