Iterative multi-atlas-based multi-image segmentation with tree-based registration

Abstract

In this paper, we present a multi-atlas-based framework for accurate, consistent and simultaneous segmentation of a group of target images. Multi-atlas-based segmentation algorithms consider concurrently complementary information from multiple atlases to produce optimal segmentation outcomes. However, the accuracy of these algorithms relies heavily on the precise alignment of the atlases with the target image. In particular, the commonly used pairwise registration may result in inaccurate alignment especially between images with large shape differences. Additionally, when segmenting a group of target images, most current methods consider these images independently with disregard of their correlation, thus resulting in inconsistent segmentations of the same structures across different target images. We propose two novel strategies to address these limitations: 1) a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 2) an iterative groupwise segmentation method for simultaneous consideration of segmentation information propagated from all available images, including the atlases and other newly segmented target images. Evaluation based on various datasets indicates that the proposed multi-atlas-based multi-image segmentation (MABMIS) framework yields substantial improvements in terms of consistency and accuracy over methods that do not consider the group of target images holistically.

Accurate non-rigid registration based on heuristic tree for registering point sets with large deformation

“…Therefore, the similarity measurement is the most important for the tree building. Jia et al [21] simply used averaged intensity difference to measure the similarity which is not suitable for nonrigid registration. Here, we present a shape similarity measurement which is done by implementing the affine ICP with bidirectional distance to register two point sets [15].…”

“…Jia et al [21] proposed the tree-based approach to handle this case, but it employed the mean squared difference of the intensity differences and was used primarily for image segmentation which didn't meet our requirement of point set registration. Moreover, Ying et al [22] proposed to use intensity differences to build the graph, and then apply a groupwise nonlinear registration method for image registration.…”

Groupwise multi-atlas segmentation of the spinal cord’s internal structure

“…In a typical multi-atlas framework, each atlas is non-rigidly registered to the target in a pairwise fashion (i.e., each atlas-target registration is computed independently). More recently, “groupwise” registration approaches (i.e., pre-alignment of the atlas information to a common groupwise space) have become increasingly popular (Balci et al, 2007; Bhatia et al, 2007; Cootes et al, 2001; Cootes et al, 1995; Depa et al, 2011; Jia et al, 2012; Wolz et al, 2010). Groupwise registrations have several benefits, primarily: (1) they reduce the computational burden by requiring only a single registration from the groupwise space to the target space, and (2) through projecting the co-registered atlas information into a low dimensional space (i.e., a “manifold”) (Cao et al, 2011; Jia et al, 2012; Wolz et al, 2010), they provide a natural framework for modeling the relationships between atlases – e.g., for atlas selection (Aljabar et al, 2009; Rohlfing et al, 2004).…”

A Bayesian approach to the creation of a study-customized neonatal brain atlas

“…On the other hand, atlas-based analysis (ABA) can be performed on an original image space. Namely, a pre-segmented set of anatomical structures for the entire brain (parcellation map) in a template space can be transformed to the original image to quantify the volume of each anatomical structure, as well as to measure the intensities of the images (Aljabar et al., 2009; Collins et al, 1995; Heckemann et al, 2006; Heckemann et al, 2010; Jia et al, 2012; Joshi et al, 2004; Klein and Hirsch, 2005; Maldjian et al, 2003; Mori et al, 2008; Oishi et al, 2009; Oishi et al., 2008; Tzourio-Mazoyer et al, 2002; Warfield et al, 2004). This ABA is suitable for creating a “growth percentile chart” of each anatomical structure, which is necessary to interpret individual images based on population statistics (Oishi et al, 2013).…”