简介: |
Abstract: The applications of two-dimensional (2D) X-ray imaging in orthopedics are pervasive, both pre-operatively and intra-operatively. However, due to the projective characteristics of 2D X-ray imaging, the accuracy of an X-ray image based application is restricted. One way to address this limitation is to learn a statistical model and to adapt the learned model to the patient’s individual anatomy based on a limited number of calibrated X-ray images. The reconstructed model can then provide detailed 3D information for the considered anatomical structure. In this talk, I will present various solutions that have been developed in my team for reconstructing 3D personalized shape and intensity from 2D X-ray images. I will start with a solution that can reconstruct the shape of an anatomical structure with none or mild degree of pathology even when a statistical model learned from a normal population is used. Challenges and adaptations of applying this method to various pre-operative and intra-operative scenarios will be discussed. Our more recent work focuses on reconstructing not only the shape but also the internal intensity distribution. Applications of our solutions are pre-operative planning, intra-operative surgical interventions, and post-operative treatment evaluation. |
