Skip to main content

Table 4 The performance of UMLF-COVID and comparison models in three-classification tasks

From: UMLF-COVID: an unsupervised meta-learning model specifically designed to identify X-ray images of COVID-19 patients

Model

Precision

Recall

F1-score

Accuracy

UMLF-COVID

0.97

0.97

0.97

0.97

LeNet

0.92

0.92

0.92

0.92

Alexnet

0.91

0.89

0.89

0.89

VGG

0.85

0.83

0.83

0.83

CovXNet

0.91

0.89

0.88

0.89

CNN-LSTM

0.93

0.93

0.93

0.93

CNN-RNN

0.92

0.92

0.92

0.92

EMCNet

0.92

0.91

0.92

0.91

  1. The strategy is 3-way 10-shot
  2. Bold values are highlight our model
Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us