Orientation Prior and Consistent Model Selection Increase Sensitivity of Tract-Based Spatial Statistics in Crossing-Fiber Regions.
Georgius A. M. ArkesteijnDirk H. J. PootMohammad Arfan IkramWiro J. NiessenLucas J. van VlietMeike W. VernooijFrans M. VosPublished in: IEEE Trans. Medical Imaging (2020)
Keyphrases
- model selection
- spatial statistics
- prior probabilities
- cross validation
- white matter
- white matter tracts
- natural scenes
- diffusion tensor
- sample size
- hyperparameters
- machine learning
- optical flow
- diffusion mri
- high angular resolution diffusion imaging
- diffusion tensor imaging
- parameter estimation
- tensor field
- model selection criteria
- gaussian process
- diffusion tensor images
- selection criterion
- prior knowledge
- motion segmentation
- mixture model
- feature selection
- input image
- human brain
- bayesian model
- fiber bundles
- maximum a posteriori
- training data