We investigate incorporating structural information from segmentation into agroupwise registration framework. Previous work by Petrovic et al., using MR brainimages, showed that using tissue fractions to help construct an intensity referenceimage gives better results than just using intensity images alone. In their work, aGaussian Mixture Model (GMM) was fitted to the 1D intensity histogram, then usedto construct tissue fraction images for each example. The mean fraction images were then used to create an artificial intensity reference for the registration.By using only the mean, this discarded much of the structural information. Weretain all this information, and augment each intensity image with its set of tissuefraction images (and also intensity gradient images) to form an image ensemble foreach example. We then perform groupwise registration using these ensembles ofimages. This groupwise ensemble registration is applied to the same real-world dataset as used by Petrovic et al. Ground-truth labels enable quantitative evaluation to be performed. It is shown that ensemble registration gives quantitatively better results than the algorithm of Petrovic et al., and that the best results are achieved when more than one of the three types of images (intensity, tissue fraction and gradient) are included as an ensemble.