#### DMCA

## Fast parametric elastic image registration (2003)

Venue: | IEEE Transactions on Image Processing |

Citations: | 102 - 8 self |

### Citations

3137 |
A wavelet tour of signal processing
- Mallat
- 1998
(Show Context)
Citation Context ..., where denotes the scale. This makes the Fourier spectrum of the displacement decrease as required over the whole frequency range and ensures that the (mean) displacement belong to the Sobolev space =-=[63]-=-. To obtain corresponding 2-D deformation fields, we use separable 2-D wavelet transforms with the same basis functions and the same decrease of amplitude of the coefficients in each component as in t... |

962 | A survey of image registration techniques
- Brown
- 1992
(Show Context)
Citation Context ... landmarks, splines. I. INTRODUCTION IMAGE registration is the task of finding a correspondence function mapping coordinates from a reference image to coordinates of homologous points in a test image =-=[1]-=-. We call the registration elastic [2] if the family of correspondence functions is sufficiently general, capable of expressing essentially arbitrary nonlinear relations. 1 Image registration is appli... |

952 |
Principal warps : Thin-plate splines and the decomposition of deformations
- Bookstein
- 1989
(Show Context)
Citation Context ...gistration, targeted to more difficult registration problems. We ask an expert to identify a small number of corresponding points in both images. The points are also called landmarks [3], [12], [39], =-=[40]-=-. We add a term to the data part of the criterion, to steer the algorithm toward the correct solution indicated by the landmarks. B. Organization of This Article In Section II, we describe the concept... |

769 | Multimodality image registration by maximization of mutual information
- Maes, Collignon, et al.
- 1997
(Show Context)
Citation Context ... registering the images and aligning them by warping using the correspondence function identified. Applications include intra-subject [12], inter-subject [13], [14], and inter-modality analysis [15], =-=[16]-=-, [17], registration with annotated atlases [18], [19], quantification and qualification of feature shapes and sizes [20], distortion compensation [21], [22] and motion detection [23], [24] and compen... |

395 |
Morphometric Tools for Landmark Data: Geometry and Biology
- Bookstein
- 1991
(Show Context)
Citation Context ...hnology Lausanne, CH-1015 Lausanne EPFL, Switzerland. Digital Object Identifier 10.1109/TIP.2003.813139 1 Note that elasticity is used here in a wider sense than just the mechanical linear elasticity =-=[3]-=-. 1057-7149/03$17.00 © 2003 IEEE Various nonlinear registration algorithms for brain warping applications are presented by Warfield et al. [9]. Bayesian interpretation of elastic matching was reviewed... |

370 | Splines - a perfect fit for signal and image processing
- Unser
- 1999
(Show Context)
Citation Context ... a priori information and a regularization term; extra regularization can be applied [44] if desired. III. DEFORMATION BASIS The purpose of this section is to motivate our choice of (cubic) B-splines =-=[42]-=- as the most adequate basis functions to represent the deformation in model (3). The alternative possibilities that come to mind are polynomials [45], harmonic functions [18], [46], radial basis funct... |

346 |
Multiresolution elastic matching
- Bajcsy, Kovacic
- 1989
(Show Context)
Citation Context ...MAGE registration is the task of finding a correspondence function mapping coordinates from a reference image to coordinates of homologous points in a test image [1]. We call the registration elastic =-=[2]-=- if the family of correspondence functions is sufficiently general, capable of expressing essentially arbitrary nonlinear relations. 1 Image registration is applied in the areas of motion analysis [4]... |

304 | Nonlinear spatial normalization using basis functions
- Ashburner, Friston
- 1999
(Show Context)
Citation Context ...ping using the correspondence function identified. Applications include intra-subject [12], inter-subject [13], [14], and inter-modality analysis [15], [16], [17], registration with annotated atlases =-=[18]-=-, [19], quantification and qualification of feature shapes and sizes [20], distortion compensation [21], [22] and motion detection [23], [24] and compensation [25]. Manuscript received September 6, 20... |

245 |
Wavelet analysis and synthesis of fractional brownian motion
- Flandrin
- 1992
(Show Context)
Citation Context ...teed if the Fourier transform decreases asymptotically at least as . We express the random displacement in an orthogonal wavelet basis. We use orthonormal symmetric fractional B-spline wavelets [61], =-=[62]-=- of degree , which have precisely the desired regularity and Fourier decay at infinity. We let the wavelet coefficients be random (zero mean, independent, and normally distributed) with standard devia... |

227 | Variational principles, surface evolution, PDE’s, level set methods, and the stereo problem
- Faugeras, Keriven
- 1998
(Show Context)
Citation Context ...s of motion analysis [4]–[6], video compression and coding [7], object tracking [8], or image stabilization. It leads to algorithms for segmentation [9], depth reconstruction from stereo images [10], =-=[11]-=-, and for general 3-D reconstruction. In the biomedical domain, there is a frequent need for comparing images for analysis and diagnostic purposes. This is accomplished by registering the images and a... |

225 | A pyramid approach to subpixel registration based on intensity
- Thevenaz, Unser
- 1998
(Show Context)
Citation Context ...best. This is because its higher cost per iteration is compensated for by a smaller number of iterations due to the quadratic convergence. An example of such a situation is shown in Fig. 3. (See also =-=[57]-=-.) Among Marquardt–Levenberg (ML) algorithms, we found the performance to be superior when using the full Hessian.sKYBIC AND UNSER: FAST PARAMETRIC ELASTIC IMAGE REGISTRATION 1431 B. Multiresolution A... |

222 |
The Theory of Splines and Their Applications
- Ahlberg, Nilson, et al.
- 1967
(Show Context)
Citation Context ... only multiplications per pixel. The B-spline model has good approximation properties and is fast to evaluate. It is physically plausible, for example cubic splines minimize the ‘strain energy’ [55], =-=[56]-=-. It can encode all affine transformations, including rigid body motion. (4)s1430 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 12, NO. 11, NOVEMBER 2003 Moreover, B-splines are scalable in the sense th... |

156 | Consistent image registration - Christensen, Johnson - 2001 |

155 | Hierarchical spline-based image registration
- Szeliski, Coughlan
- 1994
(Show Context)
Citation Context ...e areas of motion analysis [4]–[6], video compression and coding [7], object tracking [8], or image stabilization. It leads to algorithms for segmentation [9], depth reconstruction from stereo images =-=[10]-=-, [11], and for general 3-D reconstruction. In the biomedical domain, there is a frequent need for comparing images for analysis and diagnostic purposes. This is accomplished by registering the images... |

143 | Optimization of mutual information for multiresolution image registration
- Thevenaz, Unser
- 2000
(Show Context)
Citation Context ...tering the images and aligning them by warping using the correspondence function identified. Applications include intra-subject [12], inter-subject [13], [14], and inter-modality analysis [15], [16], =-=[17]-=-, registration with annotated atlases [18], [19], quantification and qualification of feature shapes and sizes [20], distortion compensation [21], [22] and motion detection [23], [24] and compensation... |

137 | Volumetric transformations of brain anatomy
- Christensen, Joshi, et al.
- 1997
(Show Context)
Citation Context ... can be formulated as variational, defining a scalar criterion that completely determines the final solution [2]. More generally, they can be also expressed using partial differential equations (PDE) =-=[29]-=-–[32]. The presented algorithm belongs to a second group of methods that use parametric models, representing the deformation by a moderate number of parameters, often in the multiscale setting. Specif... |

126 |
Computation and analysis of image motion: a synopsis of current problems and methods
- Mitchie, Bouthemy
- 1996
(Show Context)
Citation Context ...[2] if the family of correspondence functions is sufficiently general, capable of expressing essentially arbitrary nonlinear relations. 1 Image registration is applied in the areas of motion analysis =-=[4]-=-–[6], video compression and coding [7], object tracking [8], or image stabilization. It leads to algorithms for segmentation [9], depth reconstruction from stereo images [10], [11], and for general 3-... |

112 |
An implementation of the fast multipole method without multipoles
- Anderson
- 1992
(Show Context)
Citation Context ...force evaluation is slow due to their long support. As for the radial basis functions, although there are algorithms with reduced asymptotical complexity for evaluation of radial basis functions [50]–=-=[53]-=-, their overhead is still nonnegligible. We decided against the harmonic (Fourier) basis functions because of their lack of localization (the fact that any two of them overlap). Another argument again... |

109 |
A survey of hierarchical non-linear medical image registration. Pattern Recognition, 32:129–149. Bibliography 300
- Lester, Arridge
- 1999
(Show Context)
Citation Context ... Articles by Van den Elsen et al. [26] and Maintz and Viergever [27] contain a very comprehensive and detailed classification of available methods for medical imaging applications. Lester and Arridge =-=[28]-=- treat the hierarchical aspects of the algorithms. The deformation models of elastic registration algorithms fall into two basic categories. The first type are nonparametric, local methods—the deforma... |

106 |
Image registration by maximization of combined mutual information and gradient information
- Pluim, Maintz, et al.
- 2000
(Show Context)
Citation Context ...pass filtering and histogram normalization [22]. In principle, there is no difficulty in extending our method for more sophisticated pixelbased similarity measures, such as information-based measures =-=[41]-=-, especially mutual information [17], or weighted norms. Only the evaluation of the criterion and its derivatives (gradient) needs to be changed. 2 In the multimodal case, which we are not considering... |

103 |
Multiscale minimization of global energy functions in some visual recovery problems,” CVGIP
- Heitz, Perez, et al.
- 1994
(Show Context)
Citation Context ...by a moderate number of parameters, often in the multiscale setting. Specific examples include hierarchical basis functions by Moulin et al. [7], quadtree-splines [5], multiresolution subspaces [33], =-=[34]-=-, and wavelets [35], [36]. Splines are well suited for this kind of problems; they have appeared in various incarnations. In this paper we use a multiresolution B-spline representation, as was initial... |

96 |
Viergever, “A survey of medical image registration,” Med
- Maintz, A
- 1998
(Show Context)
Citation Context ...by Warfield et al. [9]. Bayesian interpretation of elastic matching was reviewed by Gee [19], also in the context of human neuroanatomy. Articles by Van den Elsen et al. [26] and Maintz and Viergever =-=[27]-=- contain a very comprehensive and detailed classification of available methods for medical imaging applications. Lester and Arridge [28] treat the hierarchical aspects of the algorithms. The deformati... |

94 |
Fractional splines and wavelets
- Unser, Blu
- 2000
(Show Context)
Citation Context ...guaranteed if the Fourier transform decreases asymptotically at least as . We express the random displacement in an orthogonal wavelet basis. We use orthonormal symmetric fractional B-spline wavelets =-=[61]-=-, [62] of degree , which have precisely the desired regularity and Fourier decay at infinity. We let the wavelet coefficients be random (zero mean, independent, and normally distributed) with standard... |

87 |
Variational methods for multi-modal image matching
- Hermosillo
- 2002
(Show Context)
Citation Context ...be formulated as variational, defining a scalar criterion that completely determines the final solution [2]. More generally, they can be also expressed using partial differential equations (PDE) [29]–=-=[32]-=-. The presented algorithm belongs to a second group of methods that use parametric models, representing the deformation by a moderate number of parameters, often in the multiscale setting. Specific ex... |

74 |
A family of polynomial spline wavelet transforms
- Unser, Aldroubi, et al.
- 1993
(Show Context)
Citation Context ...e basis are therefore B-splines and B-spline wavelets. A. Splines Versus Wavelets To make a fair comparison between B-spline and wavelet bases, we consider compactly supported cubic B-spline wavelets =-=[54]-=- spanning the same cubic spline space. First, let us analyze the task of evaluating the deformation at a single point. For simplicity, we will work in 1-D. There are only four participating B-splines ... |

70 | F.: A non-linear variational problem for image matching
- Amit, Let
- 1994
(Show Context)
Citation Context ...ns to represent the deformation in model (3). The alternative possibilities that come to mind are polynomials [45], harmonic functions [18], [46], radial basis functions [3], [47], and wavelets [35], =-=[48]-=-, [49]. It is highly desirable to have as few basis functions as possible to contribute to each particular point, while keeping the 3 Uniform symmetric B-splines [42] of degree � are piecewise polynom... |

63 | Point-based elastic registration of medical image data using approximating thin-plate splines
- Rohr, Stiehl, et al.
- 1996
(Show Context)
Citation Context ...tic registration, targeted to more difficult registration problems. We ask an expert to identify a small number of corresponding points in both images. The points are also called landmarks [3], [12], =-=[39]-=-, [40]. We add a term to the data part of the criterion, to steer the algorithm toward the correct solution indicated by the landmarks. B. Organization of This Article In Section II, we describe the c... |

62 | Motion estimation with quadtree splines
- Szeliski, Shum
- 1996
(Show Context)
Citation Context ...models, representing the deformation by a moderate number of parameters, often in the multiscale setting. Specific examples include hierarchical basis functions by Moulin et al. [7], quadtree-splines =-=[5]-=-, multiresolution subspaces [33], [34], and wavelets [35], [36]. Splines are well suited for this kind of problems; they have appeared in various incarnations. In this paper we use a multiresolution B... |

54 | Fast evaluation of radial basis functions - Beatson, Newsam - 1992 |

48 |
The l2 polynomial spline pyramid
- Unser, Aldroubi, et al.
- 1993
(Show Context)
Citation Context ...nsion and reduction operators. We will use the same approach for both the deformation model and the image model. The expansion can be performed exactly; we choose to do optimal reduction in the sense =-=[60]-=-. Both expansions and reductions can be performed efficiently using FIR and recursive IIR filters. To cope with the finite extent of our signals, we put extra B-splines outside the interval of interes... |

44 | Characterization of neuropathological shape deformations
- Martin, Pentland, et al.
- 1998
(Show Context)
Citation Context ...ntra-subject [12], inter-subject [13], [14], and inter-modality analysis [15], [16], [17], registration with annotated atlases [18], [19], quantification and qualification of feature shapes and sizes =-=[20]-=-, distortion compensation [21], [22] and motion detection [23], [24] and compensation [25]. Manuscript received September 6, 2001; revised February 12, 2003. The associate editor coordinating the revi... |

40 |
Voxel-based 2-D/3-D registration of fluoroscopy images and CT scans for image-guided surgery
- Weese, Penney, et al.
- 1997
(Show Context)
Citation Context ...ly general, capable of expressing essentially arbitrary nonlinear relations. 1 Image registration is applied in the areas of motion analysis [4]–[6], video compression and coding [7], object tracking =-=[8]-=-, or image stabilization. It leads to algorithms for segmentation [9], depth reconstruction from stereo images [10], [11], and for general 3-D reconstruction. In the biomedical domain, there is a freq... |

40 | Unwarping of unidirectionally distorted EPI images
- Kybic, Thevenaz, et al.
- 2000
(Show Context)
Citation Context ...], [14], and inter-modality analysis [15], [16], [17], registration with annotated atlases [18], [19], quantification and qualification of feature shapes and sizes [20], distortion compensation [21], =-=[22]-=- and motion detection [23], [24] and compensation [25]. Manuscript received September 6, 2001; revised February 12, 2003. The associate editor coordinating the review of this manuscript and approving ... |

34 |
Image registration using wavelet-based motion model
- Wu, Kanade, et al.
- 2000
(Show Context)
Citation Context ...arameters, often in the multiscale setting. Specific examples include hierarchical basis functions by Moulin et al. [7], quadtree-splines [5], multiresolution subspaces [33], [34], and wavelets [35], =-=[36]-=-. Splines are well suited for this kind of problems; they have appeared in various incarnations. In this paper we use a multiresolution B-spline representation, as was initially suggested in the pione... |

31 | On matching brain volumes
- Gee
- 1999
(Show Context)
Citation Context ...sing the correspondence function identified. Applications include intra-subject [12], inter-subject [13], [14], and inter-modality analysis [15], [16], [17], registration with annotated atlases [18], =-=[19]-=-, quantification and qualification of feature shapes and sizes [20], distortion compensation [21], [22] and motion detection [23], [24] and compensation [25]. Manuscript received September 6, 2001; re... |

26 | Multiscale modeling and estimation of motion fields for video coding
- Moulin, Krishnamurthy, et al.
- 1997
(Show Context)
Citation Context ...nctions is sufficiently general, capable of expressing essentially arbitrary nonlinear relations. 1 Image registration is applied in the areas of motion analysis [4]–[6], video compression and coding =-=[7]-=-, object tracking [8], or image stabilization. It leads to algorithms for segmentation [9], depth reconstruction from stereo images [10], [11], and for general 3-D reconstruction. In the biomedical do... |

26 |
Two methods for calculating regional cerebral blood flow from emission computed tomography of inert gas concentrations. J Comput Assist Tomogr 1979;3 : 71-76 11
- Kanno, NA
(Show Context)
Citation Context ...eriments With Real Data We applied our algorithm to various problems involving medical images of several modalities. We developed a registration procedure for ECDf10 and Xenon inhalation SPECT images =-=[64]-=- in the view of atlas creation [37]. Fig. 17 shows the resulting alignment obtained after registering two slices of anatomical (spin-echo) MRI images of two different subjects. 11 To further illustrat... |

25 | Large deformation fluid diffeomorphisms for landmark and image matching - Miller, Joshi, et al. - 1999 |

24 | Feature-adaptive motion tracking of ultrasound image sequences using a deformable mesh - Yeung, Levinson, et al. - 1998 |

19 |
Topology preserving deformable image matching using constrained hierarchical parametric models
- Musse, Heitz, et al.
(Show Context)
Citation Context ...ation by a moderate number of parameters, often in the multiscale setting. Specific examples include hierarchical basis functions by Moulin et al. [7], quadtree-splines [5], multiresolution subspaces =-=[33]-=-, [34], and wavelets [35], [36]. Splines are well suited for this kind of problems; they have appeared in various incarnations. In this paper we use a multiresolution B-spline representation, as was i... |

18 | A new approach for nonlinear distortion correction in endoscopic images based on least squares estimation
- Asari, Kumar, et al.
- 1999
(Show Context)
Citation Context ...ct [13], [14], and inter-modality analysis [15], [16], [17], registration with annotated atlases [18], [19], quantification and qualification of feature shapes and sizes [20], distortion compensation =-=[21]-=-, [22] and motion detection [23], [24] and compensation [25]. Manuscript received September 6, 2001; revised February 12, 2003. The associate editor coordinating the review of this manuscript and appr... |

18 | Elastic registration of medical images using radial basis functions with compact support
- Fornefett, Rohr, et al.
- 1999
(Show Context)
Citation Context ...st adequate basis functions to represent the deformation in model (3). The alternative possibilities that come to mind are polynomials [45], harmonic functions [18], [46], radial basis functions [3], =-=[47]-=-, and wavelets [35], [48], [49]. It is highly desirable to have as few basis functions as possible to contribute to each particular point, while keeping the 3 Uniform symmetric B-splines [42] of degre... |

17 |
Left ventricular motion reconstruction based on elastic vector splines
- Suter, Chen
- 2000
(Show Context)
Citation Context ...ysis [15], [16], [17], registration with annotated atlases [18], [19], quantification and qualification of feature shapes and sizes [20], distortion compensation [21], [22] and motion detection [23], =-=[24]-=- and compensation [25]. Manuscript received September 6, 2001; revised February 12, 2003. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Patri... |

14 | Cardiac motion analysis from ultrasound sequences using non-rigid registration
- Ledesma-Carbayo, Kybic, et al.
(Show Context)
Citation Context ...ing this field also permits the determination of the velocity and derived parameters, such as the accumulated displacement, and strain. We also analyzed standard 2-D ultrasound sequences of the heart =-=[65]-=-. The algorithm proved to be robust to the occasional change of structure (topology) due to the underlying 3-D nature of the true movement. 13 Another technique for assessing cardiac performance is my... |

13 | 2000 Multidimensional elastic registration of images using splines
- Kybic, Unser
(Show Context)
Citation Context ...mage and the deformation, a double multiresolution strategy (for both the image and the deformation), a scalar pixel-based difference measure, and an iterative multidimensional optimization algorithm =-=[37]-=-, [38]. The deformation model has been generalized and the whole algorithm re-engineered for faster execution. Second, we present the idea of semi-automatic registration, targeted to more difficult re... |

13 |
Spline functions and the problem of graduation, Proc
- Schoenberg
- 1964
(Show Context)
Citation Context ...ost of only multiplications per pixel. The B-spline model has good approximation properties and is fast to evaluate. It is physically plausible, for example cubic splines minimize the ‘strain energy’ =-=[55]-=-, [56]. It can encode all affine transformations, including rigid body motion. (4)s1430 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 12, NO. 11, NOVEMBER 2003 Moreover, B-splines are scalable in the se... |

12 |
Surface-based matching using elastic transformations. Pattern Recogni tion
- Gabrani, Tretiak
- 1999
(Show Context)
Citation Context ...d diagnostic purposes. This is accomplished by registering the images and aligning them by warping using the correspondence function identified. Applications include intra-subject [12], inter-subject =-=[13]-=-, [14], and inter-modality analysis [15], [16], [17], registration with annotated atlases [18], [19], quantification and qualification of feature shapes and sizes [20], distortion compensation [21], [... |

12 |
Robust voxel similarity metric for the registration of dissimilar single and multimodal images, Pattern Recognition 32
- Nikou, Heitz, et al.
- 1999
(Show Context)
Citation Context ...hed by registering the images and aligning them by warping using the correspondence function identified. Applications include intra-subject [12], inter-subject [13], [14], and inter-modality analysis =-=[15]-=-, [16], [17], registration with annotated atlases [18], [19], quantification and qualification of feature shapes and sizes [20], distortion compensation [21], [22] and motion detection [23], [24] and ... |

10 |
Spatio-temporal energy-based method for velocity estimation
- Spinei, Pellerin, et al.
- 1998
(Show Context)
Citation Context ...if the family of correspondence functions is sufficiently general, capable of expressing essentially arbitrary nonlinear relations. 1 Image registration is applied in the areas of motion analysis [4]–=-=[6]-=-, video compression and coding [7], object tracking [8], or image stabilization. It leads to algorithms for segmentation [9], depth reconstruction from stereo images [10], [11], and for general 3-D re... |

8 |
MRI and PET coregistration—a cross validation of statistical parametric mapping and automated image registration
- Kiebel, Ashburner, et al.
- 1997
(Show Context)
Citation Context ...f (cubic) B-splines [42] as the most adequate basis functions to represent the deformation in model (3). The alternative possibilities that come to mind are polynomials [45], harmonic functions [18], =-=[46]-=-, radial basis functions [3], [47], and wavelets [35], [48], [49]. It is highly desirable to have as few basis functions as possible to contribute to each particular point, while keeping the 3 Uniform... |

6 |
Nonlinear registration and template-driven segmentation
- Warfield, Robatino, et al.
- 1999
(Show Context)
Citation Context ...ations. 1 Image registration is applied in the areas of motion analysis [4]–[6], video compression and coding [7], object tracking [8], or image stabilization. It leads to algorithms for segmentation =-=[9]-=-, depth reconstruction from stereo images [10], [11], and for general 3-D reconstruction. In the biomedical domain, there is a frequent need for comparing images for analysis and diagnostic purposes. ... |

6 |
Automated image registration using a 105 parameter non-linear model
- Sicotte, Woods, et al.
- 1996
(Show Context)
Citation Context ...ion is to motivate our choice of (cubic) B-splines [42] as the most adequate basis functions to represent the deformation in model (3). The alternative possibilities that come to mind are polynomials =-=[45]-=-, harmonic functions [18], [46], radial basis functions [3], [47], and wavelets [35], [48], [49]. It is highly desirable to have as few basis functions as possible to contribute to each particular poi... |

6 | Cooperation between local and global approaches to register brain images
- Hellier, Barillot
(Show Context)
Citation Context ...the algorithm toward the correct solution. The idea of a hybrid registration algorithm combining both local features (points or lines) with global ones (intensities) has appeared for example in [58], =-=[59]-=- 6 and others. However, as both [58], [59] use essentially local, nonparametric deformation models, the landmark constraints need to be first interpolated everywhere to serve as an a priori deformatio... |

4 |
image matching—A review with classification
- A
- 1993
(Show Context)
Citation Context ...ng applications are presented by Warfield et al. [9]. Bayesian interpretation of elastic matching was reviewed by Gee [19], also in the context of human neuroanatomy. Articles by Van den Elsen et al. =-=[26]-=- and Maintz and Viergever [27] contain a very comprehensive and detailed classification of available methods for medical imaging applications. Lester and Arridge [28] treat the hierarchical aspects of... |

4 |
Removal of normal anatomic structures in radiographs using waveletbased nonlinear variational method for image matching
- Yoshida
- 1998
(Show Context)
Citation Context ...r of parameters, often in the multiscale setting. Specific examples include hierarchical basis functions by Moulin et al. [7], quadtree-splines [5], multiresolution subspaces [33], [34], and wavelets =-=[35]-=-, [36]. Splines are well suited for this kind of problems; they have appeared in various incarnations. In this paper we use a multiresolution B-spline representation, as was initially suggested in the... |

4 | An iterative method for thin-plate spline interpolation that employs approximations to the Lagrange functions - Beatson, Powell - 1993 |

4 |
et al.: Multisubject non-rigid registration of brain MRI using intensity and geometric features
- Cachier
(Show Context)
Citation Context ... gear the algorithm toward the correct solution. The idea of a hybrid registration algorithm combining both local features (points or lines) with global ones (intensities) has appeared for example in =-=[58]-=-, [59] 6 and others. However, as both [58], [59] use essentially local, nonparametric deformation models, the landmark constraints need to be first interpolated everywhere to serve as an a priori defo... |

3 |
Automatic registration of images of pigmented skin lesions
- McGregor
- 1998
(Show Context)
Citation Context ...ages for analysis and diagnostic purposes. This is accomplished by registering the images and aligning them by warping using the correspondence function identified. Applications include intra-subject =-=[12]-=-, inter-subject [13], [14], and inter-modality analysis [15], [16], [17], registration with annotated atlases [18], [19], quantification and qualification of feature shapes and sizes [20], distortion ... |

2 |
Enhancing the multivariate signal of [ O] water PET studies with a new nonlinear neuroanatomical registration algorithm
- Kjems, Strother, et al.
- 1999
(Show Context)
Citation Context ...nostic purposes. This is accomplished by registering the images and aligning them by warping using the correspondence function identified. Applications include intra-subject [12], inter-subject [13], =-=[14]-=-, and inter-modality analysis [15], [16], [17], registration with annotated atlases [18], [19], quantification and qualification of feature shapes and sizes [20], distortion compensation [21], [22] an... |

2 |
Robust 3D deformation field estimation by template propagation
- Rösch, Weese, et al.
- 2000
(Show Context)
Citation Context ... registration with annotated atlases [18], [19], quantification and qualification of feature shapes and sizes [20], distortion compensation [21], [22] and motion detection [23], [24] and compensation =-=[25]-=-. Manuscript received September 6, 2001; revised February 12, 2003. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Patrick Perez. J. Kybic was... |

2 | Compensation of unidirectional geometric distortion in EPI using spline warping
- Kybic, Thevénaz, et al.
- 1999
(Show Context)
Citation Context ...solution if started within the attraction basin of that solution. The virtual springs (Section V) play a role of an a priori information and a regularization term; extra regularization can be applied =-=[44]-=- if desired. III. DEFORMATION BASIS The purpose of this section is to motivate our choice of (cubic) B-splines [42] as the most adequate basis functions to represent the deformation in model (3). The ... |

2 | Using a fast multipole method to accelerate the evaluation of splines
- Sutter, Chen
- 1998
(Show Context)
Citation Context ...rute-force evaluation is slow due to their long support. As for the radial basis functions, although there are algorithms with reduced asymptotical complexity for evaluation of radial basis functions =-=[50]-=-–[53], their overhead is still nonnegligible. We decided against the harmonic (Fourier) basis functions because of their lack of localization (the fact that any two of them overlap). Another argument ... |

2 |
et al., “MRI quantitative myocardial perfusion with compartmental analysis: A rest and stress study,” Magn
- Vallée
- 1997
(Show Context)
Citation Context ...be robust to the occasional change of structure (topology) due to the underlying 3-D nature of the true movement. 13 Another technique for assessing cardiac performance is myocardial perfusion by MRI =-=[66]-=-, [67]. A sequence of MRI images14 is acquired with at high speed to assess the diffusion of the agent. A role of the registration is to compensate for the (heart) motion to provide the time profiles ... |

1 |
Biomedical image processing by elastic warping, Ph.D. dissertation. Ecole Polytechnique Fédérale de
- Kybic
(Show Context)
Citation Context ...nd the deformation, a double multiresolution strategy (for both the image and the deformation), a scalar pixel-based difference measure, and an iterative multidimensional optimization algorithm [37], =-=[38]-=-. The deformation model has been generalized and the whole algorithm re-engineered for faster execution. Second, we present the idea of semi-automatic registration, targeted to more difficult registra... |