4. Image manipulation and visualization

In this section, we detail the general tools to manipulation and visualize neuroimaging volume with nilearn.

• 4.1. Plotting brain images
  • 4.1.1. Different plotting functions
  • 4.1.2. Different display modes
  • 4.1.3. Adding overlays, edges and contours
  • 4.1.4. Saving to an image file
• 4.2. Data preparation: loading and basic transformation
  • 4.2.1. The concept of “masker” objects
  • 4.2.2. NiftiMasker: loading, masking and filtering
    • 4.2.2.1. Custom data loading
    • 4.2.2.2. Controlling how the mask is computed from the data
      • 4.2.2.2.1. Computing the mask
    • 4.2.2.3. Common data preparation steps: resampling, smoothing, filtering
      • 4.2.2.3.1. Resampling
      • 4.2.2.3.2. Smoothing
      • 4.2.2.3.3. Temporal Filtering
    • 4.2.2.4. Inverse transform: unmasking data
  • 4.2.3. Extraction of signals from regions: NiftiLabelsMasker, NiftiMapsMasker.
    • 4.2.3.1. Regions definition
    • 4.2.3.2. NiftiMapsMasker Usage
    • 4.2.3.3. NiftiLabelsMasker Usage
• 4.3. Manipulating brain volume: input/output, masking, ROIs, smoothing...
  • 4.3.1. Loading data
    • 4.3.1.1. Fetching datasets
    • 4.3.1.2. Loading your own data
  • 4.3.2. Understanding Neuroimaging data
    • 4.3.2.1. Nifti and Analyze files
    • 4.3.2.2. Niimg-like objects
    • 4.3.2.3. Text files: phenotype or behavior
  • 4.3.3. Masking data manually
    • 4.3.3.1. Extracting a brain mask
      • 4.3.3.1.1. nilearn.masking.compute_epi_mask
    • 4.3.3.2. From 4D to 2D arrays
  • 4.3.4. Functions for data preparation steps
  • 4.3.5. Image operations: creating a ROI mask manually
    • 4.3.5.1. Smoothing
    • 4.3.5.2. Selecting features
    • 4.3.5.3. Thresholding
    • 4.3.5.4. Mask intersection
    • 4.3.5.5. Mask dilation
    • 4.3.5.6. Extracting connected components
    • 4.3.5.7. Saving the result