Feasibility of automatic screw planning via transformer-based shape completion from RGB-D imaging.
Authors
Affiliations (3)
Affiliations (3)
- Research in Orthopedic Computer Science (ROCS), University Hospital Balgrist, University of Zurich, 8008, Zurich, Switzerland. [email protected].
- Department of Orthopedics, University Hospital Balgrist, 8008, Zurich, Switzerland.
- Research in Orthopedic Computer Science (ROCS), University Hospital Balgrist, University of Zurich, 8008, Zurich, Switzerland.
Abstract
Accurate pedicle screw placement (PSP) is essential in spinal fusion surgery. Conventional navigation relies on computed tomography (CT) or fluoroscopy, which involves ionizing radiation and requires an error-prone registration procedure. We propose a pipeline that enables PSP planning directly on vertebral point clouds reconstructed from intraoperative RGB-D scans, using the SurgPointTransformer network. The system detects screw entry and pedicle regions, estimates initial trajectories, and refines them via anatomically constrained optimization. We evaluated our method on nine ex-vivo cadaveric specimens, comparing RGB-D-based planning to a CT-based baseline using both RGB-D reconstructions and ground-truth CT meshes. No significant differences were found in entry-point offset (3.53 ± 1.30 mm vs. 3.90 ± 1.29 mm), pedicle-center offset (1.58 ± 0.58 mm vs. 1.68 ± 0.59 mm), trajectory-angle error (7.31 ± 3.34[Formula: see text] vs. 7.67 ± 3.59[Formula: see text]); all [Formula: see text]. Safety analysis using the Gertzbein-Robbins classification showed 100% radiologically optimal screw placement (grade A) with both methods. PSP planned from RGB-D reconstructions of the exposed dorsal surface alone achieved planning-level accuracy comparable to CT-based planning on the entire vertebral body. Prospective intraoperative validation is required to establish execution accuracy and clinical outcomes.