Directed graph based image registration

Abstract

In this paper, a novel image registration method is proposed to achieve accurate registration between images having large shape differences with the help of a set of appropriate intermediate templates. We first demonstrate that directionality is a key factor in both pairwise image registration and groupwise registration, which is defined in this paper to describe the influence of the registration direction and paths on the registration performance. In our solution, the intermediate template selection and intermediate template guided registration are two coherent steps with directionality being considered. To take advantage of the directionality, a directed graph is built based on the asymmetric distance defined on all ordered image pairs in the image population, which is fundamentally different from the undirected graph with symmetric distance metrics in all previous methods, and the shortest distance between template and subject on the directed graph is calculated. The allocated directed path can be thus utilized to better guide the registration by successively registering the subject through the intermediate templates one by one on the path towards the template. The proposed directed graph based solution can also be used in groupwise registration. Specifically, by building a minimum spanning arborescence (MSA) on the directed graph, the population center, i.e., a selected template, as well as the directed registration paths from all the rest of images to the population center, is determined simultaneously. The performance of directed graph based registration algorithm is demonstrated by the spatial normalization on both synthetic dataset and real brain MR images. It is shown that our method can achieve more accurate registration results than both the undirected graph based solution and the direct pairwise registration.

Registration of challenging pre-clinical brain images

“…In Section 1, we mentioned the work of Jia et al (2012) as being conceptually similar to our approach. They described an image registration technique based on a directed graph approach that optimally selects the reference image and the registration paths from each image to that reference.…”

“…This method depends on the PCA ability to adequately represent the range of morphological variation in the population; this may not be possible in small populations with large variation. Conceptually, the closest work to ours (Jia et al, 2012) uses a (different) directed graph approach to determine optimal registration paths. However, this approach and other related approaches are focussed on non-rigid morphological (shape) variations rather than pathology and assume that good affine registration already exists for the population.…”

Predict brain MR image registration via sparse learning of appearance and transformation

“…The high inter-image variation could potentially hinder the registration of two images (Jia et al, 2012a; Munsell et al, 2012). For example, in order to register the non-root images with the root directly (i.e., via state-of-the-art methods), we should better utilize the distribution of the dataset (i.e., in the tree structure) and acquire the transformation fields for the non-root images recursively.…”

Multi sequence average templates for aging and neurodegenerative disease populations

“…As for nonlinear registration, these templates can be used as intermediate registration targets even in cases where the intended final application is to register all subjects to one healthy or younger average brain. Intermediate templates have been previously used for various registration tasks, particularly when there exists a large difference between source and target templates 35 – 38 . Disease appropriate average templates can be used as intermediate registration targets to improve nonlinear registration, using the following steps: Linearly register patient brain image(s) to the disease appropriate template.…”