Objective: Accurate placement of external ventricular drains (EVDs) is achieved in only approximately 67–74% of cases using the conventional freehand technique. Augmented reality (AR) offers the potential to improve this by providing real-time, patient-specific anatomical guidance. This thesis evaluates whether CT-based anatomical landmark registration using the Lumi AR workflow is sufficiently accurate, robust, and feasible to support and eventually improve EVD placement. This also includes exploring the clinical acceptability of AI-generated landmarks to streamline the workflow.
Methods: Two studies were performed. First, four clinicians assessed the accuracy of AI-generated anatomical landmarks on CT-derived 3D models, with adjustment rates and interobserver agreement quantified. Second, a prospective pilot study in the operating room (OR) was conducted using the Lumi AR workflow on the HoloLens 2 to perform point-based registration with manually annotated landmarks. The primary outcome was target registration error (TRE); secondary outcomes included fiducial registration error (FRE), visual accuracy ratings, registration time, system robustness and workflow feasibility.
Results: AI-generated landmarks required adjustment in 22.9% of cases (95% CI, 19.1–27.1%), with high median partial interobserver agreement (100.0%, IQR 25.0%) but only moderate mean unanimous agreement (61.0%, 95% CI 51.4–69.7%; Fleiss’ kappa = 0.42). In the OR pilot (n=11), the mean TRE at the nasion was 4.9 mm (SD, 2.1 mm). For fiducial validation points, mean TREs were 7.4 mm (SD, 1.7 mm) and 4.9 mm (SD, 1.9 mm). The mean FRE was non-inferior to that reported in a previous phantom study, visual accuracy ratings indicated good perceived alignment, and registration was completed in five minutes on average. Workflow interruptions were primarily due to hardware instability, including three critical failures.
Discussion & Conclusion: AI-generated anatomical landmarks are not yet sufficiently reliable for clinical use in high-stakes scenarios such as EVD placement. In contrast, point-based registration with manually annotated landmarks, using the Lumi AR workflow, proved clinically feasible and achieved an accuracy that is likely acceptable for EVD guidance. However, system robustness remains a key limitation, with AR hardware instability representing the primary obstacle to clinical implementation. Additional limitations include the small pilot sample size, which restricts generalisability, and the variability of soft-tissue surface landmarks. While further advances in AR hardware and validation in larger cohorts are required, these findings indicate that CT-based anatomical landmark registration using AR shows clear potential for guiding future EVD placements.

Purpose: Patient-specific implants (PSIs) and surgical guides are widely used nowadays for the reconstruction of craniofacial defects. In this research, we quantitatively compared the realised position of craniofacial PSIs with the planned position and we calculated the difference between the realised osteotomy and the planned osteotomy if a resection preceded the reconstruction. Methods: We retrospectively included patients who received a craniofacial polyetheretherketone (PEEK) PSI in the LUMC between February 2019 and January 2021 and had a postoperative CT scan available. Postoperative CT scans were aligned with preoperative CT scans, followed by segmentation of the postoperative PSI position and skull, on which the realised osteotomy was defined by an inner and outer curve. Translation and rotation between the realised PSI position and planned PSI position were calculated as well as the surface distance between the realised osteotomy curves and the planned osteotomy. Results: 19 patients were included, regarding cranial (n = 11) and orbital (n = 8) implants. The translation vector length ranged from 0.5 mm to 6.7 mm and rotational deviation ranged from 0.9° to 17.4°, both being higher for orbital implants than for cranial implants (U = 3.00, p = .000, U = 15.0, p = .016). 12 patients were included in the osteotomy analysis. Mean distance between realised and planned osteotomy was 1.4 mm (SD 1.6) for outer curves and 0.5 mm (SD 1.7) for inner curves. Absolute mean distances over the two curves ranged from 0.6 mm (SD 0.5) to 4.1 mm (SD 2.6), accurately reproducing the planned osteotomy in most cases. Conclusion: In this study, there was a large variation in positioning accuracy for craniofacial PSIs. Cranial implants, being in good agreement with the planned PSI positions, were positioned with higher accuracy than orbital implants. In general, realised osteotomies were larger than planned. Better use and positioning of surgical guides could increase the PSI positioning accuracy. Clinical and aesthetical outcomes need to be included in future studies.