Diffeomorphic demons: Efficient non-parametric image registration

By Tom Kamiel Magda Vercauteren, Xavier Pennec, Aymeric Perchant, Nicholas Ayache. NeuroImage, 2009

1,723 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/29ba51fbb935b9b948bb880423a70494da8f4e7f

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

A review of atlas-based segmentation for magnetic resonance brain images (2011, methodology): “[60] T.”
Large Deformation Diffeomorphic Image Registration with Laplacian Pyramid Networks (2020, methodology): “Conventional image registration methods [23,18,2,24] often rely on the multi-resolution strategy and estimate the target transformation iteratively along with a smoothness regularization.”
Digital Topology and Geometry in Medical Imaging: A Survey (2015, background): “a major issue in deformable image registration and several methods from continuous mathematics have been adopted to solve this challenge [34]–[36].”
Deformable Medical Image Registration: A Survey (2013, methodology): “The intensity-based update ﬁeld was calculated as in [99].”
Deep Learning in Medical Image Analysis (2017, methodology): “Compared to the state-of-the-art registration methods of intensity-based diffeomorphic Demons (83) and feature-based HAMMER (84) for 1.5-and 3.0-Tesla MR images, the method of using the SAE-learned feature representation in Fig.”
Latent feature representation with stacked auto-encoder for AD/MCI diagnosis (2013, methodology): “…other advanced registration methods can also be applied for this process (Friston et al. 1995; Evans and Collins 1997; Rueckert et al. 1999; Shen et al. 1999; Wu et al. 2006; Xue et al. 2006a, b; Avants et al. 2008; Yang et al. 2008; Tang et al. 2009; Vercauteren et al. 2009; Jia et al. 2010).”
Deformable Image Registration Using Cue-aware Deep Regression Network (2018, methodology): “Here, we use two versions of Demons: SSD-Demons [21] and LCC-Demons [39].”
Deep learning in medical image registration: a review (2019, methodology): “Popular registration methods include optical flow [169, 167], demons [154], ANTs [3], HAMMER [131], ELASTIX [75] and so on.”
The Insight ToolKit image registration framework (2014, neutral): “The diffeomorphic demons is a fast/efﬁcient approximation to a diffeomorphic mapping (Vercauteren et al., 2009).”
Medical Image Synthesis with Context-Aware Generative Adversarial Networks (2016, methodology): “We can clearly see that the generated data using the GAN approach has less artifacts than the traditional FCN, by estimating an image that is closer to the desired output not only quantitatively but also qualitatively.”
A Reproducible Evaluation of ANTs Similarity Metric Performance in Brain Image Registration (2010, methodology): “We include—within ANTs options—these four diffeomorphic transformation models for parameterizing ϕ(⋅): Geodesic SyN, Greedy SyN, exponential mapping, and Greedy Exp (based on Diffeomorphic Demons).”
Spherical Demons: Fast Diffeomorphic Landmark-Free Surface Registration (2009, methodology): “We emphasize that unlike Diffeomorphic Demons [66], ~v is a tangent vector ﬁeld on the sphere and not an arbitrary 3D vector ﬁeld.”
CycleMorph: Cycle Consistent Unsupervised Deformable Image Registration (2020, background): “A diffeomorphic deformation ensures certain desirable properties between two image volumes like continuous, differentiable, and preserving topology [6], [7], [21].”
VoxelMorph: A Learning Framework for Deformable Medical Image Registration (2018, methodology): “Popular formulations include Large Diffeomorphic Distance Metric Mapping (LDDMM) [9], [21], [27]–[32], DARTEL [16], diffeomorphic demons [33], and standard symmetric normalization (SyN) [11].”
Deep learning in medical image registration: a survey (2019, methodology): “This method outperforms SyN [5] and Demons [127] based registration methods.”
Scalable High Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning (2015, methodology): “Then, we extend the diffeomorphic Demons from a single channel (i.e., image intensity) to multichannel Demons by adapting the learned feature representations via deep learning to multiple channels, which is denoted by M + DP. Similarly, we modify HAMMER to use the feature representations learned via”