Groupwise Spectral Log-Demons Framework for Atlas Construction

Lombaert, Hervé; Grady, Leo; Pennec, Xavier; Peyrat, Jean-Marc; Ayache, Nicholas; Cheriet, Foued

doi:10.1007/978-3-642-36620-8_2

Cited by 5 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is registered in parallel with a reference shapeĨ that evolves until a convergence is reached on an average shapeĨ. In order to further illustrate the benefits of using Spectral Forces, within conventional registration methods, we extend the symmetric Log-Demons algorithm (Vercauteren et al, 2008) in order to perform groupwise registration (Lombaert et al, 2012b) by using either classical gradient-based updates (in the Groupwise Log-Demons, or GL-Demons), or Spectral Forces, (in the Groupwise Spectral Log-Demons, or GSL-Demons).…”

Section: Groupwise Registrationmentioning

confidence: 99%

“…Here, the method is fully explained and we provide extensive details as well as the general intuition behind the Spectral Forces. A second example is provided by extending the conventional symmetric Demons algorithm (Vercauteren et al, 2008) in order to perform groupwise registration (Lombaert et al, 2012b), i.e., the atlas is computed in parallel to the registration process rather than with a series of pairwise registrations. Similarly, this new method, named Groupwise Log-Demons, or GL-Demons, can be adapted to use Spectral Forces, yielding the Groupwise Spectral Log-Demons algorithm, or GSL-Demons.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spectral Log-Demons: Diffeomorphic Image Registration with Very Large Deformations

et al. 2013

Self Cite

View full text Add to dashboard Cite

This paper presents a new framework for capturing large and complex deformations in image registration and atlas construction. This challenging and recurrent problem in computer vision and medical imaging currently relies on iterative and local approaches, which are prone to local minima and, therefore, limit present methods to relatively small deformations. Our general framework introduces to this effect a new direct feature matching technique that finds global correspondences between images via simple nearest-neighbor searches. More specifically, very large image deformations are captured in Spectral Forces, which are derived from an improved graph spectral representation. We illustrate the benefits of our framework through a new enhanced version of the popular Log-Demons algorithm, named the Spectral Log-Demons, as well as through a groupwise extension, named the Groupwise Spectral Log-Demons, which is relevant for atlas construction. The evaluations of these extended versions demonstrate substantial improvements in accuracy and robustness to large deformations over the conventional Demons approaches.

show abstract

Section: Groupwise Registrationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Spectral Log-Demons: Diffeomorphic Image Registration with Very Large Deformations

et al. 2013

Self Cite

View full text Add to dashboard Cite

show abstract

“…The results of tests show that RC measure outperforms other three measures in the presence of illumination variations and geometrical transformation. In the futhure, the RC measure can be generalized to groupwise registration [18][19][20][21][22][23][24][25][26][27] of color images.…”

Section: A Nonrigid Registration Between Color Pepper Imagementioning

confidence: 99%

Nonrigid color image registration by minimizing residual complexity under illumination variations

Wang

Zhu³

et al. 2013

2013 6th International Congress on Image and Signal Processing (CISP)

View full text Add to dashboard Cite

In the presence of spatially-varying illumination changes, many intensity-based similarity measures cannot capture the complex interactions among the pixel intensities and result in wrong registration. Residual complexity (RC) measure can solve this problem and provide accurate and robust registration results in the same modality images registration. In this study, RC measure is generalized to nonrigid color image registration and the corresponding color image registration scheme is proposed. By nonrigid registration of three kinds of color images, four similarity measures, i.e. RC, mutual information, correlation coefficient and sum-of-squared differences, are contrasted and studied. The results of tests show that RC measure outperforms other three measures in the presence of illumination variations and geometrical transformation of color images.

show abstract

“…Some researchers have studied registration of multiple images at the same time -called ensemble registration [5][6][7] or groupwise registration [8][9][10][11]. Ensemble registration based on GMM can avoid calculating high dimensional joint histogram [15], and it will decrease memory and enhance registration speed.…”

Section: Introductionmentioning

confidence: 99%

Medical image ensemble registration based on Gaussian mixture model and color component regularization

Orchard

2015

Optik

View full text Add to dashboard Cite

Groupwise Spectral Log-Demons Framework for Atlas Construction

Cited by 5 publications

References 26 publications

Spectral Log-Demons: Diffeomorphic Image Registration with Very Large Deformations

Spectral Log-Demons: Diffeomorphic Image Registration with Very Large Deformations

Nonrigid color image registration by minimizing residual complexity under illumination variations

Medical image ensemble registration based on Gaussian mixture model and color component regularization

Contact Info

Product

Resources

About