Evaluation of Optimization Methods for Nonrigid Medical Image Registration Using Mutual Information and B-Splines

By Stefan Klein, Marius Staring, Josien P. W. Pluim. IEEE Transactions on Image Processing, 2007

511 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/3916bdbadb4d82cb1e3a0bc73c072ccb5d060532

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

Lung Segmentation in Chest Radiographs Using Anatomical Atlases With Nonrigid Registration (2013, unknown): “Several non-rigid registration algorithms have been reported in the literature [47], [48], [49], [50], [51], [52], [53], [54], [55], [56].”
Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “Based on information theory, the MI, such as non-rigid image registration using MI together with B-splines (Klein et al. 2007) and conditionalMI (Loeckx et al. 2009), is ameasurement of statistical dependency between two images and works with the entire image (Maes et al. 1997).”
Dense image registration through MRFs and efficient linear programming (2008, methodology): “We run the gradient-based registrations with two different optimizers, a standard gradient-descent and a quasi-Newton optimizer using line search strategies (Klein et al., 2007).”
elastix: A Toolbox for Intensity-Based Medical Image Registration (2010, methodology): “mization method are discussed in [23] and [24].”
Fast parallel image registration on CPU and GPU for diagnostic classification of Alzheimer's disease (2013, methodology): “Examples of the ﬁrst are the mean square difference (MSD), normalized correlation (NC), and mutual information (MI) (Maes et al., 1997) measure; examples of the last are the bending energy (Rueckert et al., 1999) and rigidity penalty term (Staring et al., 2007).”
Deformable Medical Image Registration: A Survey (2013, methodology): “[400] studied two variants of gradient descent.”
Survey of Medical Image Registration (2013, methodology): “Klein et al compared the performance of eight optimization methods: gradient descent (with two different step size selection algorithms), quasi-Newton, nonlinear conjugate gradient, Kiefer-Wolfowitz, simultaneous perturbation, Robbins-Monroe, and evolution strategy [110].”
Medical image registration: a review (2014, unknown): “Acomparisonamongeightoptimisationalgorithmsfor non-rigidmedicalimageregistrationbasedoncubic B-splineandthemaximisationoftheMIisdescribedin Kleinetal.”
White matter lesion extension to automatic brain tissue segmentation on MRI (2009, unknown): “Computation time may be reduced by faster registration methods, e.g. Klein et al. (2007) .”
A Review on Medical Image Registration as an Optimization Problem (2017, methodology): “Similar to TPS, B-splines also optimize the projective correlation between images by solving a series of parameters [40].”
Adaptive Stochastic Gradient Descent Optimisation for Image Registration (2009, methodology): “In Klein et al. (2007), it was shown for a number of medical image registration applications that RM outperforms several well-known deterministic optimisation meth-ods, such as quasi-Newton and nonlinear conjugate gradient.”
MRF-Based Deformable Registration and Ventilation Estimation of Lung CT (2013, methodology): “A similar approach has been introduced for continuous optimization in [8].”
Combination Strategies in Multi-Atlas Image Segmentation: Application to Brain MR Data (2009, methodology): “A stochastic gradient descent optimizer was used, because it provides a good trade-off between precision and computation time [ 29 ].”