Spatial Extent module

Welcome to the section on Spatial Extent! You will find a detailed description of the rationale behind this method and detailed instructions on how you can use it on your own.

Warning

Note that sihnpy provides data to practice using the spatial extent module. While the PREVENT-AD participants are used, the data available for this method is simulated data (i.e., the numbers observed are fake; they were randomly generated to fit the purpose of the tutorials). As a general rule for sihnpy, and especially for this module, only use the data provided to help you practice using the module, not to conduct or publish actual research.

• Introduction to spatial extent
  • Rationale
  • Definitions
  • Data type
  • Use cases and limitations
  • Logistical considerations
  • References
• Spatial extent analysis
  • Outline
  • Practice data
  • Deriving thresholds
    • Introduction to Gaussian mixture modelling (GMM)
    • Limitations
    • Steps to derive thresholds with GMMs
      • 1. Get the data
      • 2. Estimate the GMM
      • 3. Cluster measures
      • 4. Extracting clustering probabilities
      • 5. (Optional) Visual verifications with histograms
      • 6. Threshold derivation
      • 7. Exporting the threshold data
    • Introduction to pre-determined (normative sample) thresholds
  • Applying thresholds
    • 1. Clean data
    • 2. Binary masks
    • 3. Spatial extent index
    • 4. Individualized spatial extent masks
    • 5. Exporting the data
  • tl;dr
  • References
• Additional topics
  • Creating Gaussian simulated data
    • Inspiration from realistic data
    • Generating randomized data
  • Literature - Abnormality in PET data
  • References