Title | ||
---|---|---|
Interactive Hierarchical-Flow Segmentation of Scar Tissue From Late-Enhancement Cardiac MR Images |
Abstract | ||
---|---|---|
We propose a novel multi-region image segmentation approach to extract myocardial scar tissue from 3-D whole-heart cardiac late-enhancement magnetic resonance images in an interactive manner. For this purpose, we developed a graphical user interface to initialize a fast max-flow-based segmentation algorithm and segment scar accurately with progressive interaction. We propose a partially-ordered Potts (POP) model to multi-region segmentation to properly encode the known spatial consistency of cardiac regions. Its generalization introduces a custom label/region order constraint to Potts model to multi-region segmentation. The combinatorial optimization problem associated with the proposed POP model is solved by means of convex relaxation, for which a novel multi-level continuous max-flow formulation, i.e., the hierarchical continuous max-flow (HMF) model, is proposed and studied. We demonstrate that the proposed HMF model is dual or equivalent to the convex relaxed POP model and introduces a new and efficient hierarchical continuous max-flow based algorithm by modern convex optimization theory. In practice, the introduced hierarchical continuous max-flow based algorithm can be implemented on the parallel GPU to achieve significant acceleration in numerics. Experiments are performed in 50 whole heart 3-D LE datasets, 35 with left-ventricular and 15 with right-ventricular scar. The experimental results are compared to full-width-at-half-maximum and Signal-threshold to reference-mean methods using manual expert myocardial segmentations and operator variabilities and the effect of user interaction are assessed. The results indicate a substantial reduction in image processing time with robust accuracy for detection of myocardial scar. This is achieved without the need for additional region constraints and using a single optimization procedure, substantially reducing the potential for error. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/TMI.2013.2282932 | Medical Imaging, IEEE Transactions |
Keywords | Field | DocType |
Potts model,biological tissues,biomedical MRI,cardiology,combinatorial mathematics,diseases,feature extraction,graphical user interfaces,graphics processing units,image segmentation,medical image processing,optimisation,3D whole-heart cardiac late-enhancement magnetic resonance image,HMF model,POP model convex relaxation,Potts model custom label constraint,Potts model region order constraint,cardiac region spatial consistency encoding,combinatorial optimization problem,fast max-flow-based segmentation algorithm,full-width-at-half-maximum method,graphical user interface,hierarchical continuous max-flow based algorithm,hierarchical continuous max-flow model,image processing time reduction,interactive hierarchical-flow segmentation,late-enhancement cardiac MR image,left ventricular scar,manual expert myocardial segmentation,modern convex optimization theory,multilevel continuous max-flow formulation,multiregion image segmentation,myocardial scar tissue extraction,operator variability,parallel GPU,partially-ordered Potts model,right ventricular scar,robust myocardial scar detection accuracy,scar segmentation,signal-threshold to reference-mean method,user interaction effect,whole heart 3D LE dataset,Convex relaxation,dual optimization method,image segmentation,late-enhancement magnetic resonance imaging (MRI),max-flow | Computer vision,Scale-space segmentation,Computer science,Segmentation,Segmentation-based object categorization,Image processing,Image segmentation,Feature extraction,Artificial intelligence,Convex optimization,Potts model | Journal |
Volume | Issue | ISSN |
33 | 1 | 0278-0062 |
Citations | PageRank | References |
27 | 1.40 | 20 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Martin Rajchl | 1 | 421 | 34.67 |
Jing Yuan | 2 | 182 | 12.30 |
James A. White | 3 | 52 | 7.70 |
Eranga Ukwatta | 4 | 154 | 18.10 |
John Stirrat | 5 | 37 | 2.42 |
Cyrus Nambakhsh | 6 | 98 | 5.10 |
Feng Li | 7 | 42 | 4.24 |
Terry M. Peters | 8 | 1335 | 181.71 |