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.

Sample images from the Kaggle [41] dataset (a) Negative for pneumonia (b) Typical (c) Indeterminate (d) Atypical.

More »

Fig 1 Expand

Table 1.

Distribution of image classes.

More »

Table 1 Expand

Fig 2.

Proposed system architecture.

Each EfficientNetn (where n = 1, 2, 3 …, 10) has been trained on a different subset of train data. The variants of YOLOv5an (where n = 1, 2) have been trained in the same manner.

More »

Fig 2 Expand

Fig 3.

The original image (a) and the results of the selected image pre-processing techniques—(b) Unsharp Masking and Histogram Equalisation (c) CLAHE (d) Psuedo-Coloring.

More »

Fig 3 Expand

Fig 4.

Image Augmentation [from Top to Bottom] Original, Horizontal Flipped, Vertical Flipped, Saturation, Contrast, Rotation, Shear, Zoom and Shift.

More »

Fig 4 Expand

Fig 5.

Region of interests for opacity localisation.

More »

Fig 5 Expand

Fig 6.

Proposed neural network model.

More »

Fig 6 Expand

Table 2.

Hyperparameter values used in proposed architecture.

More »

Table 2 Expand

Table 3.

Model performance metrics.

More »

Table 3 Expand

Table 4.

Combined confusion matrix.

More »

Table 4 Expand

Table 5.

Mean average precision.

More »

Table 5 Expand

Fig 7.

Results of opacity localisation: (a) Ground Truth (b) WBF Top 3 Bounding Boxes (c) WBF Top 5 Bounding Boxes (d) WBF Top 10 Bounding Boxes (e) WBF All Bounding Boxes with lowered threshold.

More »

Fig 7 Expand

Table 6.

Mean average precision for the training dataset.

More »

Table 6 Expand

Table 7.

Comparison with top scoring methodologies on [41].

More »

Table 7 Expand

Table 8.

Comparison of proposed methodology with existing techniques on RSNA dataset.

More »

Table 8 Expand

Fig 8.

Gradient-weighted Class Activation Mapping (Grad-CAM): From left to right–Negative for pneumonia, typical appearance, indeterminate and atypical appearance. The heat map of the activations show that the area of high activations shrinks in diseased images as compared to healthy images.

More »

Fig 8 Expand