Multichannel image registration is an important challenge in medical image analysis. Multichannel images result from modalities such as dual-energy CT or multispectral microscopy. Besides, multichannel feature images can be derived from acquired images, for instance, by applying multiscale feature banks to the original images to register. Multichannel registration techniques have been proposed, but most of them are applicable to only two multichannel images at a time. In the present study, we propose to formulate multichannel registration as a groupwise image registration problem. In this way, we derive a method that allows the registration of two or more multichannel images in a fully symmetric manner (i.e., all images play the same role in the registration procedure), and therefore, has transitive consistency by definition. The method that we introduce is applicable to any number of multichannel images, any number of channels per image, and it allows to take into account correlation between any pair of images and not just corresponding channels. In addition, it is fully modular in terms of dissimilarity measure, transformation model, regularisation method, and optimisation strategy. For two multimodal datasets, we computed feature images from the initially acquired images, and applied the proposed registration technique to the newly created sets of multichannel images. MIND descriptors were used as feature images, and we chose total correlation as groupwise dissimilarity measure. Results show that groupwise multichannel image registration is a competitive alternative to the pairwise multichannel scheme, in terms of registration accuracy and insensitivity towards registration reference spaces.

The most widespread technique used to register sets of medical images consists of selecting one image as fixed reference, to which all remaining images are successively registered. This pairwise scheme requires one optimization procedure per pair of images to register. Pairwise mutual information is a common dissimilarity measure applied to a large variety of datasets. Alternative methods, called groupwise registrations, have been presented to register two or more images in a single optimization procedure, without the need of a reference image. Given the success of mutual information in pairwise registration, we adapt one of its multivariate versions, called total correlation, in a groupwise context. We justify the choice of total correlation among other multivariate versions of mutual information, and provide full implementation details. The resulting total correlation measure is remarkably close to measures previously proposed by Huizinga et al. based on principal component analysis. Our experiments, performed on five quantitative imaging datasets and on a dynamic CT imaging dataset, show that total correlation yields registration results that are comparable to Huizinga’s methods. Total correlation has the advantage of being theoretically justified, while the measures of Huizinga et al. were designed empirically. Additionally, total correlation offers an alternative to pairwise mutual information on quantitative imaging datasets.

In quantitative magnetic resonance imaging (qMRI), quantitative tissue properties can be estimated by fitting a signal model to the voxel intensities of a series of images acquired with different settings. To obtain reliable quantitative measures, it is necessary that the qMRI images are spatially aligned so that a given voxel corresponds in all images to the same anatomical location. The objective of the present study is to describe and evaluate a novel automatic groupwise registration technique using a dissimilarity metric based on an approximated form of total correlation. The proposed registration method is applied to five qMRI datasets of various anatomical locations, and the obtained registration performances are compared to these of a conventional pairwise registration based on mutual information. The results show that groupwise total correlation yields better registration performances than pairwise mutual information. This study also establishes that the formulation of approximated total correlation is quite analogous to two other groupwise metrics based on principal component analysis (PCA). Registration performances of total correlation and these two PCA-based techniques are therefore compared. The results show that total correlation yields performances that are analogous to these of the PCAbased techniques. However, compared to these PCA-based metrics, total correlation has two main advantages. Firstly, it is directly derived from a multivariate form of mutual information, while the PCA-based metrics were obtained empirically. Secondly, total correlation has the advantage of requiring no user-defined parameter.