171 Hits in 4.7 sec

Diffeomorphic point set registration using non-stationary mixture models

D. Wassermann, J. Ross, G. Washko, C-F Westin, R. San Jose Estepar
2013 2013 IEEE 10th International Symposium on Biomedical Imaging  
This paper investigates a diffeomorphic point-set registration based on non-stationary mixture models.  ...  Our framework generalizes work done by others that use stationary models.  ...  Unlike [4, 5] , we present a registration algorithm with a non-stationary calculation of the point-set similarity by using a different kernel function for each point.  ... 
doi:10.1109/isbi.2013.6556656 pmid:24419463 pmcid:PMC3886289 dblp:conf/isbi/WassermannRWWE13 fatcat:jd4meyqxfbgm5hz5qzi6logxd4

Toward Computing Cross-Modality Symmetric Non-Rigid Medical Image Registration

Snigdha Mohanty, Sarada Prasad Dakua
2022 IEEE Access  
A non stationary velocity field is used to minimize the effect of forces that are derived from the image gradients.  ...  The deformation is a key challenge in medical image registration. We have proposed a diffeomorphism-based method to tackle this problem using an optimized framework.  ...  [42] use an adaptive weighted objective function that formulates the alignment of two point sets as a mixture model estimation problem.  ... 
doi:10.1109/access.2022.3154771 fatcat:3ow254kwbbh7ngw3mtsv6g5qnu

A Stochastic Approach to Diffeomorphic Point Set Registration with Landmark Constraints

Ivan Kolesov, Jehoon Lee, Gregory Sharp, Patricio Vela, Allen Tannenbaum
2016 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This work presents a deformable point set registration algorithm that seeks an optimal set of radial basis functions to describe the registration.  ...  A novel, global optimization approach is introduced composed of simulated annealing with a particle filter based generator function to perform the registration.  ...  Results of doing point set registration subject to known points remaining stationary are in Fig. 11 (c).  ... 
doi:10.1109/tpami.2015.2448102 pmid:26761731 pmcid:PMC4727970 fatcat:xc3vnwzwqzbcbmlazzj24z4xde

Deformable Registration of Feature-Endowed Point Sets Based on Tensor Fields

Demian Wassermann, James Ross, George Washko, William M. Wells, Raul San Jose-Estepar
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
The main contribution of this work is a framework to register anatomical structures characterized as a point set where each point has an associated symmetric matrix.  ...  Finally, we evaluate our registration algorithm on synthetic data sets and validate our approach on manually annotated airway trees.  ...  Particular cases of this are the Gaussian mixture model (GMM) and the discrete setting of the currents model [4, 5] .  ... 
doi:10.1109/cvpr.2014.355 pmid:25473253 pmcid:PMC4248604 dblp:conf/cvpr/WassermannRWWE14 fatcat:ycikgri6pzfptfuizlzqk6ork4

CLAIRE: Constrained Large Deformation Diffeomorphic Image Registration on Parallel Computing Architectures

Malte Brunn, Naveen Himthani, George Biros, Miriam Mehl, Andreas Mang
2021 Journal of Open Source Software  
CLAIRE (Mang & Biros, 2019) is a computational framework for Constrained LArge deformation diffeomorphic Image REgistration (Mang et al., 2019).  ...  The multi-GPU implementation uses device direct communication.  ...  Mathematics CLAIRE uses an optimal control formulation. The diffeomorphism y(x) is parameterized using a smooth, stationary velocity field v(x).  ... 
doi:10.21105/joss.03038 pmid:35295546 pmcid:PMC8923611 fatcat:iloez67yirhajkfxzzelyn3ehe

Diffeomorphic image matching with left-invariant metrics [article]

Tanya Schmah, Laurent Risser, François-Xavier Vialard
2014 arXiv   pre-print
The geometric approach to diffeomorphic image registration known as "large deformation by diffeomorphic metric mapping" (LDDMM) is based on a left action of diffeomorphisms on images, and a right-invariant  ...  metric on a diffeomorphism group, usually defined using a reproducing kernel.  ...  A mixture of Gaussian kernels was used in (a-b). In (c),(d),(e) a similar mixture of kernels was used, but with a symmetry at the large scale weighted by the factors 0.1, 0.5 and 1, respectively.  ... 
arXiv:1401.3609v1 fatcat:fiq64n7g55gd7csxp6xvddbkhu

Geometry-Aware Multiscale Image Registration via OBBTree-Based Polyaffine Log-Demons [chapter]

Christof Seiler, Xavier Pennec, Mauricio Reyes
2011 Lecture Notes in Computer Science  
Non-linear image registration is an important tool in many areas of image analysis.  ...  This closes the gap between polyaffine and non-rigid registration and opens new ways to statistically analyze the registration results.  ...  One interesting point of this registration framework is the efficient optimization in the domain of stationary velocity fields.  ... 
doi:10.1007/978-3-642-23629-7_77 fatcat:xozuflfwerboxko2ur2uchnhha

Mixture of Kernels and Iterated Semidirect Product of Diffeomorphisms Groups

Martins Bruveris, Laurent Risser, François-Xavier Vialard
2012 Multiscale Modeling & simulation  
We also show that the approaches presented in other papers and the mixture of kernels are equivalent.  ...  In the framework of large deformation diffeomorphic metric mapping (LDDMM), we develop a multi-scale theory for the diffeomorphism group based on previous works.  ...  For a stationary point, we obtain π(v) = u, K s π * p(s) = v s , λ a.e.  ... 
doi:10.1137/110846324 fatcat:t73v25dotvcoblsp64oifew6fa

Automated Emotion Morphing in Speech Based on Diffeomorphic Curve Registration and Highway Networks

Ravi Shankar, Hsi-Wei Hsieh, Nicolas Charon, Archana Venkataraman
2019 Interspeech 2019  
Our strategy is to warp the pitch contour of a source emotional utterance using diffeomorphic curve registration.  ...  Once trained, the HNet is used to obtain the initial momenta for new utterances. From here, the diffeomorphic process takes over and warps the pitch contour accordingly.  ...  In particular, let vt(x; s) be a non-stationary and finite norm vector field across time t and pitch values x.  ... 
doi:10.21437/interspeech.2019-2386 dblp:conf/interspeech/ShankarHCV19 fatcat:qbc53lqskjcdroe7nra276ojaa

Generative diffeomorphic modelling of large MRI data sets for probabilistic template construction

Claudia Blaiotta, Patrick Freund, M. Jorge Cardoso, John Ashburner
2018 NeuroImage  
Such a model has a direct application for learning average-shaped probabilistic tissue templates in a fully automated manner.  ...  At the same time we illustrate how the resulting tissue probability maps can readily be used to segment, bias correct and spatially normalise unseen data, which are all crucial pre-processing steps for  ...  From a mathematical modelling point of view, the atlas encodes local mixing proportions Θ π ¼ fπ j g j¼1;…;Nπ of the mixture model, with j being an index set over the N π template voxels (for a list of  ... 
doi:10.1016/j.neuroimage.2017.10.060 pmid:29100938 pmcid:PMC5770340 fatcat:7wleplnlubcglilc3fi5eur7eu

Metric Learning for Image Registration [article]

Marc Niethammer and Roland Kwitt and Francois-Xavier Vialard
2019 arXiv   pre-print
This allows controlling the desired level of regularity and preserving structural properties of a registration model. For example, diffeomorphic transformations can be attained.  ...  the registration model itself.  ...  We build on top of a new vector momentum-parameterized stationary velocity field (vSVF) registration model which allows us to guarantee that deformations are diffeomorphic even when using a learned regularizer  ... 
arXiv:1904.09524v1 fatcat:gmxlhllnv5gmxjtkqfmgmar57a

Generative diffeomorphic atlas construction from brain and spinal cord MRI data [article]

Claudia Blaiotta, Patrick Freund, M. Jorge Cardoso, John Ashburner
2017 arXiv   pre-print
In this paper we will focus on the potential and on the challenges associated with the development of an integrated brain and spinal cord modelling framework for processing MR neuroimaging data.  ...  The aim of the work is to explore how a hierarchical generative model of imaging data, which captures simultaneously the distribution of signal intensities and the variability of anatomical shapes across  ...  One way of constructing transformations belonging to the diffeomorphic group Diff(Ω) is to solve the following non-stationary transport equation (Joshi and Miller, 2000) d dt φ(y, t) = u(φ(y, t), t)  ... 
arXiv:1707.01342v1 fatcat:jzejls76hve63mlcgjnszcvcbm

Diffeomorphic Brain Shape Modelling Using Gauss-Newton Optimisation [chapter]

Yaël Balbastre, Mikael Brudfors, Kevin Bronik, John Ashburner
2018 Lecture Notes in Computer Science  
The model recasts the recovery of high resolution images as an inverse problem, in which a forward model simulates the slice-select profile of the MR scanner.  ...  The model was validated on a large database of brain images.  ...  If needed, it is straightforward to replace this term with a stationary Gaussian noise model.  ... 
doi:10.1007/978-3-030-00928-1_97 fatcat:k37a75nsfver3idtzwrfk6naqy

Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation

John Ashburner, Karl J. Friston
2011 NeuroImage  
This paper presents a nonlinear image registration algorithm based on the setting of Large Deformation Diffeomorphic Metric Mapping (LDDMM), but with a more efficient optimisation schemeboth in terms of  ...  The algorithm was evaluated using freely available manually labelled datasets, and found to compare favourably with other inter-subject registration algorithms evaluated using the same data.  ...  Default settings were used for the tissue segmentation, except that a non-parametric representation of the tissue intensity distributions was used, rather than the default mixture of Gaussians.  ... 
doi:10.1016/j.neuroimage.2010.12.049 pmid:21216294 pmcid:PMC3221052 fatcat:556xva376jh5vis3q7lf4xs32e

Transformations Based on Continuous Piecewise-Affine Velocity Fields

Oren Freifeld, Soren Hauberg, Kayhan Batmanghelich, Jonn W. Fisher
2017 IEEE Transactions on Pattern Analysis and Machine Intelligence  
warping; image registration; real-time diffeomorphic image editing; data augmentation for image classifiers.  ...  Importantly, the proposed approach, partly due to its rapid likelihood evaluations and partly due to its other properties, facilitates tractable inference over rich transformation spaces, including using  ...  non-diffeomorphic fusion.  ... 
doi:10.1109/tpami.2016.2646685 pmid:28092517 pmcid:PMC5889303 fatcat:pi4znbaqebfubf3wdgdezt52by
« Previous Showing results 1 — 15 out of 171 results