Self-Geometry-Guided Direct Pose Regression Based on Dual Perspective Fusion for 2D-3D Cross Dimensional Spinal Surgery Navigation
Jing Ling, Zhengyang Wu, Changqing Li, Weisheng Li, Chao Zhang, Yucheng Shu
Abstract
2D-3D cross-dimensional registration for spinal surgery navigation, which aims to achieve real-time visual navigation of preoperative 3D vertebrae based on intraoperative 2D fluoroscopy images, faces significant challenges due to semantic and dimensional gaps. Traditional 2D-3D registration methods often require fine adjustment steps and have low computational efficiency. In this paper, we propose a self-geometry-guided direct regression method based on dual perspective images. Firstly, an effective mechanism for unifying the dual view coordinate system was proposed. Secondly, a novel feature extraction module based on a face-graph convolutional network (F-GCN) is proposed to effectively extract 3D vertebra posture features. Finally, a posture direct regression network guided by self-vertebral geometry based on 2D-3D fusion features was constructed. Experimental results show that our method has made significant progress in solving the problem of 2D-3D cross-dimensional registration for spinal surgery navigation.
BibTeX
@inproceedings{icassp2025_selfgeometryguid,
title = {Self-Geometry-Guided Direct Pose Regression Based on Dual Perspective Fusion for 2D-3D Cross Dimensional Spinal Surgery Navigation},
author = {Jing Ling and Zhengyang Wu and Changqing Li and Weisheng Li and Chao Zhang and Yucheng Shu},
booktitle = {ICASSP 2025},
year = {2025}
}