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.

Methodology of the proposed skin cancer detection framework.

More »

Fig 1 Expand

Table 1.

Summary of recent studies in skin cancer diagnostics using deep learning techniques.

More »

Table 1 Expand

Table 2.

Class distribution in HAM10000 dataset.

More »

Table 2 Expand

Table 3.

Hyperparameters utilized for data augmentation.

More »

Table 3 Expand

Table 4.

Class distribution of the training dataset before and after the application of data augmentation.

More »

Table 4 Expand

Fig 2.

Fusion model 1 (FM1) structure.

More »

Fig 2 Expand

Fig 3.

Fusion model 2 (FM2) structure.

More »

Fig 3 Expand

Fig 4.

Fusion model 3 (FM3) structure.

More »

Fig 4 Expand

Fig 5.

Fusion model 4 (FM4) structure.

More »

Fig 5 Expand

Fig 6.

Fusion model 5 (FM5) structure.

More »

Fig 6 Expand

Fig 7.

Fusion model 6 (FM6) structure.

More »

Fig 7 Expand

Fig 8.

Confusion matrices for the six suggested feature fusion ideas (FM1–FM6 models) on the HAM10000 dataset.

More »

Fig 8 Expand

Fig 9.

Class-based ROC curves for the six suggested feature fusion ideas (FM1–FM6 models) on the HAM10000 dataset.

More »

Fig 9 Expand

Fig 10.

Average ROC curves for the six suggested feature fusion ideas (FM1–FM6 models) on the HAM10000 dataset.

More »

Fig 10 Expand

Table 5.

Comparison of classification metrics across different models on testing dataset.

More »

Table 5 Expand

Table 6.

Comparison of the suggested fusion models with the existing approaches in the literature.

More »

Table 6 Expand

Fig 11.

GradCAM results.

More »

Fig 11 Expand

Fig 12.

SHAP values visualization.

More »

Fig 12 Expand

Fig 13.

Diagnostic error analysis of the FM6 model comparing false positives and false negatives.

More »

Fig 13 Expand