Deformable models have found widespread applicability in diverse
fields during the past 15 years. This talk will discuss deformable
shape models in the context of two problems: computational anatomy and
modeling soft tissue deformability for surgical applications. A
shape-based approach to deformable registration of medical images will
be presented, along with applications involving primarily the
computational morphometry of the brain, the spine, and the prostate. A
framework for combining statistical shape models and biomechanics will
also be presented, with the goal of predicting diverse anatomical
deformations, including deformations to be predicted and tracked in
image-guided surgical environments.