FPGA implementation of an efficient partial volume interpolation for medical image registration

Image registration is the process of overlaying two or more images of the same scene taken at different times, from different viewpoints, and/or by different sensors. It geometrically aligns two images the reference and floating images. Medical image registration concentrates on aligning two or more images that represent the same anatomy from different angles and are obtained at different times. In recent efforts, image registration algorithms have been implemented in FPGA technology to improve performance while providing programmability and dynamic configurability. To transform points from one image to another, similarity metric is an important criteria. This can be calculated efficiently using mutual information based technique. When transforming a floating image to reference image the transformed location of a voxel of the floating image may not coincide with the location of a voxel in the reference image, so interpolation is needed. This can be done effectively by partial volume interpolation, because it produces smooth changes with small changes in transformation and improves subvoxel accuracy. Partial volume interpolator consists of multipliers as its main component. In this work, it is implemented using array multiplier and CSA multiplier and compared the performance of these multipliers.