Skip to main content

Table 16 Evaluation of dropout, batch normalization and learning rate for model2 with last unfrozen Convlayer

From: Deep convolutional neural network based medical image classification for disease diagnosis

Model

Normal vs pneumonia

Bacteria vs virus

Accuracy

Specificity

Recall

Accuracy

Specificity

Recall

Baseline

0.776

0.809

0.776

0.643

0.64

0.585

VGG16 [34]a

0.923

0.926

0.923

0.923

0.909

0.85

VGG16 [38]b

0.938

0.944

0.938

0.915

0.917

0.879

Inception V3

0.869

0.854

0.869

0.851

0.86

0.779

CapsNet

0.824

0.846

0.824

0.862

0.875

0.785

Stateof-art [3]c

0.928

0.901

0.932

0.907

0.909

0.886

  1. aThis result got from the version 2 of Kermany’s dataset.
  2. bThis result got from the version 3 of Kermany’s dataset that is a new released by authors to fix some error in version 2 dataset
  3. cThe state-of-art result got from the research of Kermany et al. [3], which is from a transfer learning based on InceptionV3