Evaluation of Depth-Sensing Accuracy for AR Surgical Guidance in Dynamic Operating Room Environments

Authors

  • Adrian K. Wong Department of Mechanical Engineering, The University of Hong Kong, Pok Fu Lam Road, Hong Kong SAR, China Author
  • Victor T. Ho Department of Mechanical Engineering, The University of Hong Kong, Pok Fu Lam Road, Hong Kong SAR, China Author
  • Samuel C. Lee Department of Mechanical Engineering, The University of Hong Kong, Pok Fu Lam Road, Hong Kong SAR, China Author
  • Mei L. Chan Department of Biomedical Engineering, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, China Author
  • Carmen Y. Lau Department of Biomedical Engineering, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, China Author

DOI:

https://doi.org/10.71465/fht453

Keywords:

depth-sensing evaluation, AR surgical navigation, device benchmarking, operating room robustness

Abstract

Operating  rooms  pose  challenges  for  depth  sensing  due  to  variable  illumination  and instrument occlusion. We benchmarked Kinect v2, RealSense D455, and HoloLens 2 across 100 trials simulating surgical conditions. Metrics included mean depth error, temporal stability, and robustness to  glare.  Results  showed Kinect v2  error  at  2.7 mm,  HoloLens 2  at  1.9  mm,  and RealSense at  1. 1 mm.  Stability under surgeon motion was highest with RealSense  (94% valid frames).  Recommendations  include  hybrid  calibration  workflows  and  adaptive  denoising  for clinical adoption.

Downloads

Download data is not yet available.

Downloads

Published

2025-11-30

Issue

Vol. 2 No. 1 (2025): Frontiers in Healthcare Technology

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.