Abstract
In orthopaedic surgery, preoperative computed tomography (CT) or cone-beam computed tomography (CBCT) provides detailed 3D anatomy for planning, but this information loses spatial correspondence with the patient after intraoperative repositioning. Improving how surgeons perceive and use preoperative information intraoperatively therefore remains challenging. Existing work has largely focused on image registration, while the intraoperative visualization of the registered anatomy has received less attention. We present an imaging-to-AR workflow that combines multi-view 2D/3D X-ray-to-volume registration with augmented reality (AR). Tracked multi-view radiographs are acquired intraoperatively and registered to the preoperative volume to estimate the registered bone pose. Optical-tracking-to-AR (OT-to-AR) calibration then transforms this pose into the AR world frame for an in situ AR bone overlay. Across 49 Femur registration trials, Dual reduced the cohort mean of per-trial 3D mean target registration error (mTRE) from 22.200 to 8.486 mm and the number of trials above 10 mm from 24 to 13. Across 366 DeepFluoro registration trials, Triple reduced the cohort mean of per-trial 3D mTRE from 4.889 to 3.188 mm and the number of trials above 10 mm from 25 to 7. Calibration convergence was assessed using 100 synchronized OT–AR pose pairs, and the error curves stabilized near 35 pairs, while independent validation yielded mean translational and rotational errors of 1.253 mm and 1.442◦. These results demonstrate the feasibility of integrating preoperative (CB)CT, intraoperative X-ray registration, and AR visualization in a unified orthopaedic workflow.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/CREATE_017.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: https://papers.miccai.org/miccai-2026-sat/supp/CREATE_017_supp.pdf
Link to Open Review
Open Review Page: https://openreview.net/forum?id=ue0EAsHxOx
BibTex
@InProceedings{YueJia_Intraoperative_MICCAISAT2026,
author = { Yue, Jianfeng AND Li, Feng AND Song, Tianyu AND Eck, Ulrich AND Navab, Nassir},
title = { { Intraoperative AR Visualization of Preoperative (CB)CT via X-Ray Registration } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17275},
month = {pending},
page = {pending}
}