PDF version of this document

Validation Experiments

Method

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, as shown below.

3#3 = 28#28

The images were initially registered using an NRR algorithm based on MDL optimisation [2]. A set of different mis-registrations was then created by applying smooth pseudo-random spatial warps to the registered images. 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.

2#2

Data

3#3 = 29#29 Increasing perturbation in mean pixel shift

Results

The results below show that all variants of both the overlap and model-based quality measures change systematically with increasing mis-registration.

3#3 = 30#30