Analysis of Residual Dependencies of Independent Components Extracted from fMRI Data

Table 3

Evaluation of ICA of the dataset with activations in ROI #1 and ROI #2 with time delay of 5 seconds at different noise levels and model orders. The AUC is shown near the IC index (in brackets).

Activations delay, 5 sec	Number of ICs	ROI #1; (IC index) AUC	ROI #2; (IC index) AUC
Noise; = 0.33%	5	() 0.9	() 0.9
	10	() 0.77 () 0.76; () 0.78	() 0.76 () 0.79; () 0.76
	15	() 0.79 () 0.74; () 0.78	() 0.74 () 0.8
	20	() 0.9	() 0.74 () 0.76; () 0.77
Noise; = 0.66%	5	() 0.83	() 0.85
	10	() 0.72 () 0.77	() 0.84
	15	() 0.74 () 0.76	() 0.75 () 0.74
	20	() 0.76 () 0.75	() 0.78 () 0.75
Noise; = 1.00%	5	() 0.81	() 0.83
	10	() 0.74 () 0.77	() 0.76 () 0.76
	15	() 0.7 () 0.68; () 0.73	() 0.76 () 0.73; () 0.7
	20	() 0.78 () 0.72	() 0.77 () 0.80
Noise; = 1.33%	5	() 0.84	() 0.8
	10	() 0.82	() 0.76 () 0.76
	15	() 0.83	() 0.71 () 0.76
	20	() 0.85	() 0.76 () 0.76