Table 5.
Model | Atlas | Balanced accuracy (%) | True positives (D)/ Total positives | True negatives (C)/ Total negatives |
---|---|---|---|---|
MKL | AAL | 66.00 (p = 0.01) | 34/50 | 32/50 |
Brodmann | 68.00 (p = 0.01) | 34/50 | 34/50 | |
HCP | 65.00 (p = 0.01) | 34/50 | 31/50 | |
SVM | AAL | 67.00 (p = 0.01) | 32/50 | 35/50 |
Brodmann | 70.00 (p = 0.01) | 33/50 | 37/50 | |
HCP | 63.00 (p = 0.01) | 29/50 | 34/50 |
True positives (resp. negatives) represent the number of demented (resp. non-demented) patients classified correctly as demented (resp. non-demented). Note that the difference between the SVM models is only the mask used to select the voxels, which is based on the atlas