PDF version of this document

EXPERIMENTS

Validation:

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].

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 = 20#20 Example image and corresponding labels

3#3 = 21#21 Examples of data with increased perturbation magnitude

Method Sensitivity:

To tell apart one method from method from another and quantifying its power, we define a measure of sensitivity. Sensitivity is the extent of measures change proportional to the degree of displacement and error.

Practical Application:

We compare 3 NRR algorithms: a pairwise algorithm, a groupwise algorithm and another groupwise algorithm which is based on minimum description length [2].