Medical image interpolation based on multi-resolution registration

摘要

We present a novel registration-based image interpolation approach in this paper. The proposed method is divided into two steps: image registration and intensity interpolation. An image registration method is developed to construct a corresponding transformation, which is represented by the bicubic B-spline vector-valued function, between the given images so that the image features are well matched. To match features from coarse to fine, a multi-resolution strategy is applied with different numbers of B-spline control points adopted at various resolution levels. After registration, the intensity values of in-between images are calculated by linear/cubic interpolation along the matching lines. Experimental results demonstrate that our interpolation approach is effective, robust, and capable of producing continuously deformed in-between images with clear shape features.