摘要：For the image-guided surgery, the positioning of mobile C-arms is a key technique to take X-ray images in a desired pose for the confirmation of current surgical outcome. Unfortunately, surgeons and patient often suffer the radiation exposure due to the repeated imaging when the X-ray image is of poor quality or not captured at a good projection view. In this paper, a virtual reality (VR) aided positioning method for the mobile C-arm is proposed by the alignment of 3D surface model of region of interest and preoperative anatomy, so that a reference pose of the mobile C-arm with respect to the inside anatomy can be figured out from outside view. It allows a one-time imaging from the outside view to greatly reduce the additional radiation exposure. To control the mobile C-arm to the desired pose, the mobile C-arm is modeled as a robotic arm with a movable base. Experiments were conducted to evaluate the accuracy of appearance model and precision of mobile C-arm positioning. The appearance model was reconstructed with the average error of 2.16 mm. One-time imaging of mobile C-arm was achieved, and new modeling of mobile C-arm with 8 DoFs enlarges the working space in the operating room.
