PDF version of this entire document

Perturbing the Registration

A test set of different registrations was created by applying smooth pseudo-random spatial warps (based on biharmonic Clamped Plate Splines [20]) to each image in the registered set. Each warp was controlled by 25 randomly placed knot-points, each displaced in a random direction by a distance drawn from a Gaussian distribution whose mean controlled the average magnitude of pixel displacement over the whole image. Example images from the test set are shown in Figure 8. Ten different warp instantiations were generated for each image and for each of seven progressively increasing values of average pixel displacement.

Figure 7: An example affinely-aligned brain image and its accompanying anatomical labels, both overlaid and expanded, for gray matter, white matter, the lateral ventricles, and the caudate nucleus. Labels are also divided into left and right.

Figure 8: Examples registration degradation through image deformation for increasing scales of smooth CPS warps. Mean pixel displacement for each image is shown.

The correspondence from the initial registration was applied to the deformed images resulting in a controlled degree of misregistration. The correspondence becomes progressively worse as the degree of image deformation increases.