Skip to main content

Table 5 Performance of ShuffleNet v2, ResNet 50, GoogleNet, DenseNet 121 and ShuffleNet-Attention on the test set

From: Use data augmentation for a deep learning classification model with chest X-ray clinical imaging featuring coal workers' pneumoconiosis

 

Accuracy

Recall

F1-score

Precision

Class A

Class B

Class C

Shufflenet-Attenion

0.96

0.97

0.96

0.96

0.92

0.93

Shufflenet v2

0.94

0.95

0.95

0.95

0.89

0.9

Resnet 50

0.9

0.94

0.93

0.93

0.85

0.84

Googlenet

0.91

0.94

0.92

0.92

0.91

0.82

Densnet 121

0.89

0.9

0.86

0.86

0.82

0.88

  1. Class A: pulmonary nodules, Class B: pulmonary interstitial changes, Class C: emphysema