Skip to main content

Table 2 Classification results comparison between FCN and GAP network (proposed) with p value

From: Multi-slice representational learning of convolutional neural network for Alzheimer’s disease classification using positron emission tomography

Dataset

Model

ACC [%]

SENS [%]

SPEC [%]

p value

Our dataset

FCN

75.50

60.00

92.96

p < 0.001

GAP (Proposed)

86.09

80.00

92.96

ADNI

FCN

76.95

82.76

72.14

p < 0.01

GAP (Proposed)

91.02

87.93

93.57

  1. FCN fully connected network, GAP global average pooling
Back to article page

BioMedical Engineering OnLine

ISSN: 1475-925X

Contact us