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

Table 1.

Portrayal of the dataset.

More »

Table 1 Expand

Fig 1.

Sample Images of Different Classes (a) Actinic Keratosis (b) Basal Cell Carcinoma (c) Benign Keratosis (d) Dermatofibroma (e) Melanoma (f) Nevus (g) Vascular Lesions.

More »

Fig 1 Expand

Fig 2.

Instance distribution for each class.

More »

Fig 2 Expand

Fig 3.

Schematic representation of methodology.

More »

Fig 3 Expand

Fig 4.

Sample images of the images after augmentation.

(a) Original Sample, (b) Rotated Sample, (c) Width_shifted, (d) Height_shifted, (e) Zoomed, (f), Horizontal_flipped, (g) Vertical_flipped.

More »

Fig 4 Expand

Fig 5.

CTL architecture.

More »

Fig 5 Expand

Fig 6.

Feature extraction after activation of each layer (One image as example).

More »

Fig 6 Expand

Fig 7.

IGPA in Level—n.

More »

Fig 7 Expand

Fig 8.

Organization of ML-IGPA.

More »

Fig 8 Expand

Table 2.

Trainable parameters for different algorithms.

More »

Table 2 Expand

Table 3.

Performance metrics of DenseNet121 approaches.

More »

Table 3 Expand

Table 4.

Performance metrics of DenseNet169 approaches.

More »

Table 4 Expand

Table 5.

Performance metrics of DenseNet201 approaches.

More »

Table 5 Expand

Table 6.

Performance metrics of MobileNet approaches.

More »

Table 6 Expand

Table 7.

Performance metrics of MobileNetV2 approaches.

More »

Table 7 Expand

Table 8.

Performance metrics of MobileNetV3Large approaches.

More »

Table 8 Expand

Table 9.

Performance metrics of InceptionV3 approaches.

More »

Table 9 Expand

Table 10.

Performance metrics of InceptionResnetV2 approaches.

More »

Table 10 Expand

Table 11.

Performance metrics of Xception approaches.

More »

Table 11 Expand

Table 12.

Performance metrics of DN approaches.

More »

Table 12 Expand

Table 13.

Performance metrics of MN approaches.

More »

Table 13 Expand

Table 14.

Performance metrics of IX approaches.

More »

Table 14 Expand

Table 15.

Performance metrics of DMIX approaches.

More »

Table 15 Expand

Table 16.

Performance metrics of Single-Levelled IGPA.

More »

Table 16 Expand

Fig 9.

Confusion matrix obtained by SL-IGPA.

More »

Fig 9 Expand

Fig 10.

Confusion matrix obtained by ML-IGPA (All classifiers).

More »

Fig 10 Expand

Fig 11.

Confusion matrix obtained by ML-IGPA (Best 3 classifiers).

More »

Fig 11 Expand

Fig 12.

ROC-AUC curve obtained by SL-IGPA.

More »

Fig 12 Expand

Fig 13.

ROC-AUC curve obtained by ML-IGPA (All classifiers).

More »

Fig 13 Expand

Fig 14.

ROC-AUC curve obtained by ML-IGPA (Best 3 classifiers).

More »

Fig 14 Expand

Fig 15.

GradCAM generation by the model for each class.

(a) GradCAM for AK, (b) GradCAM for BCC, (c) GradCAM for BKL, (d) GradCAM for DF, (e) GradCAM for MEL, (f) GradCAM for NV, (g) GradCAM for VASC.

More »

Fig 15 Expand

Fig 16.

GradCAM visualization for architecture explainability (Example by DN121).

(a) Original, (b) CACNN, (c) SEACNN, (d) SACNN.

More »

Fig 16 Expand

Table 17.

Performance metrics of IGPA without TA.

More »

Table 17 Expand

Table 18.

Performance metrics of Softmax Averaging of all classifiers.

More »

Table 18 Expand

Table 19.

Performance metrics of Softmax Averaging of best 3 classifiers.

More »

Table 19 Expand

Table 20.

Performance metrics of Single Level Softmax Averaging.

More »

Table 20 Expand

Table 21.

Performance metrics of Majority Voting of all classifiers.

More »

Table 21 Expand

Table 22.

Performance metrics of Majority Voting of best 3 classifiers.

More »

Table 22 Expand

Table 23.

Performance metrics of Single Level Majority Voting.

More »

Table 23 Expand

Table 24.

Performance metrics of Weighted Averaging of all classifiers.

More »

Table 24 Expand

Table 25.

Performance metrics of Weighted Averaging of best 3 classifiers.

More »

Table 25 Expand

Table 26.

Performance metrics of Single Level Weighted Averaging.

More »

Table 26 Expand

Table 27.

Comparison of our proposed model with other existing models.

More »

Table 27 Expand