Deformable Ultrasound Registration without Reconstruction

Authors:
Rupert Brooks;D. Louis Collins;Xavier Morandi;Tal Arbel
Affiliations:
Centre for Intelligent Machines, McGill University,;Dept. of Biomedical Engineering, McGill University,;Dept. of Neurosurgery, University Hospital of Rennes,;Centre for Intelligent Machines, McGill University,
Venue:
MICCAI '08 Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention, Part II
Year:
2008

Citing 4
Cited 2

Scale-Space and Edge Detection Using Anisotropic Diffusion

IEEE Transactions on Pattern Analysis and Machine Intelligence
Joint image registration and volume reconstruction for 3D ultrasound

Pattern Recognition Letters - Speciqal issue: Ultrasonic image processing and analysis
An Image Registration Approach to Automated Calibration for Freehand 3D Ultrasound

MICCAI '00 Proceedings of the Third International Conference on Medical Image Computing and Computer-Assisted Intervention
Automatic Non-linear MRI-Ultrasound Registration for the Correction of Intra-operative Brain Deformations

MICCAI '01 Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention

Bayesian Registration via Local Image Regions: Information, Selection and Marginalization

IPMI '09 Proceedings of the 21st International Conference on Information Processing in Medical Imaging
Fast and robust registration based on gradient orientations: case study matching intra-operative ultrasound to pre-operative MRI in neurosurgery

IPCAI'12 Proceedings of the Third international conference on Information Processing in Computer-Assisted Interventions

Quantified Score

Hi-index	0.01

Visualization

Abstract

Ultrasound (US) imaging is often proposed as an interoperative imaging modality. This use nearly always requires that the collected data be registered to preoperative data of another modality. Existing intensity-based registration approaches all begin by reconstructing a 3D US volume from the collected 2D slices. We propose to directly register the set of 2D slices to the preoperative images. We argue this has a number of advantages, including the omission of the potentially complex reconstruction step, greater adaptability of the similarity measures, and easier parallelization. We describe a system for performing this task and present results on phantom data that show that our slice based method consistently outperforms a reconstruction based method in both speed and accuracy.