Matrix animation and polar decomposition
Proceedings of the conference on Graphics interface '92
A machine learning approach for deformable guide-wire tracking in fluoroscopic sequences
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part III
Nonparametri information fusion for motion estimation
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Graph-based geometric-iconic guide-wire tracking
MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part I
| Hi-index | 0.00 |
Tracking anatomical structures in X-Ray sequences has broad applications, such as motion compensation for dynamic 3D/2D model overlay during image guided interventions. Many anatomical structures are curve-like such as ribs and liver dome. To handle various types of anatomical curves, a generic and robust tracking framework is needed to track shapes of different anatomies in noisy X-ray images. In this paper, we present a novel tracking framework, which is based on adaptive measurements of structures' shape, motion, and image intensity patterns. The framework does not need offline training to achieve robust tracking results. The framework also incorporates an online learning method to robustly adapt to anatomical structures of different shape and appearances. Experimental results on real-world clinical sequences confirm that the presented anatomical curve tracking method improves the tracking performance compared to a baseline performance.