HIERARCHICAL NONRIGID MODEL FOR 3D MEDICAL IMAGE REGISTRATION

In this paper, we propose a hierarchical model for medical image registration with a new descriptor which considers scale, rotation, and location attributes. Our proposed algorithm is a feature-based registration technique and our features encode location and orientation for matching. Using the proposed feature, 3D medical images are registered through three phases in the hierarchical model that progressively estimate the geometric transformation to align and orient features. Our approach is evaluated on both synthetic and real data using the ground-truth evaluation. Our results show that our method improved alignment accuracy compared to traditional non-rigid image registration algorithms.