Combining Shape Priors with Conditional Adversarial Networks for Improved Scapula Segmentation in MR images.
Arnaud BoutillonBhushan BorotikarValérie BurdinPierre-Henri ConzePublished in: CoRR (2019)
Keyphrases
- shape prior
- mr images
- medical images
- deformable models
- magnetic resonance
- level set
- segmentation result
- graph cuts
- object segmentation
- active contours
- accurate segmentation
- magnetic resonance images
- shape model
- image segmentation
- intensity distribution
- variational segmentation
- segmentation algorithm
- object boundaries
- level set based segmentation
- intensity inhomogeneity
- manual segmentation
- segmentation method
- energy function
- brain mr images
- partial volume
- brain tumors
- shape variations
- prior knowledge
- mri data
- mr imaging
- curve evolution
- bias field
- shape representation
- energy functional
- image data
- level set method
- cardiac magnetic resonance
- graph cut segmentation
- appearance cues
- user interaction
- image intensity
- intensity information
- brain structures
- global optimization
- active shape model
- statistical models
- medical imaging
- input image
- bayesian framework
- model based segmentation
- image processing
- image analysis
- multiscale