"In vivo" pose estimation of artificial knee implants using computer vision

This paper describes an algorithm to estimate the position and orientation (pose) of artificial knee implants from fluoroscopy images using computer vision. The resulting information is used to determine contact position from " in vivo" bone motion in implanted knees. This determination can be used to support the development of improved prosthetic knee implants. Current generation implants have a limited life span due to premature wear of the polyethylene material at the joint surface. To get "in vivo" motion, fluoroscopy videos were taken of implant patients performing deep knee bends. Our algorithm determines the full 6 degree of freedom translation and rotation of knee components. This is necessary for artificial knees which have shown significant rotation out of the sagittal plane, in particular internal/external rotations. By creating a library of images at known orientation and performing a matching technique, the 3-D pose of the femoral and tibial components are determined. By transforming the coordinate systems into one common system contact positions can be determined. The entire process, when used at certain knee angles, will give a representation of the positions in contact during normal knee motion.