Our goal is to develop automated methods for the segmentation of thr-
dimensional biomedical images. Here, we describe the segmentation of c-
focal microscopy images of bee brains (20 individuals) by registration
to one or several atlas images. Registration is performed by a highly
parallel imp- mentation of an entropy-based nonrigid registration
algorithm using B-spline transformations. We present and evaluate
different methods to solve the cor- spondence problem in atlas based
registration. An image can be segmented by registering it to an
individual atlas, an average atlas, or multiple atlases. When
registering to multiple atlases, combining the individual segmentations
into a ?nalsegmentationcanbeachievedbyatlasselection,
ormulticlassi?erdecision fusion.
Wedescribeallthesemethodsandevaluatethesegmentationaccuracies that they
achieve by performing experiments with electronic phantoms as well as by
comparing their outputs to a manual gold standard. The present work is
focused on the mathematical and computational t- ory behind a technique
for deformable image registration termed Hyperelastic Warping, and
demonstration of the technique via applications in image regist- tion
and strain measurement. The approach combines well-established prin-
ples of nonlinear continuum mechanics with forces derived directly from
thr- dimensional image data to achieve registration. The general
approach does not require the de?nition of landmarks, ?ducials, or
surfaces, although it can - commodate these if available. Representative
problems demonstrate the robust and ?exible nature of the approach.
Three-dimensional registration methods are introduced for registering
MRI volumes of the pelvis and prostate. The chapter ?rst reviews the
applications, xi xii Preface challenges, and previous methods of image
registration in the prostate