3D-2D Registration using X-ray Simulation and CMA-ES

Radiographs of the hand are useful in diagnosing and staging diseases such as rheumatoid arthritis (RA) and other musculoskeletal diseases. Radiographs are projections of the 3D anatomy, with the useful information such as pose and pathology becoming lost in the process. We propose a 3D hand pose recovery method for radiographs of hands using a novel hybrid image registration method. Our pose recovery pipeline consists of aligning a simulated X-ray (digitally reconstructed radiograph) of an articulated phantom mesh model to a real hand radiograph using Covariance Matrix Adaptation Evolution Strategy. Early results demonstrate that our approach works well. Further inquiry is required to evaluate the applicability of our registration approach to other articulated musculoskeletal anatomy.