Module Detail Information

Name:FAST (nii.gz)
Type: Module
Short URL:
Description:FAST (FMRIB's Automated Segmentation Tool) segments a 3D image of the brain into different tissue types (Grey Matter, White Matter, CSF, etc.), whilst also correcting for spatial intensity variations (also known as bias field or RF inhomogeneities). The underlying method is based on a hidden Markov random field model and an associated Expectation-Maximization algorithm. The whole process is fully automated and can also produce a bias field-corrected input image and a probabilistic and/or partial volume tissue segmentation. It is robust and reliable, compared to most finite mixture model-based methods, which are sensitive to noise.
Input Parameters:
 - Input
 - Help
 - Number of Tissue Type Classes
 - Main-Loop Iterations
 - Bias Field Smoothing Extent
 - Image type
 - Initial Seg Spatial Smoothness
 - Output Separate Tissue Types
 - Priors
 - Alternative Priors
 - No PVE
 - Estimated Bias Field
 - Bias-Corrected Image
 - Do Not Remove Bias Field
 - Use Priors Throughout
 - Seg-Init Iterations
 - Spatial Smoothness for Mixeltype
 - Main-Loop Iteration After Bias Field Removal
 - Segmentation Spatial Smoothness
 - Verbose
 - Manual Seg
 - Individual Probability Maps
 - number of inputs
Output Parameters:
 - Mixel Type Output
 - CSF Probability Map
 - GM Probability Map
 - WM Probability Map
 - Tissue Labels - Partial Volume Estimates
 - Tissue Labels
 - Output
File size:30.57 KB
View Source    Download    Open