A fast diffeomorphic image registration algorithm

By John Ashburner. NeuroImage, 2007

8,199 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/21b65bbf11bc246a80b7f08043db3ff5c0844e91

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: Exploring the influence of various parameters (2010, neutral): “In order to demonstrate the performance of his algorithm for diffeomorphic image registration, Ashburner (2007) estimated the age of subjects based on their brain images utilizing a relevance vector machine (RVM) for regression (Tipping, 2000, 2001).”
Unsupervised End-to-end Learning for Deformable Medical Image Registration (2017, background): “A variety of traditional medical image registration algorithms have been proposed over the past few decades [4], [5], [6], [3], [7].”
Quantitative multi-parameter mapping of R1, PD*, MT, and R2* at 3T: a multi-center validation (2013, methodology): “After appropriate spatial normalization the local GM volume is compared voxel-wise between groups and volunteers (Ashburner, 2007).”
Issues with threshold masking in voxel-based morphometry of atrophied brains (2009, background): “However, it should also be noted that finer scale spatial normalisation (Shen and Davatzikos, 2003; Ashburner, 2007) may counterbalance this effect, as atrophied structures can be better warped to match those of the template/average, with the information about their atrophy being transferred to the…”
An unsupervised convolutional neural network-based algorithm for deformable image registration (2018, background): “Many intensity based feature selection algorithms that aim to distinguish a good set of candidate regions with correspondingly strong features have been implemented for medical image registration (Arsigny et al 2006, Ashburner 2007, Rueckert and Aljabar 2015).”
Multi-Modal Multi-Task Learning for Joint Prediction of Multiple Regression and Classification Variables in Alzheimer’s Disease (2011, methodology): “The initial goal of ADNI was to recruit 800 adults, aged 55 to 90, to participate in the research – approximately 200 cognitively normal older individuals to be followed for 3 years, 400 people with MCI to be followed for 3 years, and 200 people with early AD to be followed for 2 years (see…”
A Brain-Wide Study of Age-Related Changes in Functional Connectivity. (2015, methodology): “A study-specific anatomic template was created (for young and elderly participants together), using Diffeomorphic Anatomical Registration Exponentiated Lie algebra (DARTEL), to optimize interparticipant alignment (Ashburner 2007).”
A Comprehensive Assessment of Regional Variation in the Impact of Head Micromovements on Functional Connectomics (2013, methodology): “The Diffeomorphic Anatomical Registration Through Exponentiated Lie algebra (DARTEL) tool (Ashburner, 2007) was used to compute transformations from individual native space to MNI space and vice-versa.”
The salience network is responsible for switching between the default mode network and the central executive network: Replication from DCM (2014, methodology): “Functional data were then normalised to standard space and smoothed using DARTEL (Ashburner, 2007).”
Diffeomorphic demons: Efficient non-parametric image registration (2009, methodology): “With the setup given hereafter, the registration of two 256× 256× 181 BrainWeb images runs in 2 minutes and 30 seconds on a 2× 2.8 GHz quad-core Intel Xeon Apple Mac pro computer: 3 multi-resolution levels with 20 diffeomorphic demons iterations at the coarsest level, and 10 diffeomorphic demons ite”
SynthStrip: skull-stripping for any brain image (2022, neutral): “Nonlinear registration (Ashburner, 2007; Avants et al., 2008; Rueckert et al., 1999; Vercauteren et al., 2009) estimates local deformations between pairs of images, and these algorithms tend to produce more accurate estimates when they can focus entirely on the anatomy of interest (Klein et al.,…”
A Generative Model for Image Segmentation Based on Label Fusion (2010, neutral): “Bi-directional or symmetric approaches that apply warps to both images seem to yield more accurate alignment [7], [9], [14], [65].”