Mjolnir: Extending HAMMER Using a Diffusion Transformation Model and Histogram Equalization for Deformable Image Registration

<table>Demonstration of the benefits of Mjolnir's displacement field interpolation. The input to both algorithms (HAMMER and Mjolnir) was the hard segmentation of the image; hence the attribute vectors in both methods are the same. The top row shows the average over all regions, and the error bars represent the standard deviation.</table>

International Journal of Biomedical Imaging

fig9

Figure 9

Figure 9: Mjolnir: Extending HAMMER Using a Diffusion Transformation Model and Histogram Equalization for Deformable Image Registration 