Skip to main content
. Author manuscript; available in PMC: 2015 Sep 14.
Published in final edited form as: Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2014 Jun 23;2014:3089–3096. doi: 10.1109/CVPR.2014.395

Table 1.

Comparison of classification performances (%) of the competing methods.

Modality Method AD vs. NC MCI vs. NC

ACC SEN SPE AUC ACC SEN SPE AUC

MRI MRI-N 89.5 82.7 86.3 95.3 68.3 92.6 39.2 82.5
MRI-S 91.2 85.9 92.5 96.7 76.7 93.3 37.6 83.7
HOGM 93.4 89.5 92.5 97.1 77.7 95.6 51.4 84.4
M3T 92.6 87.2 95.9 97.5 78.1 94.5 54.0 83.1
SJCR 92.5 89.6 96.1 97.5 77.9 95.2 52.7 84.9
Proposed 93.8 89.7 96.7 97.9 79.7 95.0 56.1 85.2

PET PET-N 86.2 83.5 84.8 94.8 69.0 95.0 30.8 77.9
PET-S 87.9 85.7 90.9 94.7 73.8 96.5 36.2 78.7
HOGM 91.7 91.1 92.8 95.6 74.7 96.5 43.2 79.3
M3T 90.9 90.5 93.1 96.4 77.2 94.5 44.3 80.5
SJCR 91.6 83.7 93.6 95.9 73.8 96.4 23.2 80.8
Proposed 92.3 92.3 93.9 96.6 79.1 96.1 47.2 81.2

MP MP-N 89.7 92.2 85.9 96.1 71.6 96.1 43.9 82.7
MP-S 90.8 92.6 93.8 96.7 76.3 97.0 39.9 83.4
M2TFS-C 91.0 90.4 91.4 95.0 73.4 76.5 67.1 78.0
M2TFS-K 95.0 94.9 95.0 97.0 79.3 85.9 66.6 82.0
HOGM 95.2 92.8 95.4 97.8 79.5 96.6 58.6 84.6
M3T 94.0 92.0 96.3 98.0 78.4 95.0 57.7 83.9
SJCR 93.4 92.7 96.5 96.8 78.2 96.1 54.4 83.1
Proposed 95.3 93.5 98.1 98.3 80.2 96.5 59.7 85.5

MPC MPC-N 90.8 93.1 88.3 96.5 72.5 96.3 47.1 84.1
MPC-S 92.5 94.1 93.8 97.6 77.1 97.1 47.5 83.9
HOGM 95.6 94.5 96.9 98.5 80.6 96.7 64.7 86.2
M3T 94.6 93.1 96.4 98.5 80.1 95.2 58.7 84.3
SJCR 93.9 92.8 96.5 97.0 78.9 96.2 55.9 83.4
Proposed 95.9 95.7 98.6 98.8 82.0 98.0 60.1 87.0

(ACC: ACCuracy, SEN: SENsitivity, SPE: SPEcificity, and AUC: Area Under the receiver operating characteristic Curve)