Patch-Based Label Fusion with Spatio-Temporal Graph Cuts for Cardiac MR Images

A patch-based method is proposed for cardiac MR image sequence segmentation, combined with the graph cuts algorithm to guarantee spatio-temporal smoothness of the segmentation. It was tested on the challenge training set with 83 subjects and achieved an average Dice metric of 0.792 for the myocardium.

[1]  Colin Studholme,et al.  A Supervised Patch-Based Approach for Human Brain Labeling , 2011, IEEE Transactions on Medical Imaging.

[2]  Daniel Rueckert,et al.  A Probabilistic Patch-Based Label Fusion Model for Multi-Atlas Segmentation With Registration Refinement: Application to Cardiac MR Images , 2013, IEEE Transactions on Medical Imaging.

[3]  Jayaram K. Udupa,et al.  New variants of a method of MRI scale standardization , 2000, IEEE Transactions on Medical Imaging.

[4]  Xiang Lin,et al.  Automated Detection of Left Ventricle in 4D MR Images: Experience from a Large Study , 2006, MICCAI.

[5]  Alistair A. Young,et al.  The Cardiac Atlas Project—an imaging database for computational modeling and statistical atlases of the heart , 2011, Bioinform..

[6]  Caroline Petitjean,et al.  A review of segmentation methods in short axis cardiac MR images , 2011, Medical Image Anal..

[7]  D. Louis Collins,et al.  Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation , 2011, NeuroImage.

[8]  Daniel Rueckert,et al.  Multi-atlas based segmentation of brain images: Atlas selection and its effect on accuracy , 2009, NeuroImage.

[9]  Marie-Pierre Jolly,et al.  Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images , 2001, ICCV.

[10]  D. Rueckert,et al.  Multi-Atlas Based Segmentation with Local Label Fusion for Right Ventricle MR Images , 2012 .

[11]  Chengwen Chu,et al.  Multi-organ Abdominal CT Segmentation Using Hierarchically Weighted Subject-Specific Atlases , 2012, MICCAI.