Consistent image registration

By Gary E. Christensen, Hans J. Johnson. IEEE Transactions on Medical Imaging, 2001

721 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/836b44cf08e8720325ee06365dfe2f5a4810e812

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 Mechanical Engineering

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Optimal Mass Transport for Registration and Warping (2004, background): “It is thus symmetrical, the optimal mapping from image to image being the inverse of the optimal mapping from to It is not necessary for using an extra constraint to guarantee the symmetrical property, as in [10].”
Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain (2008, methodology): “Inverse consistency was first introduced by Thirion as an extension to his Demons algorithm (Thirion, 1998) but was popularized by Christensen and Johnson (2001) and others (Shen and Davatzikos, 2002).”
A review of multimodal image matching: Methods and applications (2021, methodology): “Other interpolation-based models include elastic body splines [70], basis functions from signal representation [71,72], and locally affine models [73,74].”
Symmetric Diffeomorphic Modeling of Longitudinal Structural MRI (2013, background): “Concerns about asymmetry in pairwise image registration, related to one image being chosen as a (fixed) reference and the other as a (moving) source, first arose at the turn of the century (Ashburner et al., 1999; Cachier and Rey, 2000; Christensen and Johnson, 2001).”
Survey of Non-Rigid Registration Tools in Medicine (2017, background): “In several non-rigid registration techniques, the estimated transformation from one image to the other does not equal the inverse of the estimated reverse transform [40].”
Consistent landmark and intensity-based image registration (2002, methodology): “The displacement field is computed by taking the inverse of the transformation as described in our previous paper describing the consistent intensity registration algorithm [34].”
Evaluation of atlas selection strategies for atlas-based image segmentation with application to confocal microscopy images of bee brains (2004, methodology): “Miller et al. (1993) used an algorithm with an elastic deformable solid model, which was later extended by Christensen and Johnson (2001) to preserve consistency between forward and backward transformations and to accept an initialization using a landmark-based nonrigid transformation.”
Statistical analysis of trajectories on Riemannian manifolds: Bird migration, hurricane tracking and video surveillance (2014, background): “…problem with this procedure is that (a) it is not symmetric, that is, the registration of α1 to α2 is not the same as that of α2 to α1, as pointed out by Christensen and Johnson (2001), among others, and (b) the minimum value is not a proper distance, so it cannot be used to compare trajectories.”
Avoiding asymmetry-induced bias in longitudinal image processing (2011, background): “Often, both forward and backward warps are jointly estimated, e.g., (Christensen and Johnson, 2001; Zeng and Chen, 2008), while others match at the midpoint (Beg and Khan, 2007).”
Brain Functional Localization: A Survey of Image Registration Techniques (2007, methodology): “Consistency tests have also been employed as a part of validation in several studies [77], [202], [212], [228].”
Deformable Medical Image Registration: A Survey (2013, background): “to tackle this shortcoming, Christensen and Johnson [19] pro-”
Highly Accurate Inverse Consistent Registration: A Robust Approach (2010, background): “Often both forward and backward warps are jointly estimated , e.g. (Christensen and Johnson, 2001; Zeng and Chen, 2008).”
A Review of Geometric Transformations for Nonrigid Body Registration (2008, methodology): “Christensen and Johnson [138], [139] used inverse consistency as regularization constraint.”
Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration (2009, methodology): “6 is minimized using the gradient descent method described in (Christensen and Johnson, 2001) where each component of the displacement field is parameterized in terms of a 3-D Fourier series.”
Evaluation of Optimization Methods for Nonrigid Medical Image Registration Using Mutual Information and B-Splines (2007, background): “Well-known examples for are the curvature term [6], the elastic energy [7], and the volume preserving penalty term [8].”
CycleMorph: Cycle Consistent Unsupervised Deformable Image Registration (2020, background): “In consistent image registration approaches [3]–[5], this problem is alleviated by imposing additional inverse consistency R (cid:39) F − 1 .”