Estimation Of Non-rigid Deformations In The Three-dimensional Space AndTime Domains In Medical Images

Estimation of the non-rigid deformation in objects over the three-dimensional space and time domains can be applied to the field of medical image analysis. We present a new methodology that extends techniques for estimation of deformation over the spatial domain to incorporate the time domain by introducing a scheme for tracking the surface in moving and deformable objects, which supports semi-automatic segmentation of sets of 3-D medical images. Furthermore, previous methods for estimation of deformation are based only on matching two 3-D surfaces by minimizing the differences between them. In the other hand, our approach also incorporates the matching of two sets of feature points, and we have shown that deformation estimates based on simultaneous matching of surfaces and features are more accurate than those based on surface matching alone. This is especially true when the deformation involves physically realistic cases, such as those in human organs. Our technique applies the Wavelet Transform to extract feature points in the 3-D space. Feature point extraction also provides a means to compute the error in our estimates. We have applied our method to register sequences of MRI images of the carotid artery.