Determining Geometrical Parameters by Particle Filter for Automatic Reconstruction of Surface Model of Proximal Femur from Biplanar Calibrated Fluoroscopic Images

We address the problem of automatic reconstruction of patient-specific 3D surface model of proximal femur from biplanar calibrated fluoroscopic images. Previously, we proposed a point distribution model (PDM) based reconstruction algorithm which incorporates an original 2D/3D correspondence building method to convert a 2D/3D surface reconstruction problem to a 3D/3D one. The convergence of this algorithm relies on a proper initialization. In our previous work, interactively reconstructed anatomical landmarks were used for this purpose. In contrast, this paper presents a fully automatic initialization method, which uses a particle filter based inference algorithm to automatically determine the geometrical parameters of a proximal femur from its biplanar fluoroscopic images. The estimated geometrical parameters are then used to initialize the reconstruction algorithm. Here we report the quantitative and qualitative evaluation results on 10 dry cadaveric bones. Compared to the manual initialization, the automated initialization results in a little bit less accurate reconstruction but has the advantage of elimination of user interactions