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.

Overview of the proposed method for our COVID-19 study.

More »

Fig 1 Expand

Fig 2.

Flowchart of radiomic feature extraction.

More »

Fig 2 Expand

Fig 3.

t-SNE dimensions of the class distributions using whole CXR images (left) and lung segments (right).

More »

Fig 3 Expand

Table 1.

CXR data information.

More »

Table 1 Expand

Table 2.

Best classification metrics for each feature-level approach.

More »

Table 2 Expand

Table 3.

Classification accuracy obtained using handcrafted and radiomic features.

More »

Table 3 Expand

Table 4.

Classification accuracy obtained using all handcrafted and radiomic feature combinations.

More »

Table 4 Expand

Table 5.

Classification accuracy obtained using selected handcrafted (LBP + HOG + GLCM) and radiomic feature combinations.

More »

Table 5 Expand

Table 6.

Classification accuracy obtained using combined deep features (Pool5 of Resnet18 + Conv5 of Densenet121).

More »

Table 6 Expand

Table 7.

Classification accuracy obtained using all features.

More »

Table 7 Expand

Table 8.

Classification accuracy obtained using selected handcrafted, radiomic and deep features.

More »

Table 8 Expand

Table 9.

Comparison of the three-class classification studies from previous CXR-based COVID-19 studies.

More »

Table 9 Expand