A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Principal Warps: Thin-Plate Splines and the Decomposition of Deformations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Approximate Thin Plate Spline Mappings
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
MR Compatible Surgical Assist Robot: System Integration and Preliminary Feasibility Study
MICCAI '00 Proceedings of the Third International Conference on Medical Image Computing and Computer-Assisted Intervention
MICCAI '01 Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention
A new point matching algorithm for non-rigid registration
Computer Vision and Image Understanding - Special issue on nonrigid image registration
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
An Adaptive and Stable Method for Fitting Implicit Polynomial Curves and Surfaces
IEEE Transactions on Pattern Analysis and Machine Intelligence
SURF: speeded up robust features
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Hi-index | 0.00 |
In surgery, it is common to open large incisions to remove tiny tumors. Now, robotic surgery has been well recognized for high precision. However, target localization is still a challenge, owing to non-rigid deformations. Thus, we propose a precise and flexible localization framework for an MRIcompatible needle-insertion robot. We primarily address with two problems: 1) How to predict the position after deformation? 2) How to turn MRI coordinate to real-world one? Correspondingly, the primary novelty is the non-rigid position transformation model based on Thin-Plate Splines. A minor contribution lies in the data acquisition for coordinate correspondences. We validate the precision of the whole framework, and each procedure of coordinate acquisition and position transformation. It is proven that the system under our framework can predict the position with a good approximation to the target's real position.