# i3PosNet: Instrument Pose Estimation from X-Ray in temporal bone surgery

arXiv: https://arxiv.org/abs/1802.09575 · HTML: https://mlsanity.com/paper/1802.09575/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2018.

## Built on by (most cited first, 4 of 4)

- [Artificial Intelligence for Cochlear Implants: Review of Strategies, Challenges, and Perspectives](https://mlsanity.com/paper/2403.15442/) (2024)
- [Advancing 6-DoF Instrument Pose Estimation in Variable X-Ray Imaging Geometries](https://mlsanity.com/paper/2405.11677/) (2024)
- [Towards real-time 6D pose estimation of objects in single-view cone-beam X-ray](https://mlsanity.com/paper/2211.03211/) (2022)
- [Multi-view X-ray Image Synthesis with Multiple Domain Disentanglement from CT Scans](https://mlsanity.com/paper/2404.11889/) (2024)

## Abstract (arXiv)

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 less than 0.05mm. 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.