论文信息 - A Comparison of 2D-3D Intensity-Based Registration and Feature-Based Registration for Neurointerventions

A Comparison of 2D-3D Intensity-Based Registration and Feature-Based Registration for Neurointerventions

Registration of 2D-3D data can improve visualisation during minimally-invasive neurointerventions. Using four clinical data sets, we quantitatively compared two approaches: an intensity-based algorithm and a feature-based algorithm. The intensity-based approach was found to be more accurate, with an average registration accuracy of 1.4mm, compared to the feature-based algorithm with an average accuracy of 2.3mm. The intensity-based algorithm was also found to be more reliable. Reliability of the feature-based algorithm was found to be more sensitive to the complexity of the vasculature structure.

[1] Jürgen Weese,et al. A comparison of similarity measures for use in 2-D-3-D medical image registration , 1998, IEEE Transactions on Medical Imaging.

[2] Robert C. Bolles,et al. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[3] J. Alison Noble,et al. Real-Time Registration of 3D Cerebral Vessels to X-ray Angiograms , 1998, MICCAI.

[4] Hiroshi Iseki,et al. Interactive virtualized display system for intravascular neurosurgery , 1997, CVRMed.

[5] J. Alison Noble,et al. Statistical 3D Vessel Segmentation Using a Rician Distribution , 1999, MICCAI.

[6] J. Alison Noble,et al. Fusing Speed and Phase Information for Vascular Segmentation in Phase Contrast MR Angiograms , 2000, MICCAI.

[7] Graeme Penney. Registration of tomographic images to X-ray projections for use in image guided interventions , 2000 .

[8] David W. Murray,et al. Visual head tracking and slaving for visual telepresence , 1996, Proceedings of IEEE International Conference on Robotics and Automation.