Extension of the ICP algorithm to non-rigid intensity-based registration of 3D volumes

Abstract

Presents a new registration and gain correction algorithm for 3D medical images. It is intensity based. The basic idea is to represent the images by 4D points (x/sub j/, y/sub j/, z/sub j/, i/sub j/) and to define a global energy function based on this representation. For minimization, the authors propose a technique which does not require to compute the derivatives of this criterion with respect to the parameters. It can be understood as an extension of the Iterative Closest Point algorithm (P. Besl and N. McKay, 1992; Z. Zhang, 1992) or as an application of the formalism proposed by L. Cohen (Use of auxiliary variables in computer vision problems. In Proceedings of the Fifth International Conference on Computer Vision (ICCV '95), Boston, June 1995). Two parameters allow one to have a coarse to fine strategy both for resolution and deformation. The authors' technique presents the advantage to minimize a well defined global criterion to deal with various classes of transformations (for example rigid, affine and volume spline), to be simple to implement and to be efficient in practice. Results on real brain and heart 3D images are presented to demonstrate the validity of the authors' approach.