Optimization of mutual information for multiresolution image registration

By Philippe Thévenaz, Michael A. Unser. IEEE Transactions on Image Processing, 2000

819 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6d143237a6b2c627aa5c1cc035416be87bbb9888

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

Citations in the corpus

Mutual-information-based registration of medical images: a survey (2003, methodology): “MR-CT: A popular combination, and one of the earliest described, is registration of MR and CT images [11], [41], [43], [44], [49], [50], [53], [57], [69], [92], [97], [100], [103],”
Medical image registration using mutual information (2003, methodology): “Thévenaz and Unser [110] presented a gradient based optimization strategy using analytic expressions for the gradient of MI computed using cubic spline based image interpolation and Parzen windowing of the joint intensity histogram.”
Estimating mutual information using B-spline functions – an improved similarity measure for analysing gene expression data (2004, background): “Also aside the bioinformatics field, mutual information is widely utilised in diverse disciplines, such as physics [14], image recognition [15], speech recognition [16], and various others.”
elastix: A Toolbox for Intensity-Based Medical Image Registration (2010, background): “For example, the number of joint histogram bins that is used for computing MI and NMI could be gradually increased, as was suggested in [45].”
Fast parametric elastic image registration (2003, background): “based similarity measures, such as information-based measures [41], especially mutual information [17], or weightednorms.”
Evaluation of Optimization Methods for Nonrigid Medical Image Registration Using Mutual Information and B-Splines (2007, methodology): “The design of the algorithm is largely based on the papers by Rueckert et al. [5], Mattes et al. [4], and Thévenaz and Unser [21].”
Medical image registration: a review (2014, methodology): “Several optimisation algorithms have been used in the ﬁeld of medical image registration, including: the Powell’s method (Collignon et al. 1997; Maes et al. 1997; Pluim et al. 2000; Lavely et al. 2004; Pluim et al. 2004; Auer et al. 2005; Meyer 2007; Sun et al. 2007; Oliveira and Tavares 2011), the ”
Brain Functional Localization: A Survey of Image Registration Techniques (2007, methodology): “hand, multiresolution and multiscale optimization frameworks have shown to be effective in obtaining a faster and more robust convergence toward the solution [136]–[138].”
Deformable Medical Image Registration: A Survey (2013, methodology): “Based on the LM algorithm, Thevanez and Unser [413] proposed an efﬁcient optimizer for mutual information driven registration.”
Adaptive Stochastic Gradient Descent Optimisation for Image Registration (2009, methodology): “Both MI and NMI were implemented using cubic B-spline Parzen windows, as in Thévenaz and Unser (2000), with a 32 × 32 joint histogram.”
Multiresolution registration of remote sensing imagery by optimization of mutual information using a stochastic gradient (2003, methodology): “Prior work on optimization techniques for image registration can be found in references [3]–[5] and [9]–[11].”
An automatic image registration for applications in remote sensing (2005, methodology): “Other warping functions such as B-splines have been used to achieve subpixel accuracy [9], [13].”
Information-theoretic analysis of interscale and intrascale dependencies between image wavelet coefficients (2001, background): “Mutual information may also be useful in practical image processing algorithms; see recent research on image registration [30, 31], blind source separation [32, 33], and image restoration [34] for examples.”