Skip to main content
. 2022 Jun 3;16:902528. doi: 10.3389/fnins.2022.902528

Table 2.

Classification results for AD vs. NC with different kinds of feature representations.

Feature representation OFMROI OFMnetwork CFM ROI CFM network
Parameters setting E1 = 2 E1 = 3 E1 = 4 E1 = 2 E1 = 3 E1 = 4
E2 = 1 E2 = 2 E2 = 3 E2 = 4 E2 = 5 E2 = 1 E2 = 2 E2 = 3 E2 = 4 E2 = 5 E2 = 1 E2 = 2 E2 = 3 E2 = 4 E2 = 5
ACC (%) 69.21 71.29 73.51 71.77 68.27 71.2 76.84 81.72 76.09 70.85 85.02 90.44 83.3 77.94 72.47 77.47 87.32 81.13 75.19 70.2
SEN (%) 67.29 67.72 69.32 69.57 64.03 68.67 74.12 76.75 72.41 68.29 82.28 88.5 81.08 74.04 68.01 79.4 85.72 77.42 71.01 67.18
SPE (%) 71.60 73.20 75.42 74.02 70.57 73.9 79.61 83.57 80.62 73.16 87.75 93.67 86.1 80.07 74.51 81.13 90.04 84.91 77.38 72.55

OFMROI, the original ROI-level feature representation; OFMnetwork, the original network-level feature representation; CFMROI, the coupled ROI-level feature representation; CFMnetwork, the two-level feature representation; Acc, accuracy; Sen, sensitivity; Spe, specificity. The values with the highest accuracy are highlighted in boldface. The shadow of gray color is used to visually differentiate columns of the table.