Related Experiment Video
Updated: Dec 20, 2025
In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
Published on: July 2, 2021
i3PosNet: instrument pose estimation from X-ray in temporal bone surgery
David Kügler1,2, Jannik Sehring3, Andrei Stefanov3
1Department of Computer Science, Technischer Universität Darmstadt, Darmstadt, Germany. david.kuegler@dzne.de.
Purpose:
Accurate estimation of the position and orientation (pose) of surgical instruments is crucial for delicate minimally invasive temporal bone surgery. Current techniques lack in accuracy and/or line-of-sight constraints (conventional tracking systems) or expose the patient to prohibitive ionizing radiation (intra-operative CT). A possible solution is to capture the instrument with a c-arm at irregular intervals and recover the pose from the image.
Methods:
i3PosNet infers the position and orientation of instruments from images using a pose estimation network. Said framework considers localized patches and outputs pseudo-landmarks. The pose is reconstructed from pseudo-landmarks by geometric considerations.
Results:
We show i3PosNet reaches errors [Formula: see text] mm. It outperforms conventional image registration-based approaches reducing average and maximum errors by at least two thirds. i3PosNet trained on synthetic images generalizes to real X-rays without any further adaptation.
Conclusion:
The translation of deep learning-based methods to surgical applications is difficult, because large representative datasets for training and testing are not available. This work empirically shows sub-millimeter pose estimation trained solely based on synthetic training data.
