A Computational Framework for Automatic Determination of Morphological Parameters of Proximal Femur from Intraoperative Fluoroscopic Images

Determination of morphological parameters of proximal femur using different image modalities is discussed. In this paper, a computational framework based on particle filter is proposed for automatic determination of morphological parameters of proximal femur from intraoperative fluoroscopic images. In this framework, the proximal femur is decomposed into three constrained components: (1) femoral head, (2) femoral neck, and (3) femoral shaft. Each component is represented by a set of parameters describing its three-dimensional (3D) spatial position and 3D geometrical shape. Particle filter based inference is then used to estimate those parameters from the acquired fluoroscopic images. The constraints between different components are modeled by a single directional rational network to improve the efficiency and robustness of the proposed approach. We report the initial quantitative and qualitative evaluation results on a plastic femur, which indicate the validity of our approach