Automatic puncture path planning before percutaneous vertebroplasty based on image processing

Abstract Background Percutaneous vertebroplasty (PVP) has become the mainstream method for the treatment of osteoporotic vertebral compression fractures(OVCF). Generally, surgeons manually plan the puncture path by themselves. This is time-consuming and laborious, which increases the working pressure of surgeons. Image processing algorithm is used to automatically segment contour of vertebral body, and plan the puncture path before operation. In order to obtain the contours of vertebral body and skin, binarization and contour extraction algorithm were performed. The connecting algorithm we proposed was used to connect the discontinuous contour of vertebral foramen. We determined the centerline of vertebral body by inscribed circle center of the contours of vertebral body and vertebral foramen, located the narrowest part of vertebral pedicle based on rotating segment algorithm and calculated medical parameters. The experimental results show that the segmentation accuracy of algorithm is 95.92%, the average relative error of extracted parameters was no more than 4.18%. This method realizes automatic and accurate planning of puncture path before PVP, and it is of great significance to reduce the workload of surgeons, the number of intraoperative fluoroscopy and the harm of radiation to surgeons.