Enhancing Model Generalization for Substantia Nigra Segmentation Using a Test-time Normalization-Based Method.
Tao HuHayato ItohMasahiro OdaYuichiro HayashiZhongyang LuShinji SaikiNobutaka HattoriKoji KamagataShigeki AokiKanako K. KumamaruToshiaki AkashiKensaku MoriPublished in: MICCAI (8) (2022)
Keyphrases
- mathematical model
- prior knowledge
- energy function
- segmentation method
- probabilistic model
- theoretical analysis
- fully automatic
- modeling method
- test data
- cost function
- sensitivity analysis
- detection method
- prior information
- linear model
- final result
- segmentation accuracy
- piece wise
- real image data
- objective function
- edge detection
- statistical model
- input data
- optimization method
- similarity measure
- evaluation method
- pairwise
- segmentation errors
- grey level
- multiscale
- autoregressive
- piecewise constant
- prediction model
- image segmentation
- normalization method
- statistical methods
- em algorithm
- parameter estimation
- active contours
- feature selection
- reconstruction method
- preprocessing
- bp neural network
- linear regression
- bayesian framework
- support vector machine
- model selection