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.

Breast thermography procedure (thermal image is aquired at room temperature = 22°C).

More »

Fig 1 Expand

Fig 2.

Flowchart of the proposed method.

More »

Fig 2 Expand

Fig 3.

Example of U-Net architecture [33].

More »

Fig 3 Expand

Fig 4.

Example of breast area segmentation with U-Net.

More »

Fig 4 Expand

Fig 5.

Architecture of the proposed deep learning model.

More »

Fig 5 Expand

Fig 6.

Different cases of breast (a) small breast (b) large breast (c) asymmetric breast.

More »

Fig 6 Expand

Table 1.

Dataset description.

More »

Table 1 Expand

Fig 7.

Breast area segmentation resuls (a) thermal image (b) ground truth (c) output.

More »

Fig 7 Expand

Fig 8.

The training progress of the proposed deep learning model.

More »

Fig 8 Expand

Fig 9.

The confusion matrix of the proposed model.

More »

Fig 9 Expand

Table 2.

Comparison between solvers (initial learn rate = 2.0e−3, number of epochs = 30 and batch size = 60).

More »

Table 2 Expand

Table 3.

The impact of using different number of epochs on the classification accuracy, sensitivity and specificity (solver = ADAM, initial learn rate = 2.0e−3, batch size = 60).

More »

Table 3 Expand

Table 4.

Impact of using different batch size on the classification accuracy, sensitivity and specificity (solver = ADAM, initial learn rate = 2.0e−3, number of epochs = 30).

More »

Table 4 Expand

Table 5.

Impact of starting the training process with different initial learn rate on the classification accuracy, sensitivity and specificity (solver = ADAM, batch size = 60 and number of epochs = 30).

More »

Table 5 Expand

Table 6.

Comparison between the performance metrics of different CNN models and the proposed model.

More »

Table 6 Expand

Fig 10.

Evaluation metrics over different dataset size.

More »

Fig 10 Expand

Table 7.

Comparison between the performance metrics of different machine learning classifier with texture features and the proposed model.

More »

Table 7 Expand

Table 8.

Comparison between the performance metrics of different machine learning classifier with HOG features and the proposed model.

More »

Table 8 Expand

Table 9.

Results of the ANOVA test of the proposed model and CNN models.

More »

Table 9 Expand

Table 10.

Comparison with other studies on breast cancer detection (n = normal, ab = abnormal, Ea = Early, Ac = Acute).

More »

Table 10 Expand

Table 11.

Table of abbreviation.

More »

Table 11 Expand