摘要：Image-based change quantitation has been recognized as a promising
tool for accurate assessment of tumor's early response to
chemoprevention in cancer research. For example, various changes
on breast density and vascularity in glandular tissue are the
indicators of early response to treatment. Accurate extraction of
glandular tissue from pre- and postcontrast magnetic resonance
(MR) images requires a nonrigid registration of sequential MR
images embedded with local deformations. This paper reports a
newly developed registration method that aligns MR breast images
using finite-element deformable sheet-curve models. Specifically,
deformable curves are constructed to match the boundaries
dynamically, while a deformable sheet of thin-plate splines is
designed to model complex local deformations. The experimental
results on both digital phantoms and real MR breast images using
the new method have been compared to point-based thin-plate-spline
(TPS) approach, and have demonstrated a significant and robust
improvement in both boundary alignment and local deformation
recovery.
