A new method for contour correspondence based on the internal information in intensity-based ultrasound image registration

Comparing with the CT imaging, there are a lot of speckles in the ultrasound images. When we use the probe to detect the organism, we get a set of slices which are consecutive in the centroid. In the new method proposed in this paper, every contour in a slice is designated a value that represents its size and density, then the overall "centroid" of the slice is found. For each contour, its corresponding contour on the adjacent slice is determined based on their designated value and their polar coordinate to the slice centroid. For the aim of slice registration, adjacent slices are first aligned roughly according to their centroid, furthermore, the optimal registration position nearby which minimize the efficacy function which reflects the registration suitability at a given position.

[1]  B. N. Chatterji,et al.  An FFT-based technique for translation, rotation, and scale-invariant image registration , 1996, IEEE Trans. Image Process..

[2]  Scott T. Grafton,et al.  Automated image registration: I. General methods and intrasubject, intramodality validation. , 1998, Journal of computer assisted tomography.

[3]  Michael Unser,et al.  A pyramid approach to subpixel registration based on intensity , 1998, IEEE Trans. Image Process..

[4]  Bjørn Olstad,et al.  Volume rendering of 3D medical ultrasound data using direct feature mapping , 1994, IEEE Trans. Medical Imaging.

[5]  Clark F. Olson Image registration by aligning entropies , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[6]  J. Alison Noble,et al.  Nonrigid registration of 3-D free-hand ultrasound images of the breast , 2002, IEEE Transactions on Medical Imaging.

[7]  Muriel D. Ross,et al.  Method for semiautomated serial section reconstruction and visualization of neural tissue from TEM images , 1993, Electronic Imaging.

[8]  Raj Shekhar,et al.  Mutual information-based rigid and nonrigid registration of ultrasound volumes , 2002, IEEE Transactions on Medical Imaging.