FSL_FAST

参考：FSL里的FAST、核磁数据处理: FSL系列之segmentation工具FAST、fslwiki_FAST、FSL-Introduction
相关文档：FSL Structural Segmentation ☆☆☆☆☆

The various output images are:

• Partial volume maps: A (non-binary) partial volume image for each class, where each voxel contains a value in the range 0-1 that represents the proportion of that class's tissue present in that voxel. This is the default output. 局部体积图：每个类别的（非二进制）局部体积图像，其中每个体素包含0-1范围内的值，该值表示该体素中该类别组织的比例。 这是默认输出。

# Partial volume maps  (Default)
/usr/share/fsl/5.0/bin/fast -t 1 -n 3 -H 0.1 -I 4 -l 20.0 -o /home/captain/Desktop/7_30_fsl/sample-001_brain_fast /home/captain/Desktop/7_30_fsl/sample-001_brain

# output the files as below:
sample-001_brain_fast_mixeltype.nii.gz
sample-001_brain_fast_pve_0.nii.gz
sample-001_brain_fast_pve_1.nii.gz
sample-001_brain_fast_pve_2.nii.gz
sample-001_brain_fast_pveseg.nii.gz
sample-001_brain_fast_seg.nii.gz

• Binary segmentation: single image: This is the "hard" (binary) segmentation, where each voxel is classified into only one class. A single image contains all the necessary information, with the first class taking intensity value 1 in the image, etc. 二进制分割：单个图像：这是“硬”（二进制）分割，其中每个体素仅分类为一类。 一幅图像包含所有必要的信息，第一类图像中的强度值为1，依此类推。

# pure
/usr/share/fsl/5.0/bin/fast -t 1 -n 3 -H 0.1 -I 4 -l 20.0 --nopve 
-o /home/captain/Desktop/7_30_fsl/sample-001_brain_fast 
/home/captain/Desktop/7_30_fsl/sample-001_brain

# output the files as below:
sample-001_brain_fast_seg.nii.gz 

• Binary segmentation: One image per class: This is also a hard segmentation output; the difference is that there is one output image per class, and values are only either 0 or 1. 二进制分割：每类一张图像：这也是硬分割输出； 区别在于每个类只有一个输出图像，并且值仅为0或1。

# Binary segmentation: Also output one image per class
/usr/share/fsl/5.0/bin/fast -t 1 -n 3 -H 0.1 -I 4 -l 20.0 -g --nopve 
-o /home/captain/Desktop/7_30_fsl/sample-001_brain_fast 
/home/captain/Desktop/7_30_fsl/sample-001_brain

# output the files as below: (White matter、Gray matter、CSF)
sample-001_brain_fast_seg.nii.gz
sample-001_brain_fast_seg_0.nii.gz
sample-001_brain_fast_seg_1.nii.gz
sample-001_brain_fast_seg_2.nii.gz

• Restored input: This is the estimated restored input image after correction for bias field. 恢复的输入：这是在对偏差字段进行校正后估计的恢复的输入图像。

# Restored input
/usr/share/fsl/5.0/bin/fast -t 1 -n 3 -H 0.1 -I 4 -l 20.0 --nopve -B -o /home/captain/Desktop/7_30_fsl/sample-001_brain_fast /home/captain/Desktop/7_30_fsl/sample-001_brain

# output the files as below:
sample-001_brain_fast_restore.nii.gz
sample-001_brain_fast_seg.nii.gz

• Bias field: This is the estimated bias field. 偏差字段：这是估计的偏差字段。

# Estimated Bias field
/usr/share/fsl/5.0/bin/fast -t 1 -n 3 -H 0.1 -I 4 -l 20.0 --nopve -b -o /home/captain/Desktop/7_30_fsl/sample-001_brain_fast /home/captain/Desktop/7_30_fsl/sample-001_brain

# output the files as below:
sample-001_brain_fast_bias.nii.gz
sample-001_brain_fast_seg.nii.gz

Advanced Options

• Bias field iterations determines the number of passes made during the initial bias field estimation stage. A greater number of iterations can help esitmate particularly strong bias fields. 偏置场迭代确定了初始偏置场估计阶段的通过次数。大量的迭代可以帮助确定特别强的偏置场。
• Bias field smoothing controls the amount of smoothness expected in the estimated bias field. The value entered is the Full-Width Half-Maximum (FWHM) in mm. A larger value here will impose more smoothness on the estimated bias field. 偏置场平滑控制估计的偏置场中期望的平滑度。输入的值为以毫米为单位的全宽半最大值（FWHM）。此处较大的值将对估计的偏置场施加更大的平滑度。
• Use a-priori probability maps tells FAST to start by registering the input image to standard space and then use standard tissue-type probability maps (from the MNI152 dataset) instead of the initial K-means segmentation, in order to estimate the initial parameters of the classes. This can help in cases where there is very bad bias field. By default the a-priori probability maps are only used to initialise the segmentation; however, you can also optionally tell FAST to use these priors in the final segmentation - this can help, for example, with the segmentation of deep grey structures. 使用先验概率图告诉FAST首先将输入图像注册到标准空间，然后使用标准组织类型概率图（来自MNI152数据集）代替初始K均值分割，以便估算类。这在偏置场非常差的情况下可以提供帮助。默认情况下，先验概率图仅用于初始化分割。但是，您也可以选择告诉FAST在最终的细分中使用这些先验-例如，这可以帮助细分深灰色结构。
• Use file of initial tissue-type means tells FAST to use a text file with mean intensity values (separated by newlines) for the starting mean values of the different classes to be segmented. This is then used instead of the automated K-means starting parameter estimation. 初始组织类型均值的使用文件告诉FAST使用具有平均强度值（用换行符分隔）的文本文件作为要分割的不同类别的起始均值。然后使用它代替自动K均值开始参数估计。

---

# Partial volume maps  (Default)
/usr/share/fsl/5.0/bin/fast -t 1 -n 3 -H 0.1 -I 4 -l 20.0 -o 
/home/captain/Desktop/7_30_fsl/sample-001_brain_fast 
/home/captain/Desktop/7_30_fsl/sample-001_brain

# output the files as below:
sample-001_brain_fast_mixeltype.nii.gz
sample-001_brain_fast_pve_0.nii.gz
sample-001_brain_fast_pve_1.nii.gz
sample-001_brain_fast_pve_2.nii.gz
sample-001_brain_fast_pveseg.nii.gz
sample-001_brain_fast_seg.nii.gz

常用参数:
-S or --channels= 图像通道数, 通常设为1
-t or --type= 图像种类, T1的话设置为1, T2设置为2, PD设置为3 Type of image (e.g. T1, T2, PD) - Note space in fast4 version e.g. t 2 not t2 → Fast3
-o or --out= 输出文件的基本名称,生成的文件会自动附上后缀, 例如seg, pve_0, pve_1等.
-n or --class= 组织类型数.T1的话通常设置为3, (Grey Matter, White Matter and CSF) T2的话通常设置为4. 如果图像很不清晰, 可以设置为2.
-b 输出的估计偏置场(estimated bias field)
-B 输出偏置图像并保存(bias-corrected image)
-l or –lowpass= 偏置场平滑, m是FWHM, 单位是mm, m ≅ 2 √n
-I 或者 –iter 循环次数

---

• ADNI_023_S_1190_FDG.nii（左）原始数据
• ADNI_023_S_1190_FDG_brain.nii （右）去除颅骨

---

• ADNI_023_S_1190_FDG_brain_pve_0.nii（左）脑脊液
• ADNI_023_S_1190_FDG_brain_pve_1.nii（中）灰质
• ADNI_023_S_1190_FDG_brain_pve_2.nii（右）白质
  注：partial volume (PVE)

---

• ADNI_023_S_1190_FDG_brain_mixeltype.nii （左）
• ADNI_023_S_1190_FDG_brain_pveseg.nii（中）
• ADNI_023_S_1190_FDG_brain_seg.nii（右）（= *_pveseg.nii）

---

ADNI_023_S_1190_FDG_brain_pveseg.nii：（Advanced Options）

• no Use a-priori probability maps for initiallsation; no and for final segmentation (左)
• √ Use a-priori probability maps for initiallsation; no and for final segmentation (中)
• √ Use a-priori probability maps for initiallsation; √ and for final segmentation (右)

---

ADNI_023_S_1190_FDG_brain_pveseg.nii：（Advanced Options）

• Bias field smoothing (FWHM in mm) ：20.0 （左） 默认值，较优
• Bias field smoothing (FWHM in mm) ：8.0 （右）