Figure 1.

Comparison of classification and clusterization pipelines used for the analysis of dendritic spine morphology. For classification approach (A) several possible morphological spine types (mushroom, stubby, thin, and filopodia) are defined based on pre-determined criteria. Each spine is then assigned to one of these classes based on numerical morphological criteria. For the clusterization approach (B), spines are grouped into clusters based on their common morphological features. Ten different clusters (1–10) are shown as an example, but the number of different clusters and parameters used for clusterization depends on the particular algorithm and dataset.