PDF version of this document

Validation Experiments

Ground-Truth Data:

The overlap-based and model-based approaches were validated and compared, using a dataset consisting of 36 transaxial mid-brain slices, extracted at equivalent levels from a set of T1-weighted 3D MR scans of different subjects. Eight manually annotated anatomical labels were used as the basis for the overlap method: L/R white matter, L/R grey matter, L/R lateral ventricle, and L/R caudate. The images were brought into alignment using an NRR algorithm based on MDL optimisation [2].

3#3 = 26#26 Example image and corresponding labels

2#2

Systematic Perturbation:

A set of different mis-registrations was then created by applying smooth pseudo-random spatial warps to the registered images. These warps were based on biharmonic Clamped Plate Splines. Ten different warp instantiations were generated for each image at each of seven progressively increasing values of average pixel displacement. Registration quality was measured, for each level of registration degradation, using several variants of each of the proposed assessment methods.

3#3 = 27#27 Examples of data with increased perturbation magnitude

Results:

Shown below are the two non-rigid registration assessment methods, as function of misalignment.

3#3 = 28#28