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

By Alejandro F Frangi, Daniel Rueckert, Julia Anne Schnabel, Wiro J. Niessen. IEEE Transactions on Medical Imaging, 2002

431 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7c6f57511eb42dd5e2f43a62b11e7fcbfcbf47d6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Statistical shape models for 3D medical image segmentation: A review (2009, methodology): “(2004)) and gradient descent optimization (used by Freedman et al. (2005) and Nain et al.”
A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion (2015, neutral): “Email address: w.bai@imperial.ac.uk (Wenjia Bai) 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…”
Survey of Medical Image Registration (2013, background): “Such problems have not prevented these techniques ﬁnding widespread use in the brain [54], the chest [55] the heart [56,57], the liver [58], the breast [59,60] etc.”
Robust Brain Extraction Across Datasets and Comparison With Publicly Available Methods (2011, methodology): “This is accomplished by a method very similar to [37].”
Non-rigid image registration: theory and practice. (2004, background): “Such problems have not prevented these techniques finding widespread use (in the brain [61], the chest [62] the heart [63, 64], the liver [65], the breast [66, 67] etc.”
Generalized Overlap Measures for Evaluation and Validation in Medical Image Analysis (2006, methodology): “[43] used the label consistency measure, which is essentially a TC, and a Kappa statistic measure that is related to the DSC, for Free Form Deformation registration of labelled MR cardiac images and found no significant difference between them.”
Four-Chamber Heart Modeling and Automatic Segmentation for 3-D Cardiac CT Volumes Using Marginal Space Learning and Steerable Features (2008, neutral): “Compared to other approaches [18], [19], [29] for establishing point correspondence, our solution is simple and each shape is processed independently.”
A review of segmentation methods in short axis cardiac MR images (2011, background): “Spatial (and temporal if required) alignment of manually segmented contours or images is of utmost importance to compensate for differences in ventricle position and size, and can be very difficult, especially in 3D (Frangi et al., 2002).”
Automatic construction of 3-D statistical deformation models of the brain using nonrigid registration (2003, methodology): “In [32], we described an automated way in which correspondences between the surfaces of different shapes are established via a nonrigid registration algorithm [33].”