Mattes mutual information metric configuration object
metric = registration.metric.MattesMutualInformation() constructs a MattesMutualInformation object.
Number of spatial samples used to compute the metric.
NumberOfSpatialSamples is a positive scalar integer value that defines the number of random pixels imregister uses to compute the metric. Your registration results are more reproducible (at the cost of performance) as you increase this value. imregister only uses NumberOfSpatialSamples when UseAllPixels = 0 (false). The default value for NumberOfSpatialSamples is 500.
Number of histogram bins used to compute the metric.
NumberOfHistogramBins is a positive scalar integer value that defines the number of bins imregister uses to compute the joint distribution histogram. The default value is 50, and the minimum value is 5.
Logical scalar that specifies whether imregister should use all pixels in the overlap region of the images to compute the metric.
You can achieve significantly better performance if you set this property to 0 (false). When UseAllPixels = 0, the NumberOfSpatialSamples property controls the number of random pixel locations that imregister uses to compute the metric. The results of your registration might not be reproducible when UseAllPixels = 0. This is because imregister selects a random subset of pixels from the images to compute the metric. The default value forUseAllPixels is 1 (true).
Metric used to maximize the number of coincident pixels with the same relative brightness value. This metric is best suited for images with different brightness ranges.
Value. To learn how value classes affect copy operations, see Copying Objects in the MATLAB® documentation.
Larger values of mutual information correspond to better registration results. You can examine the computed values of Mattes mutual information if you enable 'DisplayOptimization' when you call imregister, for example:
movingRegistered = imregister(moving,fixed,'rigid',optimizer,metric,'DisplayOptimization',true);
Register two MRI images of a knee that were obtained using different protocols.
Read the images into the workspace.
fixed = dicomread('knee1.dcm'); moving = dicomread('knee2.dcm');
View the misaligned images.
Create the optimizer configuration object suitable for registering images from different sensors.
optimizer = registration.optimizer.OnePlusOneEvolutionary;
Create the MattesMutualInformation metric configuration object.
metric = registration.metric.MattesMutualInformation
metric = registration.metric.MattesMutualInformation Properties: NumberOfSpatialSamples: 500 NumberOfHistogramBins: 50 UseAllPixels: 1
Tune the properties of the optimizer so that the problem will converge on a global maxima. Increase the number of iterations the optimizer will use to solve the problem.
optimizer.InitialRadius = 0.009; optimizer.Epsilon = 1.5e-4; optimizer.GrowthFactor = 1.01; optimizer.MaximumIterations = 300;
Register the moving and fixed images.
movingRegistered = imregister(moving, fixed, 'affine', optimizer, metric);
View the registered images.
figure; imshowpair(fixed, movingRegistered,'Scaling','joint');
The imregister function uses an iterative process to register images. The metric you pass to imregister defines the image similarity metric for evaluating the accuracy of the registration. An image similarity metric takes two images and returns a scalar value that describes how similar the images are. The optimizer you pass to imregister defines the methodology for minimizing or maximizing the similarity metric.
Mutual information metrics are information theoretic techniques for measuring how related two variables are. These algorithms use the joint probability distribution of a sampling of pixels from two images to measure the certainty that the values of one set of pixels map to similar values in the other image. This information is a quantitative measure of how similar the images are. High mutual information implies a large reduction in the uncertainty (entropy) between the two distributions, signaling that the images are likely better aligned.
The Mattes mutual information algorithm uses a single set of pixel locations for the duration of the optimization, instead of drawing a new set at each iteration. The number of samples used to compute the probability density estimates and the number of bins used to compute the entropy are both user selectable. The marginal and joint probability density function is evaluated at the uniformly spaced bins using the samples. Entropy values are computed by summing over the bins. Zero-order and third-order B-spline kernels are used to compute the probability density functions of the fixed and moving images, respectively.
 Rahunathan, Smriti, D. Stredney, P. Schmalbrock, and B.D. Clymer. Image Registration Using Rigid Registration and Maximization of Mutual Information. Poster presented at: MMVR13. The 13th Annual Medicine Meets Virtual Reality Conference; 2005 January 26–29; Long Beach, CA.
 D. Mattes, D.R. Haynor, H. Vesselle, T. Lewellen, and W. Eubank. "Non-rigid multimodality image registration." (Proceedings paper).Medical Imaging 2001: Image Processing. SPIE Publications, 3 July 2001. pp. 1609–1620.
Use imregconfig to construct a metric configuration for typical image registration scenarios.