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.

Previous studies on automated leukemia classification.

More »

Table 1 Expand

Fig 1.

The outline of the proposed methodology.

More »

Fig 1 Expand

Fig 2.

Sample images of the datasets.

(a) ALL, (b) ALL-IDB2, (c) C-NMC, and (d) Mixture-Leukemia.

More »

Fig 2 Expand

Table 2.

The properties of the used datasets.

More »

Table 2 Expand

Table 3.

Splitting train-validation-test of data.

More »

Table 3 Expand

Fig 3.

The 5-fold cross-validation procedure.

More »

Fig 3 Expand

Fig 4.

The architecture of the proposed networks.

More »

Fig 4 Expand

Fig 5.

The architecture of the PCAB.

More »

Fig 5 Expand

Fig 6.

The architecture of the SCAB.

More »

Fig 6 Expand

Table 4.

Experimental hardware and software environments.

More »

Table 4 Expand

Table 5.

Hyperparameter configuration of the networks.

More »

Table 5 Expand

Fig 7.

The accuracy and loss curves of the ResNet18 models.

More »

Fig 7 Expand

Fig 8.

The accuracy and loss curves of the MobileNetv4 models.

More »

Fig 8 Expand

Fig 9.

The confusion matrix of the ResNet18 models.

More »

Fig 9 Expand

Fig 10.

The confusion matrix of the MobileNetv4 models.

More »

Fig 10 Expand

Table 6.

Performance metrics equations for leukemia classification.

More »

Table 6 Expand

Table 7.

The performance metrics of the ResNet18 models.

More »

Table 7 Expand

Table 8.

The performance metrics of the MobileNetv4 models.

More »

Table 8 Expand

Table 9.

The accuracy of the ResNet18 models.

More »

Table 9 Expand

Table 10.

The accuracy of the MobileNetv4 models.

More »

Table 10 Expand

Table 11.

Comparison of the time and computational complexities.

More »

Table 11 Expand

Table 12.

Ablation experiment data for different pooling layers.

More »

Table 12 Expand

Table 13.

Ablation experiment data for different convolution layers.

More »

Table 13 Expand

Table 14.

Overall comparison of the model with existing models.

More »

Table 14 Expand

Fig 11.

The ANOVA results for models.

More »

Fig 11 Expand

Fig 12.

Feature maps from the last convolution layers of the models on the datasets.

() are the images and their feature maps from the ALL, ALL-IDB2, C-NMC, and Mixture-Leukemia datasets, whereas (1) include input images, () are the output feature maps of the last convolution layers of each model.

More »

Fig 12 Expand

Fig 13.

Grad-CAM images from the last convolution layers of the models on the datasets.

() are the images and their activation maps from the ALL, ALL-IDB2, C-NMC, and Mixture-Leukemia datasets, whereas (1) include input images, () are the Grad-CAM images extracted from the last convolution layers of the ResNet18, ResNet18PCAB, ResNet18SCAB, MobileNetv4, MobileNetv4PCAB, and MobileNetv4SCAB, respectively.

More »

Fig 13 Expand

Fig 14.

Samples of images of correct and incorrect prediction of the datasets.

() are correctly classified while () are misclassified.

More »

Fig 14 Expand