Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain

By Brian B. Avants, Charles L. Epstein, Murray C. Grossman, James C. Gee. Medical Image Anal., 2008

5,742 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/66b498a54843e14270b75f0c3c8fc65a0b2e1e98

How researchers see this paper

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

In Biophysics

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Automated Volumetry and Regional Thickness Analysis of Hippocampal Subfields and Medial Temporal Cortical Structures in Mild Cognitive Impairment (2014, methodology): “, 2004] and ANTS [Avants et al., 2008] rigid registration algorithms, using the normalized mutual information (NMI) metric as the similarity measure.”
Unbiased Average Age-Appropriate Atlases for Pediatric Studies (2010, positive): “While other non-linear registration techniques could have been chosen (Ardekani et al., 2005; Avants et al., 2006; Lorenzen and Joshi, 2003), we selected ANIMAL because we have extensive experience with the procedure and a recent study (Guizzard et al., 2009) has shown that when used with appropriat”
SCT: Spinal Cord Toolbox, an open‐source software for processing spinal cord MRI data (2017, neutral): “rigid: Tx, Ty, Rz (3 dof) affine: Tx, Ty, Rz, Sx, Sy (5 dof) syn: (Avants et al., 2008) bsplinesyn: (Tustison and Avants, 2013) slicereg: slice-wise regularized rigid (Cohen-Adad et al.”
Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing (2023, neutral): “Registering image pairs is commonly used for change detection in other contexts [17,52,59], and has been applied to medical imaging [5, 23].”
An evaluation of the efficacy, reliability, and sensitivity of motion correction strategies for resting-state functional MRI (2017, methodology): “2.2.1 Structural image processing Each participant’s T1-weighted high-resolution structural image was processed using the following steps: (1) removing the neck using FSL’s robustfov; (2) segmentation of the native T1-weighted image into WM, CSF, and grey matter (GM) probability maps using SPM8’s Ne”
MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration (2012, background): “In Avants et al. (2008), a symmetric deformable registration is presented, which calculates a transform from both images to a common intermediate image and also ensures that the forward transform is the inverse of the backward transform.”
Multi-atlas segmentation of the whole hippocampus and subfields using multiple automatically generated templates (2014, methodology): “Automatic Normalization Tools (ANTS) ANTS is a diffeomorphic registration algorithm which provides great flexibility over the choice of transformation model, objective function, and the consistency of the final transformation (Avants et al., 2008).”
TransMorph: Transformer for unsupervised medical image registration (2021, positive): “2005), sum of squared differences (SSD) (Wolberg and Zokai 2000), normalized cross-correlation (NCC) (Avants et al. 2008), structural similarity index (SSIM) (Chen et al.”
The impact of T1 vs EPI spatial normalization templates for fMRI data analyses (2017, methodology): “The nonlinear boundary based registration (BBR) approach in FSL 5.0 was used to align EPI and T1 data, and linear and nonlinear approaches in the advanced normalization tools (ANTs) software package [Avants et al., 2008] were used to transform T1 data to standard space.”
Diffeomorphic demons: Efficient non-parametric image registration (2009, methodology): “Diﬀeomorphic image registration usually relies on the computationally heavy solution of some partial diﬀerential equations (Avants et al., 2008; Beg et al., 2005; Christensen et al., 1996; Joshi and Miller, 2000; Leow et al., 2007; Marsland and Twining, 2004; Miller et al., 1998; Trouvé, 1998;…”
Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration (2018, background): “Diffeomorphic transforms have seen extensive methodological development, yielding state-of-the-art tools, such as LDDMM [6,29], DARTEL [2], and SyN [3].”
Deformable Medical Image Registration: A Survey (2013, background): “[80] presented a symmetric LDDMM registration process driven by cross-correlation”
Multi-Atlas Segmentation with Joint Label Fusion (2012, methodology): “(SyN) algorithm [4] with the cross-correlation similarity metric (with radius 2) and a Gaussian regularizer with 1⁄4 3.”
A normative spatiotemporal MRI atlas of the fetal brain for automatic segmentation and analysis of early brain growth (2017, methodology): “To achieve this, we integrate kernel regression over age 72 with symmetric diffeomorphic deformable registration based on a viscous fluid deformation model 60 in space.”
Data-Efficient Mutual Information Neural Estimator (2019, methodology): “T1-weighted images were corrected for intensity non-uniformity using N4 bias field correction [45] and skull-stripped using ANTs [3].”