Segmentation of 4D Cardiac MR Images Using a Probabilistic Atlas and the EM Algorithm

By M. Lorenzo-Valdés, G. I. Sanchez-Ortiz, R. Mohiaddin, Daniel Rueckert. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2003

326 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bc99db0a24c81570fdad3d2418c86e9cd1d26398

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

Combination Strategies in Multi-Atlas Image Segmentation: Application to Brain MR Data (2009, background): “Information from several reference images can be combined into an average atlas [12], [13] or, if probability values for each particular location are included, into a so-called probabilistic atlas [1], [2], [ 4 ], [9].”
Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI (2008, methodology): “In (Lorenzo-Valdés et al., 2004), the authors use the EM algorithm with a probabilistic 4D atlas of the heart for automatic atlas-based segmentation.”
A review of segmentation methods in short axis cardiac MR images (2011, methodology): “The EM segmentation result can be embedded in a cost matrix for dynamic programming (Pednekar et al., 2006), or precedes a step based on Markov Random Fields (MRF) in order to incorporate spatial correlations into the segmentation process (Gering, 2003).”
A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion (2015, unknown): “Similar to (Lorenzo-Valdés et al., 2004; KuklisovaMurgasova et al., 2011), we transform the segmentations of the subjects images to the template space using the non-rigid transformation established in the previous section and compute the probabilistic atlas by averaging all the segmentations.”
A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI (2015, methodology): “…2009; Liu et al., 2012), deformable methods (Billet et al., 2009; Ben Ayed et al., 2009; Chang et al., 2010; Pluempitiwiriyawej et al., 2005), active appearance and shape models (AAM/ASM) (Zhang et al., 2010; Assen et al., 2006) and atlas models (Zhuang et al., 2008; Lorenzo-Vald´es et al., 2004).”
Automatic Model-Based Segmentation of the Heart in CT Images (2008, methodology): “Segmentation of the ventricles using nonrigid registration between a statistical cardiac atlas and MR images was presented in [27] and [28].”
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks (2019, methodology): “Later, [17] used a 4D Markov Random Fields for cardiac segmentation.”
Multivariate Mixture Model for Myocardial Segmentation Combining Multi-Source Images (2016, methodology): “pathologies result in heterogeneous intensity of the myocardium, making the assumption of a simple distribution invalid; for example the single component Gaussian density function is widely used in the segmentation of bSSFP cine CMR [3], [8], but can not be used for LGE CMR.”