Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Chest x-ray images: (A) normal; (B) COVID-19 positive; (C) viral pneumonia.

More »

Fig 1 Expand

Fig 2.

The pipeline process.

More »

Fig 2 Expand

Fig 3.

Variation in chest x-ray images distribution.

More »

Fig 3 Expand

Table 1.

Hyper-parameters of the build CNN model and preferred weights in this study.

More »

Table 1 Expand

Fig 4.

Feature extraction of the input image is performed via the convolution, ReLU and pooling layers, before classification by the fully connected layer.

More »

Fig 4 Expand

Table 2.

The layers and layer parameters of the VGG16 model.

More »

Table 2 Expand

Table 3.

Hyper-parameters of the VGG16 model and preferred weights in this study.

More »

Table 3 Expand

Table 4.

Hyper-parameters of the InceptionV3 model and preferred weights in this study.

More »

Table 4 Expand

Table 5.

Hyper-parameters of the Xception model and preferred weights in this study.

More »

Table 5 Expand

Fig 5.

Proposed pre-trained method for COVID-19 detection.

More »

Fig 5 Expand

Table 6.

Description of classification task.

More »

Table 6 Expand

Fig 6.

(A) and (C) original chest x-ray COVID-19 and Pneumonia images; (B) and (D) contrast enhanced image using Icomb.

More »

Fig 6 Expand

Fig 7.

Visual feature maps in first layer and deep layer.

More »

Fig 7 Expand

Table 7.

Confusion matrix.

More »

Table 7 Expand

Table 8.

Average performance of the pre-trained CNN models.

More »

Table 8 Expand

Table 9.

Average performance of the build CNN models.

More »

Table 9 Expand

Fig 8.

Confusion matrices for scenario I obtained by (A) build CNN and (B) VGG16.

More »

Fig 8 Expand

Fig 9.

Confusion matrices for scenario II obtained by (A) build CNN and (B) VGG16.

More »

Fig 9 Expand

Fig 10.

Visualisation on chest x-ray of normal/COVID-19/pneumonia infected using Grad-CAM on the proposed model.

More »

Fig 10 Expand

Fig 11.

Comparison of accuracy achieved in selected models after fine-tune: (A) scenario I and (B) scenario II.

More »

Fig 11 Expand

Fig 12.

Comparison of accuracy achieved in new CNN: Scenario I and scenario II.

More »

Fig 12 Expand

Fig 13.

ROC curve in scenario I for (A) build CNN and (B) VGG16.

More »

Fig 13 Expand

Fig 14.

ROC curve in scenario II for (A) build CNN and (B) VGG16.

More »

Fig 14 Expand

Table 10.

Accuracy obtained by existing models and models used in the study.

More »

Table 10 Expand