A hybrid method to improve target registration accuracy in surgical navigation

Background: The accuracy of surgical navigation depends greatly on that of registration between the patient and the medical image. Point-based registration has been the most common and reliable method, which typically uses skin markers. Unfortunately, high registration accuracy around the markers is not sustained at targets deeply seated within the body. To address such increase in target registration error (TRE), we proposed a hybrid point-based registration method that incorporates anatomical landmarks near the target. Material and methods: Ultrasound calibration is performed with an optical tracker for coordinate frame conversion of image coordinates into the real world. With the calibrated ultrasound probe, we could non-invasively obtain landmark positions near the target, being used together with skin markers for registration. Results: In the experiment, we examined registration accuracies achieved with and without use of an anatomical landmark. We confirmed that using an additional anatomical landmark in registration resulted in an increase in fiducial regsitration error (FRE), but a significant decrease in TRE (p < 0.001). Conclusion: We proposed and demonstrated the effectiveness of a hybrid method that uses both artificial and anatomical landmarks for patient-to-image registration. The experimental results confirmed that an improvement in TRE was evident by the proposed method, suggesting its feasibility in various spinal surgeries.