Skip to main content

Table 9 Mean ± standard deviation of the results obtained in the test stage for the classification of chest X-ray images between Pneumonia VS COVID-19 after 5 independent repetitions

From: Does imbalance in chest X-ray datasets produce biased deep learning approaches for COVID-19 screening?

Exp.

Class

Precision

Recall

F1-Score

<40

Pneumonia

0.9603 ± 0.0440

0.9292 ± 0.0241

0.9438 ± 0.0188

 

COVID-19

0.9199 ± 0.0303

0.9498 ± 0.0625

0.9336 ± 0.0356

40-50

Pneumonia

0.9811 ± 0.0177

0.9717 ± 0.0161

0.9762 ± 0.0105

 

COVID-19

0.9689 ± 0.0219

0.9821 ± 0.0172

0.9752 ± 0.0122

50-60

Pneumonia

0.9802 ± 0.0118

0.9815 ± 0.0116

0.9808 ± 0.0112

 

COVID-19

0.9796 ± 0.0126

0.9784 ± 0.0129

0.9790 ± 0.0122

60-70

Pneumonia

0.9942 ± 0.0046

0.9895 ± 0.0036

0.9918 ± 0.0036

 

COVID-19

0.9893 ± 0.0040

0.9944 ± 0.0045

0.9919 ± 0.0035

70-80

Pneumonia

0.9869 ± 0.0132

0.9678 ± 0.0101

0.9772 ± 0.0097

 

COVID-19

0.9668 ± 0.0123

0.9874 ± 0.0122

0.9770 ± 0.0097

≥ 80

Pneumonia

0.8850 ± 0.1117

0.9000 ± 0.1732

0.8893 ± 0.1380

 

COVID-19

0.9346 ± 0.1084

0.9095 ± 0.0831

0.9195 ± 0.0840