Back

Assessment of Augmented Reality Glasses for Spatial Tracking and Intraoperative Annotation in Veterinary Surgery

Tipirneni, Y.; Blandino, A.; Skouritakis, C. A.-T.; Arzi, B.; Goldschmidt, S.

2025-12-29 bioengineering
10.64898/2025.12.18.695281 bioRxiv
Show abstract

ObjectivesAugmented reality (AR) glasses may improve surgical precision by projecting holographic overlays directly onto the surgical field. This study aimed to evaluate the feasibility of AR technology for enhancing spatial tracking. MethodsWe developed an AR application in Unity compatible with XReal glasses that allowed users to annotate and interact with a realistic 3D hologram of a dog head. Resident and specialist veterinarians were recruited to completed coordinate (distance) and outline (area) annotations under two conditions: (1) transfer: memorizing targets from a computer screen, and (2) direct: seeing the targets directly on the head. Distance errors, area metrics, and completion times were recorded from each participant. ResultsThe mean distance error (N = 22) was significantly lower for direct versus transfer coordinates (2.73 {+/-} 0.79 mm vs. 3.42 {+/-} 1.81 mm). Area coverage (N = 20) was higher (83.7% {+/-} 13.4% vs. 63.3% {+/-} 16.2) and non-overlap was similarly reduced with AR-guidance. Completion times differed significantly between the transfer and direct groups for coordinate tasks (11.2 {+/-} 10.4 sec versus 8.19 {+/-} sec) but not for area tracing (25.7 {+/-} 18.3 sec versus 26.8 {+/-} 26.5 sec). ConclusionAR-guided visualization improved spatial accuracy for both distance and area metrics without reducing speed. The effects observed for specialty, eyewear, or arm length were negligible. However, the level of experience with a cutoff of 2 years did have a significant effect on distance error. Clinical RelevanceThese findings support the utility of AR for optimizing surgical precision in veterinary medicine.

Published in American Journal of Veterinary Research · not in our set (fewer than 10 published preprints to learn from) · training set

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.