Bayesian Segmentation of Atrium Wall Using Globally-Optimal Graph Cuts on 3D Meshes

Efficient segmentation of the left atrium (LA) wall from delayed enhancement MRI is challenging due to inconsistent contrast, combined with noise, and high variation in atrial shape and size. We present a surface-detection method that is capable of extracting the atrial wall by computing an optimal a-posteriori estimate. This estimation is done on a set of nested meshes, constructed from an ensemble of segmented training images, and graph cuts on an associated multi-column, proper-ordered graph. The graph/mesh is a part of a template/model that has an associated set of learned intensity features. When this mesh is overlaid onto a test image, it produces a set of costs which lead to an optimal segmentation. The 3D mesh has an associated weighted, directed multi-column graph with edges that encode smoothness and inter-surface penalties. Unlike previous graph-cut methods that impose hard constraints on the surface properties, the proposed method follows from a Bayesian formulation resulting in soft penalties on spatial variation of the cuts through the mesh. The novelty of this method also lies in the construction of proper-ordered graphs on complex shapes for choosing among distinct classes of base shapes for automatic LA segmentation. We evaluate the proposed segmentation framework on simulated and clinical cardiac MRI.

[1]  Xiaodong Wu,et al.  Optimal Net Surface Problems with Applications , 2002, ICALP.

[2]  Guang-Zhong Yang,et al.  Medical Image Computing and Computer-Assisted Intervention - MICCAI 2009, 12th International Conference, London, UK, September 20-24, 2009, Proceedings, Part II , 2009, MICCAI.

[3]  Daniel Rueckert,et al.  Left atrium segmentation for atrial fibrillation ablation , 2008, SPIE Medical Imaging.

[4]  Baba C. Vemuri,et al.  Shape Modeling with Front Propagation: A Level Set Approach , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Hiroshi Ishikawa,et al.  Exact Optimization for Markov Random Fields with Convex Priors , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[7]  David Eppstein,et al.  The Crust and the beta-Skeleton: Combinatorial Curve Reconstruction , 1998, Graph. Model. Image Process..

[8]  Ross T. Whitaker,et al.  Topology, Accuracy, and Quality of Isosurface Meshes Using Dynamic Particles , 2007, IEEE Transactions on Visualization and Computer Graphics.

[9]  Xiaodong Wu,et al.  Optimal Surface Segmentation in Volumetric Images-A Graph-Theoretic Approach , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Norbert Rahn,et al.  Automatic Left Atrium Segmentation by Cutting the Blood Pool at Narrowings , 2005, MICCAI.

[11]  Robin Milner,et al.  On Observing Nondeterminism and Concurrency , 1980, ICALP.

[12]  Xiaodong Wu,et al.  Globally optimal surface segmentation using regional properties of segmented objects , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Guido Gerig,et al.  Medical Image Computing and Computer-Assisted Intervention - MICCAI 2005, 8th International Conference, Palm Springs, CA, USA, October 26-29, 2005, Proceedings, Part II , 2005, MICCAI.

[14]  Xiaodong Wu,et al.  Optimal Graph Search Segmentation Using Arc-Weighted Graph for Simultaneous Surface Detection of Bladder and Prostate , 2009, MICCAI.

[15]  Joshua J. E. Blauer,et al.  New magnetic resonance imaging based method to define extent of left atrial wall injury after the ablation of atrial fibrillation , 2008 .

[16]  Yi Gao,et al.  Segmentation of the endocardial wall of the left atrium using local region-based active contours and statistical shape learning , 2010, Medical Imaging.