| | |
Summary: Reliability-Driven, Spatially-Adaptive
Regularization for Deformable Registration
Lisa Tang1
, Ghassan Hamarneh1
, and Rafeef Abugharbieh2
1
Medical Image Analysis Lab., School Computing Science, Simon Fraser University
2
Biomedical Signal and Image Computing Lab.,
Department of Electrical and Computer Engineering, University of British Columbia
{hamarneh,lisat}@cs.sfu.ca, rafeef@ece.ubc.ca
Abstract. We propose a reliability measure that identifies informative
image cues useful for registration, and present a novel, data-driven ap-
proach to spatially adapt regularization to the local image content via use
of the proposed measure. We illustrate the generality of this adaptive reg-
ularization approach within a powerful discrete optimization framework
and present various ways to construct a spatially varying regularization
weight based on the proposed measure. We evaluate our approach within
the registration process using synthetic experiments and demonstrate its
utility in real applications. As our results demonstrate, our approach
|
