360 Assessment of Pedicle Screw Placement Accuracy Utilizing a Novel Augmented Reality and Artificial Intelligence Surgical Guidance System

Abstract

INTRODUCTION: The integration of artificial intelligence (AI) and augmented reality (AR) technologies in spine navigation has the potential to minimize pedicle screw misplacement, decrease radiation exposure, and improve procedural efficiency, addressing some of the challenges associated with spinal instrumentation. METHODS: Sixty lumbosacral pedicle screws were placed by 4 Orthopedics surgeons in 6 cadavers using the AR/AI surgical navigation system. Two CT intraoperative scans (before and after screw placement) of the cadaveric specimens were obtained for the study to measure the 3D positional and angular discrepancies between virtual and real screws. The validation procedure consisted of 3 steps: (1) automatic registration and 3D coordinate transformation, where the preop CT scan was aligned with the postop scan to determine the virtual screw 3D positions and orientations in postop scan; (2) analysis of the postop scan to determine the real screw 3D positions and orientations as they appeared in the scan volume; (3) automatic comparison between the 3D positions and orientations of the virtual and real screws. RESULTS: A one-sample t-test statistical analysis yielded a mean positional error of 2.16 mm ± 1.00 mm (99% CI: 1.81-2.49 mm), and a mean angular error of 1.49± 0.73° (99% CI: 1.25-1.74°). These results were independent of anatomical level, side, and surgeon. CONCLUSIONS: This study indicates that this AR/AI surgical guidance system provides mean positional and angular errors lower than 3.0 mm and 3.0° respectively, thus complying with FDA-required regulatory acceptance criteria. The system was FDA-cleared as a US 510k Orthopedic Stereotaxic Instrument.