Automatic construction of multiple-object three-dimensional statistical shape models: application to cardiac modeling

Abstract

A novel method is introduced for the generation of landmarks for three-dimensional (3-D) shapes and the construction of the corresponding 3-D statistical shape models. Automatic landmarking of a set of manual segmentations from a class of shapes is achieved by 1) construction of an atlas of the class, 2) automatic extraction of the landmarks from the atlas, and 3) subsequent propagation of these landmarks to each example shape via a volumetric nonrigid registration technique using multiresolution B-spline deformations. This approach presents some advantages over previously published methods: it can treat multiple-part structures and requires less restrictive assumptions on the structure's topology. In this paper, we address the problem of building a 3-D statistical shape model of the left and right ventricle of the heart from 3-D magnetic resonance images. The average accuracy in landmark propagation is shown to be below 2.2 mm. This application demonstrates the robustness and accuracy of the method in the presence of large shape variability and multiple objects.

A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion

“…For example, in (Frangi et al, 2002), the position, orientation and size differences of the subject surface meshes are removed. The remaining information for analysis is local deformations of the surface meshes.…”

“…In terms of the imaging modality, cine MR and CT are often used to infer shape information (Frangi et al, 2002;Fonseca et al, 2011;Hoogendoorn et al, 2013), whereas tagged MR, cine MR and US are often used to capture cardiac motion (Chandrashekara et al, 2003;Suinesiaputra et al, 2009;Duchateau et al, 2011). In order to characterise the cardiac myocardial fibre architecture, diffusion tensor MRI (DT-MRI) is used for imaging ex vivo human hearts (Lombaert et al, 2012).…”

“…Based on the mean transformation, we determine a new template space, transform all the subject images to the new template space and compute the average image in the new space. The template image built in this way can be regarded as an image which represents the average heart size, position and orientation and therefore avoids or reduces the bias towards a specific subject (Frangi et al, 2002;Kuklisova-Murgasova et al, 2011;Rueckert et al, 2001). Figure 3 illustrates the computation of the new template space based on the mean transformation.…”

“…Principal component analysis (PCA) is often applied for shape analysis (Frangi et al, 2002;Lötjönen et al, 2004;Medrano-Gracia et al, 2014). PCA looks for a new coordinate system that explains the input data so that the greatest variance of the data lies on the first coordinate (the first principal component or the first mode), the second variance of the data on the second coordinate and so on.…”

Image registration and atlas-based segmentation of cardiac outflow velocity profiles

“…Atlases have broad application in medical image segmentation and registration and are often used in computer aided diagnosis to measure the shape of an object or detect the morphological differences between patient groups. Various techniques for atlas construction are developed for different human organs, like the heart [25,26,27] and especially the brain [28,29,30,31,32,33,34,35,36,37]. In this paper we use a statistical model as an atlas and an in-silico phantom model for evaluation.…”