Landmark matching via large deformation diffeomorphisms

By Sarang C. Joshi, Michael I. Miller. IEEE Transactions on Image Processing, 2000

620 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Geometry and Topology

View Paper: https://www.semanticscholar.org/paper/2d8c3c725609cd60756471800e4e442d373b1e5a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

In Geometry and Topology

Citations in the corpus

Deformable medical image registration: setting the state of the art with discrete methods. (2011, background): “(23) could be defined as well in the above manner.”
Shape deformation analysis from the optimal control viewpoint (2014, background): “Since shape analysis has a natural setting in inﬁnite dimension (indeed, in 2D, the shape space is typically a space of smooth curves in R 2 ), we need to derive an appropriate inﬁnite-dimensional variant of the PMP for constrained problems Such a variant is nontrivial and nonstandard, given that…”
Consistent landmark and intensity-based image registration (2002, background): “[27]–[29] estimates large deformation transformations in a solution space of diffeomorphisms by constraining the transformations to obey diffeomorphic fluid properties.”
Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces (2019, methodology): “Diffeomorphic transforms have seen extensive methodological development, yielding state-of-the-art tools, such as Large Diffeomorphic Distance Metric Mapping (LDDMM) [10, 12, 13, 28, 33, 42, 47, 59], DARTEL [3], diffeomorphic Demons [56], and symmetric normalization (SyN) [5].”
A review of multimodal image matching: Methods and applications (2021, background): “A diffeomorphism framework can handle large deformation registration problems because of the gradual variation behavior of the velocity field and is thus also named large deformation diffeomorphic metric mapping [60,61].”
On the metrics and euler-lagrange equations of computational anatomy. (2002, methodology): “1 (Joshi (69))For N-shapes I N, I ′ N ∈RdN, ∂ ∂t g(x, t)= v(g(x, t), t), g(xn, 0)= xn, g(xn, 1)= x′ n the optimizing diffeomorphism satisfying”
Slice-to-volume medical image registration: a survey (2017, background): “Geometric registration finds correspondences between meaningful anatomical locations or salient landmarks (Joshi and Miller, 2000; Glocker and Sotiras, 2011).”
Matrix-valued kernels for shape deformation analysis (2013, methodology): “To illustrate an application of the tools that we developed thus far, in this section we shall study the problem of matching feature points, or “landmarks” [30, 35, 42, 69].”
Geodesic Shooting for Computational Anatomy (2006, methodology): “We do not detail numerical algorithms in this paper, but the reader can refer to [4, 5, 17, 23] for examples of choices of K.”
Surface Matching via Currents (2005, background): “wherekV denotes the reproducing kernel of the deformation space V (see [4, 5]).”
Diffeomorphic demons: Efficient non-parametric image registration (2009, methodology): “have thus been using an additive adjustment rule s + u instead of the compositive update rule (Cachier et al., 2003; Ibanez et al., 2005; Modersitzki, 2004; Pennec et al., 1999).”
Deformable Medical Image Registration: A Survey (2013, background): “The advantage of this framework, known as Large Deformation Di eomorphic Metric Mapping (LDDMM), is that it allows for the de nition of a distance between images or sets of points [70, 71].”
What Happened to My Dog in That Network: Unraveling Top-down Generators in Convolutional Neural Networks (2015, background): “A related but much more theoretical diffeomorphism-based perspective is (Joshi et al., 2000).”
User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability (2006, background): “Methods based on elastic and fluid registration can identify anatomical structures in the brain by deforming a labeled probabilistic brain atlas onto the subject brain (Joshi and Miller, 2000; Avants et al., in press; Davatzikos et al., 2001; Thirion, 1996).”
A spatially unbiased atlas template of the human cerebellum (2006, methodology): “For the study of smallscale anatomical differences, we are currently working to employ alternative algorithms that do not use basis functions (Joshi and Miller, 2000).”
Population Shape Regression from Random Design Data (2007, methodology): “We apply the theory of large deformation diffeomorphisms (Beg et al. 2005; Dupuis and Grenander 1998; Joshi and Miller 2000; Miller and Younes 2001) to generate deformations φ that are solutions to the Lagrangian ODEs d ds φs(x) = vs(φs(x)) for a simulated time parameter s ∈ [0,1].”
DRAMMS: Deformable Registration via Attribute Matching and Mutual-Saliency Weighting (2009, methodology): “Existing deformable registration methods can be generally classiﬁed into two main categories: voxel-wise methods (e.g., [1,2,3,4,5,6,7]) and landmark/feature-based methods (e.g., [8,9,10,11,12,13,14]).”
A Review of Geometric Transformations for Nonrigid Body Registration (2008, background): “In general, these functions do not preserve the topology, however , recent work [70], [71] has sought to design functions that are diffeomorphisms, see Section VI-C.”