Elastic Registration with Partial Data

S. Periaswamy and H. Farid

Second International Workshop on Biomedical Image Registration, Philadelphia, PA, 2003

Paper (ps.gz)    Paper (pdf)    Bibtex

(an expanded version of this paper was selected to appear in a special issue of Medical Image Analysis)

We have developed a general purpose registration algorithm for medical images and volumes. The transformation between images is modelled as locally affine but globally smooth, and explicitly accounts for local and global variations in image intensities. An explicit model of missing data is also incorporated, allowing us to simultaneously segment and register images with partial or missing data. The algorithm is built upon a differential multiscale framework and incorporates the expectation maximization algorithm. We show that this approach is highly effective in registering a range of synthetic and clinical medical images.