Article reference:
J.P. Janssen, M. Egmont-Petersen, E.A. Hendriks, M.J.T. Reinders, R.J. van
der Geest, P.C.W. Hogendoorn, J.H.C. Reiber. "Scale-invariant segmentation
of dynamic contrast-enhanced perfusion MR-images with inherent scale
selection," Journal of Visualisation and Computer Animation, Vol.
13, No. 1, pp. 1-19, 2002.
Abstract:
Selection of the best set of scales is problematic when developing
signal-driven approaches for image segmentation. Often, different possibly
conflicting criteria need to be fulfilled in order to obtain the best possible
trade-off between uncertainty (variance) and location accuracy. The optimal set
of scales depends on several factors: the noise level present in the image
material, the prior distribution of the different types of segments, the
class-conditional distributions associated with each type of segment as well as
the actual size of the (connected) segments. We analyse, theoretically and
through experiments, the possibility of using the overall and class-conditional
error rates as criteria for selecting the optimal sampling of the linear and
morphological scale spaces. It is shown that the overall error rate is
optimised by taking the prior class distribution in the image material into
account. However, a uniform (ignorant) prior ensures constant class-conditional
error rates. Consequently, we advocate for a uniform prior class distribution
when an uncommitted, scale-invariant segmentation approach is desired.
Experiments with a neural net classifier developed for segmentation of dynamic
MR images, acquired with a paramagnetic tracer, support the theoretical
results. Furthermore, the experiments show that the addition of spatial features
to the classifier, extracted from the linear or morphological scale spaces,
improves the segmentation result compared to a signal-driven approach based
solely on the dynamic MR signal. The segmentation results obtained from the two
types of features are compared using two novel quality measures that
characterise spatial properties of labelled images.
Electronic reprint , or contact me per email: michael * egmont-petersen.nl (with * indicating @)