Low-frequency Functional Connectivity in fMRI - Biomedical Signal Analysis: Contemporary Methods and Applications - page 268

Figure 9.2
Segmentation results in the motor areas of subject #1 in the motor stimulation
experiment. The obtained task activation maps are shown for all unsupervised
methods. For comparison, the cc-cluster describes a method based on the threshold
segmentation of a pixel-specific correlation map. This map assigns to each pixel the
Pearson correlation coecient between the PTC and the stimulus function. The
threshold was chosen as Δ = 0 . 6 and thus every pixel correlation exceeding 0.6 is
considered as activated and is colored white on the map. For the clustering
methods, all the clusters with an average correlation of PTCs above the threshold
of Δ = 0 . 6 are collected and their pixels are plotted white on the map. The average
value of all PTCs belonging to a certain segmentation determines a
segmentation-specific PTC shown under the assignment maps. The motor task
reference waveform is given as a square wave and overlaid on the average PTC.
good results expressed by an area A under the curve of A> 0 . 8. For a
smaller number of clusters, for all subjects SOM is outperformed by the