Automatic Bone Surface Restoration for Markerless Computer-Assisted Orthopaedic Surgery

Abstract An automatic markerless knee tracking and registration algorithm has been proposed in the literature to avoid marker insertion required by conventional computer-assisted surgery, resulting a shorter less invasive surgical workflow. However, such an considers intact femur geometry only. The bone surface modification is inevitable due intra-operative intervention. mismatched correspondences will degrade reliability of registered target pose. To solve this problem, work supervised deep neural network automatically restore processed bone. was trained on synthetic dataset that consists real depth captures model leg simulated realistic cutting. According evaluation both data real-time captures, quality can be effectively improved reconstruction. improvement accuracy only evident over test data, indicating need for future enhancement network.