Registration is a fundamental task in image processing used to match two or more pictures taken, for example, at different times, from different sensors or from different viewpoints. Over the years, a broad range of techniques have been developed for the various types of data and problems. These techniques have been independently studied for several different applications resulting in a large body of research. This paper organizes this material by establishing the relationship between the distortions in the image and the type of registration techniques which are most suitable. Two major types of distortions are distinguished. The first type are those which are the source of misregistration, i.e., they are the cause of the misalignment between the two images. Distortions which are the source of misregistration determine the transformation class which will optimally align the two images. The transformation class in turn influences the general technique that should be taken....

This paper presents diffeomorphic transformations of three-dimensional (3-D) anatomical image data of the macaque occipital lobe and whole brain cryosection imagery and of deep brain structures in human brains as imaged via magnetic resonance imagery. These transformations are generated in a hierarchical manner, accommodating both global and local anatomical detail. The initial low-dimensional registration is accomplished by constraining the transformation to be in a low-dimensional basis. The basis is defined by the Green's function of the elasticity operator placed at predefined locations in the anatomy and the eigenfunctions of the elasticity operator. The high-dimensional large deformations are vector fields generated via the mismatch between the template and target-image volumes constrained to be the solution of a Navier--Stokes fluid model. As part of this procedure, the Jacobian of the transformation is tracked, insuring the generation of diffeomorphisms. It is shown that transformations constrained by quadratic regularization methods such as the Laplacian, biharmonic, and linear elasticity models, do not ensure that the transformation maintains topology and, therefore, must only be used for coarse global registration.

This paper presents a new method for image registration based on jointly estimating the forward and reverse transformations between two images while constraining these transforms to be inverses of one another. This approach produces a consistent set of transformations that have less pairwise registration error, i.e., better correspondence, than traditional methods that estimate the forward and reverse transformations independently. The transformations are estimated iteratively and are restricted to preserve topology by constraining them to obey the laws of continuum mechanics. The transformations are parameterized by a Fourier series to diagonalize the covariance structure imposed by the continuum mechanics constraints and to provide a computationally efficient numerical implementation. Results using a linear elastic material constraint are presented using both magnetic resonance and X-ray computed tomography image data. The results show that the joint estimation of a consistent set of forward and reverse transformations constrained by linear-elasticity give better registration results than using either constraint alone or none at all.

Medical imaging modalities, such as magnetic resonance (MR), histological images, and positron emission tomography (PET), enable study of anatomy and function in animals and humans. The technology to collect such data greatly exceeds tools to analyze it. This research seeks to address this issue by developing methods that automatically synthesize labeled electronic atlases tailored to individuals. The approach

Two new consistent image registration algorithms are presented: one is based on matching corresponding landmarks and the other is based on matching both landmark and intensity information. The consistent landmark and intensity registration algorithm produces good correspondences between images near landmark locations by matching corresponding landmarks and away from landmark locations by matching the image intensities. In contrast to similar unidirectional algorithms, these new consistent algorithms jointly estimate the forward and reverse transformation between two images while minimizing the inverse consistency error -- the error between the forward (reverse) transformation and the inverse of the the reverse (forward) transformation. This reduces the ambiguous correspondence between the forward and reverse transformations associated with large inverse consistency errors. In both algorithms a thin-plate spline (TPS) model is used to regularize the estimated transformations. Two-dimensional (2-D) examples are presented that show the inverse consistency error produced by the traditional unidirectional landmark TPS algorithm can be relatively large and that this error is minimized using the consistent landmark algorithm. Results using 2-D magnetic resonance imaging data are presented that demonstrate that using landmark and intensity information together produce better correspondence between medical images than using either landmarks or intensity information alone.

. Image matching has emerged as an important area of investigation in medical image analysis. In particular, much attention has been focused on the atlas problem, in which a template representing the structural anatomy of the human brain is deformed to match anatomic brain images from a given individual. The problem is made difficult because there are important differences in both the gross and local morphology of the brain among normal individuals. We have formulated the image matching problem under a Bayesian framework. The Bayesian methodology facilitates a principled approach to the development of a matching model. Of special interest is its capacity to deal with uncertainty in the estimates, a potentially important but generally ignored aspect of the solution. In the construction of a reference system for the human brain, the Bayesian approach is well suited to the task of modeling variation in morphology. Statistical information about morphological variability, accumulated over p...

Introduction The ever expanding gamut of medical imaging techniques provides the clinician an increasingly multifaceted view of brain function and anatomy. The information provided by the various imaging modalities is often complementary (i.e. provides separate but useful information) and synergistic (i.e. the combination of information provides useful extra information). For example, X-ray computed tomography (CT) and magnetic resonance (MR) imaging exquisitely demonstrate brain anatomy but provide little functional information. Positron emission tomography (PET) and single photon emission computed tomography (SPECT) scans display aspects of brain function and allow metabolic measurements but poorly delineate anatomy. Furthermore, CT and MR images describe complementary morphologic features. For example, bone and calcifications are best seen on CT images, while soft-tissue structures are better differentiated by MR imaging. Clinical diagnosis and therapy planning and evaluatio

The application of image matching to the problem of localizing structural anatomy in images of the human brain forms the specific aim of our work. The interpretation of such images is a difficult task for human observers because of the many ways in which the identity of a given structure can be obscured. Our approach is based on the assumption that a common topology underlies the anatomy of normal individuals. To the degree that this assumption holds, the localization problem can be solved by determining the mapping from the anatomy of a given individual to some referential atlas of cerebral anatomy. Previous such approaches have in many cases relied on a physical interpretation of this mapping. In this paper, we examine a more general Bayesian formulation of the image matching problem and demonstrate the approach on two-dimensional magnetic resonance images.

A high-level approach to describe the characteristics of a surface is to segment it into regions of uniform curvature behavior and construct an abstract representation given by a (topology) graph. We propose a surface segmentation method based on discrete mean and Gaussian curvature estimates. The surfaces are obtained from three-dimensional imaging data sets by isosurface extraction after data presmoothing and postprocessing the isosurfaces by a surface-growing algorithm. We generate a hierarchical multiresolution representation of the isosurface. Segmentation and graph generation algorithms can be performed at various levels of detail. At a coarse level of detail, the algorithm detects the main features of the surface. This low-resolution description is used to determine constraints for the segmentation and graph generation at the higher resolutions. We have applied our methods to MRI data sets of human brains. The hierarchical segmentation framework can be used for brainmapping purposes.

To evaluate our system for elastically deforming a three-dimensional atlas to match anatomical brain images, six deformed versions of an atlas were generated. The deformed atlases were created by elastically mapping an anatomical brain atlas onto different MRI brain image volumes. The mapping matches the edges of the ventricles and the surface of the brain; the resultant deformations are propagated through the atlas volume, deforming the remainder of the structures in the process. The atlas was then elastically matched to its deformed versions. The accuracy of the resultant matches was evaluated by determining the correspondence of 32 cortical and subcortical structures. The system on average matched the centroid of a structure to within 1 mm of its true position and fit a structure to within 11% of its true volume. The overlap between the matched and true structures, defined by the ratio between the volume of their intersection and the volume of their union, averaged 66%. When the gra...