Abstract — A new approach to the problem of multimodality medical image registration is proposed, using a basic concept from information theory, mutual information (MI), or relative entropy, as a new matching criterion. The method presented in this paper applies MI to measure the statistical dependence or information redundancy between the image intensities of corresponding voxels in both images, which is assumed to be maximal if the images are geometrically aligned. Maximization of MI is a very general and powerful criterion, because no assumptions are made regarding the nature of this dependence and no limiting constraints are imposed on the image content of the modalities involved. The accuracy of the MI criterion is validated for rigid body registration of computed tomography (CT), magnetic resonance (MR), and photon emission tomography (PET) images by comparison with the stereotactic registration solution, while robustness is evaluated with respect to implementation issues, such as interpolation and optimization, and image content, including partial overlap and image degradation. Our results demonstrate that subvoxel accuracy with respect to the stereotactic reference solution can be achieved completely automatically and without any prior segmentation, feature extraction, or other preprocessing steps which makes this method very well suited for clinical applications. Index Terms—Matching criterion, multimodality images, mutual information, registration. I.

The purpose of this chapter is to present a survey of recent 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 either based on segmented points or surfaces, or on techniques endeavoring to use the full information content of the images involved. Keywords: registration, matching Received May 25, 1997

A robust fully automatic method for segmenting the brain from head MR images has been developed, which works even in the presence of RF inhomogeneities. It has been successful in segmenting the brain in every slice from head images acquired from several different MRI scanners, using different resolution images and different echo sequences. The method uses an integrated approach which employs image processing techniques based on anisotropic filters and "snakes" contouring techniques, and a-priori knowledge, which is used to remove the eyes, which are tricky to remove based on image intensity alone. It is a multi-stage process, involving first removal of the background noise leaving a head mask, then finding a rough outline of the brain, then refinement of the rough brain outline to a final mask. The paper describes the main features of the method, and gives results for some brain studies. Keywords: Magnetic Resonance Imaging, Intracranial Boundary Detection, Nonlinear Anisotropic Dif...

Abstract—Ridges and valleys are useful geometric features for image analysis. Different characterizations have been proposed to formalize the intuitive notion of ridge/valley. In this paper, we review their principal characterizations and propose a new one. Subsequently, we evaluate these characterizations with respect to a list of desirable properties and their purpose in the context of representative image analysis tasks. Index Terms—Creases, separatrices, drainage patterns, comparative analysis. ————————— — F ——————————

Registration of 3D medical images consists in computing the “best” transformation between two acquisitions, or equivalently, determines the point to point correspondence between the images. Registration algorithms are usually based either on features extracted from the image (feature-based approaches) or on the optimization of a similarity measure of the images intensities (intensitybased or iconic approaches). Another classification criterion is the type of transformation sought (e.g. rigid or non-rigid). In this chapter, we concentrate on feature-based approaches for rigid registration, similar approaches for non-rigid registration being reported in another set of publication [35, 36]. We show how to reduce the dimension of the registration problem by first extracting a surface from the 3D image, then landmark curves on this surface and possibly landmark points on these curves. This concept proved its efficiency through many applications in medical image analysis as we will see in the sequel. This work has been for a long time a central investigation topic of the Epidaure team [2] and we can only reflect here on a small part of the research done in this area. We present in the first section the notions of crest lines and extremal points and how these differential geometry features can be extracted from 3D images. In Section 2, we focus on the different rigid registration algorithms that we used to register such features. The last section analyzes the possible errors in this registration scheme and demonstrates that a very accurate registration could be achieved.

One of the most promising applications of 3-D ultrasound lies in the visualisation and volume estimation of internal 3-D structures. Unfortunately, the quality of the ultrasound data can be severely degraded by artifacts and speckle, making automatic analysis of the 3-D data sets very difficult. In this paper we investigate the use of 3-D spatial compounding to improve the quality of the ultrasound data. This involves imaging the region of interest repeatedly from a variety of insonation angles, and averaging the resulting data sets. For accurate compounding, it is important to register the multiple data sets precisely. We show how state-of-the-art techniques, developed elsewhere for multimodal CT to MRI registration, are equally successful with 3-D ultrasound. Results are based on in-vivo examinations of a human gall bladder, demonstrating clearly the superiority of the compounded data. In particular, it is possible to visualise and segment the compounded data using standard software...

A parameter-free approach for non-rigid image registration based on elasticity theory is presented. In contrast to traditional physically-based numerical registration methods, no forces have to be computed from image data to drive the elastic deformation. Instead, displacements obtained with the help of mapping boundary structures in the source and target image are incorporated as hard constraints into elastic image deformation. As a consequence, our approach does not contain any parameters of the deformation model such as elastic constants. The approach guarantees the exact correspondence of boundary structures in the images assuming that correct input data are available. The implemented incremental method allows to cope with large deformations. The theoretical background, the finite element discretization of the elastic model, and experimental results for 2-D and 3-D synthetic as well as real medical images are presented.

Abstract. We developed an automated system that registers chest CT images temporally. Our registration method matches corresponding anatomical landmarks to obtain initial registration parameters. The initial point-to-point registration is then generalized to an iterative surface-tosurface registration method. Our “goodness-of-fit ” measure is evaluated at each step in the iterative scheme until the registration performance is sufficient. We applied our method to register the 3D lung surfaces of 10 pairs of chest CT scans and report a promising registration performance. 1 1

Multimodal medical images are often of too different a nature to be registered on the basis of the image grey values only. It is the purpose of this paper to construct operators that extract similar structures from these images that will enable registration by simple grey value based methods, such as maximization of cross-correlation. These operators can be constructed using only basic morphological tools such as erosion and dilation. Simple versions of these operators are easily implemented on any computer system. We will show that accurate registration of images of various modalities (MR, CT, SPECT and PET) can be obtained using this approach.

. Creases are a type of ridge/valley--like structures of a d dimensional image, characterized by local conditions. As creases tend to be at the center of anisotropic grey--level shapes, creaseness can be considered as a type of medialness. Among the several crease definitions, one of the most important is based on the extrema of the level set curvatures. In 2--d it is used the curvature of the level curves of the image landscape, however, the way it is usually computed produces a discontinuous creaseness measure. The same problem arises in 3--d with its straightforward extension and with other related creaseness measures. In this paper, we first present an alternative method of computing the level curve curvature that avoids the discontinuities. Next, we propose the Mean curvature of the level surfaces as creaseness measure of 3--d images, computed by the same method. Finally, we propose a natural extension of our first alternative method in order to enhance the creaseness...