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.

Samples of different brain tumor images.

More »

Fig 1 Expand

Table 1.

MRI image dataset distribution.

More »

Table 1 Expand

Fig 2.

Proposed novel customized CNN architecture for brain tumor classification.

More »

Fig 2 Expand

Fig 3.

Proposed optimized ResNet101 architecture for brain tumor classification.

More »

Fig 3 Expand

Table 2.

Hyperparameter settings of the novel customized CNN.

More »

Table 2 Expand

Table 3.

Fold-wise training and validation accuracies of the novel customized CNN.

More »

Table 3 Expand

Table 4.

Hyperparameter settings of the optimized ResNet101.

More »

Table 4 Expand

Table 5.

Fold-wise training and validation accuracies of the optimized ResNet101.

More »

Table 5 Expand

Table 6.

Performance comparison between the novel customized CNN and optimized ResNet101.

More »

Table 6 Expand

Fig 4.

Validation confusion matrix of the optimized ResNet101 model.

More »

Fig 4 Expand

Fig 5.

Testing confusion matrix of the optimized ResNet101 model.

More »

Fig 5 Expand

Fig 6.

Roc curve illustrating the AUC for the optimized ResNet101.

More »

Fig 6 Expand

Fig 7.

Validation confusion matrix of the novel customized CNN.

More »

Fig 7 Expand

Fig 8.

Testing confusion matrix of the novel customized CNN.

More »

Fig 8 Expand

Fig 9.

Roc curve illustrating the AUC for the novel customized CNN.

More »

Fig 9 Expand

Fig 10.

Training progress of the novel customized CNN.

More »

Fig 10 Expand

Fig 11.

Training progress of the optimized ResNet101.

More »

Fig 11 Expand

Table 7.

Testing results comparison between the novel customized CNN and the optimized ResNet101.

More »

Table 7 Expand

Table 8.

Performance comparison of the novel customized CNN and the optimized ResNet101 with existing studies.

More »

Table 8 Expand