Structured graph regularized shape prior and cross-entropy induced active contour model for myocardium segmentation in CTA images.
Yanmin NiuLan QinXuchu WangPublished in: Neurocomputing (2019)
Keyphrases
- shape prior
- active contour model
- segmentation method
- region based segmentation
- segmentation algorithm
- active contours
- level set framework
- level set
- cross entropy
- geodesic active contours
- image segmentation
- graph cuts
- segmentation result
- shape variations
- object segmentation
- accurate segmentation
- curve evolution
- automatic segmentation
- object boundaries
- region growing
- prior shape
- deformable models
- variational framework
- shape model
- gradient vector flow
- intensity distribution
- level set method
- image analysis
- energy function
- input image
- active shape model
- mumford shah functional
- pose invariant
- snake model
- energy functional
- statistical models
- edge detection
- energy minimization
- prior knowledge
- global optimization
- semi supervised
- bayesian framework
- similarity measure
- prior information
- machine learning
- least squares
- chan vese model