Last update, March 31, 2003.

BACK

References in Medical Imaging on Registration :

• 2D-3D Registration Based on Shape Matching, 2000, Kimia et al., 2000.
• 3D/2D Registration via Skeletal Near Projective Invariance in Tubular Objects, Alan Liu, Elizabeth Bullitt, Stephen M. Pizer, 1998.
• A survey of medical image registration, J.B.A. Maintz & M.A. Viergever, 1998.
• Image matching as a diffusion process: an analogy with Maxwell's demons, J.-P. Thirion, 1998.
• Deformations incorporating rigid structures, Little JA, Hill DLG, Hawkes DJ., 1997.

BibTeX references.

The purpose of this paper is to present a survey of recent (published in 1993 or later) publications concerning medical image registration techniques. These publications will be classified according to a model based on nine salient criteria, the main dichotomy of which is extrinsic versus intrinsic methods. The statistics of the classification show definite trends in the evolving registration techniques, which will be discussed. At this moment, the bulk of interesting intrinsic methods is based on either segmented points or surfaces, or on techniques endeavouring to use the full information content of the images involved.

Key words: matching, registration.

In this paper, we present the concept of diffusing models to perform image-to-image matching. Having two images to match, the main idea is to consider the objects boundaries in one image as semi-permeable membranes and to let the other image, considered as a deformable grid model, diffuse through these artefacts, by the action of effectors situated within the membranes. We illustrate this concept by an analogy with Maxwell's demons. We show that this concept relates to more traditional ones, based on attraction, with an intermediate step being optical flow techniques. We use the concept of diffusing models to derive three different non-rigid matching algorithms, one using all the intensity levels in the static image, one using only contour points, and a last one operating on already segmented images. Finally, we present results with synthesized deformations and real medical images, with applications to heart motion tracking and 3D inter-patients matching.

Keywords: deformable model, elastic matching, image sequence analysis, inter-patient registration, non-rigid matching

Medical image registration algorithms invariably assume that the objects in the images can be treated as a single rigid body. In practice, some parts of a patient, usually bony structures, may move as rigid bodies, while others may deform. To address this, we have developed a new technique that allows identified objects in the image to move as rigid bodies, while the remainder smoothly deforms. The transformation is based on a radial basis function solution with a basis function modified by use of distance transforms based on rigid structures within the image. These (Euclidean) distance transforms are also used to form an underlying transformation which ensures an interpolating solution. The resulting deformation technique is valid in any dimension, subject to the choice of the basis function. We demonstrate this algorithm in 2D on illustrative images as well as on sagittal magnetic resonance images collected from a volunteer.

BACK

Page created & maintained by Frederic Leymarie, 1998-2003.
Comments, suggestions, etc., mail to: leymarie@lems.brown.edu