Continuum manipulators (CM) have the potential to advance minimally-invasively orthopedic surgical procedures due to their high dexterity and enhanced accessibility. CMs can be very useful in surgical treatment of bone defects, such as core decompression, which is the treatment of osteonecrosis in the femoral head. However, it remains a challenging task to control and steer the CM inside the patient body. An effective navigation system is essential to assist robotic interventions including CMs.
Fluoroscopic imaging is widely used in orthopedic procedures due to its fast, low-cost and accurate supply of intra-operative deep-seated structures. We present a fluoroscopic navigation solution for a surgical robotic system including a CM. CM shape and pose estimation with respect to the bone anatomy was achieved using intensity-based 2D/3D registration. We proposed a learning-based method which performed concurrent CM detection and localization in the X-ray images for CM pose initialization. We presented a modified hand-eye calibration method that numerically optimizes the hand-eye matrix during registration. Our navigation system was evaluated through intensive simulation and cadaveric specimen studies. In simulation, the proposed registration achieved a mean error of 1.10±0.72 mm between the CM tip and a target entry point on the femur. In cadaveric experiments, the mean CM tip position error was 2.86±0.80 mm after registration and repositioning of the CM. The results showed the feasibility to apply the proposed navigation system for CM navigation in robot assisted orthopedic applications.