Independent component analysis (ICA) is a method that decomposes timeseries data into a set of components, or independent signals that when mixed up, reproduce the original data. When applied to functional magnetic resonance imaging (fMRI), the resulting components encompass a mixture of noise and brain functional networks. Each component includes a 3D brain map that shows the spatial location of the network or artifact, and a corresponding timeseries that describes the activity of the regions in the map. Temporal Features include metrics that quantify the timeseries, and Spatial Features are metrics that describe the spatial maps.