Segmentation of Anatomical Structures by Connected Statistical Models

Abstract

This paper presents a framework for the segmentation of anatomical structures in medical imagery by connected statistical models. The framework is based on three types of models: first, generic models which operate directly on image intensities, second, connecting models that impose restrictions on the spatial relationship of generic models, and third, a supervising model that represents an arbitrary number of generic and connecting models. In this paper, the statistical model of appearance is used as the generic model, whiles the statistical model of topology, obtained by applying principal component analysis (PCA) on aligned pose and shape parameters of the generic model, is used as the connecting model. The performance of such connected statistical model is demonstrated on anterior-posterior (AP) X-ray images of the hips and pelvis and compared to the modelling by one and six unconnected generic models. The most accurate and robust results were obtained by two-level hierarchical modelling, wherein connected statistical models were used first, followed by unconnected statistical models.

Computational anatomy for multi-organ analysis in medical imaging: A review

“…CoDeM►Han and Prince, 2003; ArtM► Anas et al, 2016;Chen et al ,2014;Chen et al, 2010;Kamojima and Miyata, 2004;Kuo et al, 2009;Martin-Fernandez et al, 2009;Miyata et al, 2003 Pelvis GlM►Li et al, 2016; CoDeM► Costa et al, 2007;Hensel et al, 2007;Ma et al, 2013;Rousson et al, 2005;Song et al, 2013; MuLeM► Chaney et al, 2013;Fletcher et al, 2002;Jeong et al, 2006;Lu et al, 2007;Merck et al, 2008;Pizer et al, 2005;SeqM► Chandra et al, 2016;Jeong et al, 2008;Ma et al, 2010;Pizer et al, 2005; MaLrM► Gao et al, 2016;Seifert et al, 2009; AtM► Akhondi-Asl et al, 2014;Weisenfeld and Warfield, 2011; Hip CoDeM► Kainmüeller et al, 2009b; MuLeM► Bukovec et al, 2011;Yokota et al, 2009;SeqM► Yokota et al, 2013; MaLrM► Glocker et al, 2012;Montillo et al, 2011; ArtM► Balestra et al, 2014;Kainmüeller et al, 2009a;Yokota et al, 2009;Knee GlM►Fripp et al, 2007; CoDeM► Pang et al, 2015;Uzumbas et al, 2013;ArtM►Constantinescu et al, 2016;...…”

“…However, only the center of mass was used in the global model, thus limiting its capability to characterize complex inter-organ relations. Bukovec et al (Bukovec et al, 2011) presented a more general and flexible approach, creating a threelevels framework that combines PCA-based shape and appearance models. In this latter approach, higher-level topological models operated on the parameterization of previous models.…”