J. Dengler and M. Schmidt. The dynamic pyramid --- a model for motion analysis with controlled continuity. International Journal of Pattern Recognition and Artificial Intelligence, 2:275--286, 1988.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....data set is then segmented with a spatially varying classification [9, 12, 15] Segmentation of intraoperative data helps to establish explicitly the regions of tissues that correspond in the preoperative and intraoperative data. It is then straightforward to apply our previously described [16, 17] and validated [18] multi resolution elastic matching algorithm. Once the nonrigid transformation mapping from the preoperative to the intraoperative data has been established, the mapping is applied to each of the relevant preoperative data sets to bring them into alignment with the ....

J. Dengler and M. Schmidt, "The Dynamic Pyramid -- A Model for Motion Analysis with Controlled Continuity," International Journal of Pattern Recognition and Artificial Intelligence, vol. 2, no. 2, pp. 275--286, 1988.

....experimentally that brains were aligned more precisely when preceded with a global affine head registration. 4 Non linear Registration 3D Adaptive Template Matching We used 3D adaptive template matching to estimate a 3D volumetric deformation vector field based on the work of Dengler et al. [13]. Region based template matching defines a relative translation u(x) u(x) v(x) w(x) T between a voxel x in the atlas volume I 1 (x) and the patient volume I 2 (x) The best match is found by minimizing S(u(x) Z I2 W (x) Gamma I 2 (x) Gamma I 1 (x Gamma u(x) Delta 2 dx : 2) ....

J. Dengler and M. Schmidt. The dynamic pyramid - a model for motion analysis with controlled continuity. PRAI, 2(2):275--286, 1987.

....experimentally that brains were aligned more precisely when preceded with a global affine head registration. 4 Non linear Registration 3D Adaptive Template Matching We used 3D adaptive template matching to estimate a 3D volumetric deformation vector field based on the work of Dengler et al. [13]. Region based template matching defines a relative translation G = HI # J 6#LKM N)O between a voxel in the atlas volume and the patient volume . The best match is found by minimizing P G Q SR TVUXW 4 ZY[ Y ....

J. Dengler and M. Schmidt. The dynamic pyramid - a model for motion analysis with controlled continuity. PRAI, 2(2):275--286, 1987.

....of previously selected prototype voxels of known tissue type. The segmentation of the intraoperative data helps to establish explicitly the regions of tissues that correspond in the preoperative and intraoperative data. In the past we have described an imagebased nonrigid registration algorithm [22, 23] which has been successfully applied to capture shape variation in schizophrenia [24] However, our previous approach does not constitute an accurate biomechanical simulation of the deformation, and hence it is not possible to effectively model the different material properties of different ....

J. Dengler and M. Schmidt, "The Dynamic Pyramid -- A Model for Motion Analysis with Controlled Continuity," International Journal of Pattern Recognition and Artificial Intelligence, vol. 2, no. 2, pp. 275--286, 1988.

.... [1 3] This method, in conjunction with an elastic deformation model, is often chosen for its reliable behavior and accuracy as compared to simpler analogies such as mass spring models and others [4, 5] Previous work for recovering image deformation is mainly based on local image structure [6, 7]. These methods compute a deformation field between images simultaneously minimizing a local similarity measure and satisfying some kind of arbitrarily chosen smoothness constraint. They are often referred to as optical flow methods. Later, the image registration community proposed physical ....

J. Dengler and M. Schmidt. The Dynamic Pyramid - a Model for Motion Analysis with Controlled Continuity. International Journal of Pattern Recognition and Artificial Intelligence, 2:275--288, 1988.

....to represent complex deformation fields. Optimal values for these parameters must therefore be searched, to find parameter sets that globally minimize the measure of mismatch between the warped image and target. In several robust systems for automated brain image segmentation and labeling, Dengler and Schmidt (1988), Bajcsy and Kovacic (1989) Collins et al. 1994, 1995) Gee et al. 1993,1995) and Schormann et al. 1996) recover the optimal transformation in a hierarchical multi scale fashion. Both template and target intensity data are smoothed with different sized Gaussian filters, and the registration is ....

Dengler J, Schmidt M (1988). The Dynamic Pyramid - A Model for Motion Analysis with Controlled Continuity, Int. J. Patt. Recogn. and Artif. Intell. 2(2):275-286.

....a consequence of our left invariance requirement (eq. 11) In (13) the energy does not track the accumulated stress from time 0. For this reason, we classify the matching procedure as viscous matching (as first suggested by Rabbitt [5] in opposition to the methods involving elastic matching [2, 11, 9, 1, 19, 13, 20, 10, 6, 7]) From a point of view analogous to elasticity, it should be harder to make a small deformation of an object J if it is considered to already be a deformation of another object, than to operate the same deformation, but considering that J itself is at rest. Technically, this means that the norms ....

J. Dengler and M. Schmidt. The dynamic pyramid- a model for motion analysis with controlled continuity. International Journal of Pattern Recognition and Artificial Intelligence, pages 275--286, 2(2) 1988. 32 M. I. MILLER AND L. YOUNES

....penalty is limited by clamping the distance function. This limit is applied since we do not wish very distant structures to dominate the classification distance computation. 2.2.3. Nonlinear Registration We achieve fast nonlinear registration with an elastic matching algorithm based upon that of Dengler and Schmidt (1988), which is described below. The precise formulation of the nonlinear registration algorithm is not intrinsic to the ATM SVC algorithm, and it is possible to use other nonlinear registration algorithms (Bajcsy and Kovacic, 1989; Christensen et al. 1994; Thirion, 1998) We have used the method of ....

....which is described below. The precise formulation of the nonlinear registration algorithm is not intrinsic to the ATM SVC algorithm, and it is possible to use other nonlinear registration algorithms (Bajcsy and Kovacic, 1989; Christensen et al. 1994; Thirion, 1998) We have used the method of Dengler and Schmidt (1988) because it is sufficiently fast to be used routinely. The goal of the elastic matching algorithm is, given a source data set g 1 x and a target data set g 2 x , to find a deformation vector field u x such that the function g 1 x u x is as similar to the function g 2 ....

Dengler, J. and Schmidt, M., (1988). The Dynamic Pyramid -- A Model for Motion Analysis with Controlled Continuity. International Journal of Pattern Recognition and Artificial Intelligence, 2, 2, 275--286.

....differences. The techniques for automatically identifying these local shape differences usually estimate high order nonlinear transforms, often with elastic matching algorithms [3,8] A nine parameter registration is often a necessary first step before computing a high order nonlinear registration [9], since it allows the nonlinear registration optimization process to start from a position in which global shape differences have been identified. Interpatient registration has been used to determine global alignment prior to segmentation. We have developed a template driven segmentation approach ....

J. Dengler and M. Schmidt, "The Dynamic Pyramid -- A Model for Motion Analysis with Controlled Continuity," International Journal of Pattern Recognition and Artificial Intelligence, vol. 2, no. 2, pp. 275--286, 1988.

.... [1 3] This method, in conjunction with an elastic deformation model, is often chosen for its reliable behavior and accuracy as compared to simpler analogies such as mass spring models and others [4, 5] Previous work for recovering image deformation is mainly based on local image structure [6, 7]. These methods compute a deformation field between images simultaneously minimizing a local similarity measure and satisfying some kind of arbitrarily chosen smoothness constraint. They are often referred to as optical flow (OF) methods. Later, the image registration community proposed physical ....

J. Dengler and M. Schmidt. The Dynamic Pyramid - a Model for Motion Analysis with Controlled Continuity. International Journal of Pattern Recognition and Artificial Intelligence, 2:275--288, 1988.

....until saturating it. When better error bounds on the anatomical localization are known, they can be directly incorporated by modifying the penalty in the relevant regions. Nonlinear Registration We achieve fast nonlinear registration with an elastic matching algorithm based upon that of Dengler [10]. The goal of the matcher is, given a source data set g 1 (x) and a target data set g 2 (x) to find a deformation vector field u(x) such that the function g 1 (x Gamma u(x) is as similar to the function g 2 (x) as possible. The basic method of computing u is: for a fixed value of x, consider ....

Joachim Dengler and Markus Schmidt, "The Dynamic Pyramid -- A Model for Motion Analysis with Controlled Continuity", International Journal of Pattern Recognition and Artificial Intelligence, vol. 2, no. 2, pp. 275--286, 1988.

.... on one control subject, and projected it into other MRI scans by applying an elastic match (i.e. warping the atlas into the shape of the new brain image) The global registration technique that we used to match our anatomical MR atlas onto new MR images, is based on work by Dengler and coworkers [7], 22] 25] This technique builds on the theory of elastic membranes, and it is similar to Grenander s approach [13] The elastic membrane model can be intuitively understood as the deformations occurring when a set of points on the membrane is stretched. In this context, the atlas brain can be ....

....The subsequent linear transform was computed on those skin surfaces and then applied to the atlas brain. The final product was an atlas brain image linearly registered onto the patient brain image. Elastic Matching: We summarize here some technical details of Dengler s regularization procedure [7], 22] which we used to map 3D MR images onto each other. For a more detailed discussion on the mathematical model underlying the algorithm, please see the Appendix. The goal of the elastic matching algorithm was to find a 3D deformation vector field which transformed the source data set ....

[Article contains additional citation context not shown here]

Dengler J, Schmidt M. 1988. The Dynamic Pyramid - A Model for Motion Analysis with Controlled Continuity. International Journal of Pattern Recognition and Artificial Intelligence, 2:275-286.

No context found.

Dengler J, Schmidt M (1988) The Dynamic Pyramid -- A Model for Motion Analysis with Controlled Continuity. International Journal of Pattern Recognition and Artificial Intelligence 2(2):275--286.

....of physical bodies. This chapter is organized in the following manner. Section II is an overview of nonlinear registration techniques. Section III discusses our template driven segmentation approach and our elastic matching algorithm (which is based on the Dynamic Pyramid developed by Dengler (Dengler and Schmidt, 1988)) and Section IV presents some applications of the technique. II Nonlinear Registration Techniques Several methods of nonlinear registration, with varying degrees of generalizability, have been proposed. Each is suitable for certain types of applications. Matching schemes can encode anatomical ....

....the match accuracy. The contour representation was chosen to allow for easy manual manipulation, in order to readily account for abnormalities such as tumours, abscesses, strokes and hemorrhages. Several groups have proposed automatic elastic matching schemes for volumetric anatomical models (Dengler and Schmidt, 1988; Nagel, 1983; Collins et al. 1992; Bajcsy and Kovacic, 1989; Gee et al. 1992; Miller et al. 1993; Christensen et al. 1994) These matching techniques will be reviewed in detail below. Most of these techniques have been successfully applied to the matching of structures of normal brains. An ....

[Article contains additional citation context not shown here]

Dengler, J. and Schmidt, M. (1988). The Dynamic Pyramid -- A Model for Motion Analysis with Controlled Continuity. International Journal of Pattern Recognition and Artificial Intelligence, 2(2):275--286.

No context found.

J. Dengler and M. Schmidt. The dynamic pyramid --- a model for motion analysis with controlled continuity. International Journal of Pattern Recognition and Artificial Intelligence, 2:275--286, 1988.

No context found.

Dengler, J., Schmidt, M.: The Dynamic Pyramid -- A Model for Motion Analysis with Controlled Continuity. Int. J. Patt. Recogn. Artif. Intell. 2(2), 275--286 (1988)

No context found.

J. Dengler and M. Schmidt, "The Dynamic Pyramid -- A Model for Motion Analysis with Controlled Continuity," International Journal of Pattern Recognition and Artificial Intelligence, vol. 2, no. 2, pp. 275--286, 1988.

No context found.

J. Dengler and M. Schmidt, "The Dynamic Pyramid -- A Model for Motion Analysis with Controlled Continuity," International Journal of Pattern Recognition and Artificial Intelligence, vol. 2, no. 2, pp. 275--286, 1988.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC