Figure compares the performance of the three
registration algorithms outlined in
Section
. All the measures tested in the
previous section were computed, but we show results for only the
most sensitive model-based method. Figures
(a) and
(c) show Specificity calculated using a shuffle radius of 2.1, for
different values of 34#34, the number of modes used to build the
generative model. Figure
(b) shows generalised
overlap using different weightings. The results shown in
Figure
(a) suggest that the MDL groupwise approach
gives the best registration result for the MGH Dataset, followed
by Pairwise and Congealing in order of decreasing performance -
irrespective of the value of 34#34. Inspection of the error bars
shows that these differences are statistically significant. The
results for Generalised Overlap, shown in Figure
(b),
are more complicated, with the performance of the different NRR
algorithms ordered differently for different weightings, though
inspection of the error bars shows that many of the differences
are not significant. Overall, the same general pattern emerges
as for Specificity, with the Groupwise method generally best
(statistically significantly in two cases), but with no
significant difference between Pairwise and Congealing in most
cases. The results for inverse volume weighting generally lack
significance, but are inconsistent with those obtained using the
other weighting schemes. Volume weighting gives the best
separation between the different variants, and places the three
methods in the same order as Specificity. Overall, this supports
the interpretation that Specificity give results that are
generally equivalent to those obtained using Generalised Overlap,
but with higher sensitivity. Finally, the Specificity results
shown in Figure
(c) for the Dementia Dataset, place
the three methods in the same order.
103#103
|