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.

Original capsule network (CapsNet) by Sabour et. al., 2017.

More »

Fig 1 Expand

Fig 2.

Proposed CLAHE-CapsNet architecture.

More »

Fig 2 Expand

Fig 3.

Comparison of original squash and power squash activation function.

More »

Fig 3 Expand

Fig 4.

Sample Retina OCT images.

More »

Fig 4 Expand

Table 1.

Dataset description.

More »

Table 1 Expand

Fig 5.

Training, validation accuracy and loss curve on Retina OCT images.

(a) Training and validation accuracy curves of CLAHE-CapsNet and original CapsNet., and (b) Training and validation loss curves of CLAHE-CapsNet and original CapsNet.

More »

Fig 5 Expand

Fig 6.

Performance comparison of model based on individual classes (i.e., CNV, DME, DRUSEN, and NORMAL).

More »

Fig 6 Expand

Fig 7.

Histogram accuracy comparison based on the overall accuracies of OA, OS, and OP.

More »

Fig 7 Expand

Table 2.

Comparison of results of the proposed model and original CapsNet.

The best performance is labeled in bold.

More »

Table 2 Expand

Fig 8.

Confusion matrix comparison on the proposed model and original CapsNet.

More »

Fig 8 Expand

Fig 9.

Comparison of ROC-AUC on the proposed model and original CapsNet.

(a) CLAHE-CapsNet ROC curve, and (b) Original CapsNet ROC curve.

More »

Fig 9 Expand

Fig 10.

Precision-Recall curves comparison on the proposed model and original CapsNet.

(a) CLAHE-CapsNet Precision-Recall curve, and (b) Original CapsNet Precision-Recall curve.

More »

Fig 10 Expand

Fig 11.

Comparison of results with state-of-the-art works based on the individual classes.

More »

Fig 11 Expand

Fig 12.

Comparison of results with state-of-the-art works based on the individual classes.

More »

Fig 12 Expand

Table 3.

Comparison of results of the proposed model and other state-of-the-art works.

The best performance is labeled in bold.

More »

Table 3 Expand