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.

Schematic illustration of the modified VGG-16.

Note: Except softmax layer, activation function is not shown.

More »

Fig 1 Expand

Table 1.

Summary of patient demographics.

More »

Table 1 Expand

Fig 2.

Representative CT images of lung nodules.

(A) benign nodule, (B) primary lung cancer and (C) metastatic lung cancer.

More »

Fig 2 Expand

Fig 3.

Three CT images obtained from three orthogonal planes used for input to 2D-DCNN.

Fig 2(B) is identical to Fig 3(A). (A) axial image, (B) coronal image and (C) sagittal image. Abbreviations: DCNN, deep convolutional neural network.

More »

Fig 3 Expand

Table 2.

Optimal hyperparameters and classification results for CADx by DCNN with and without transfer learning.

More »

Table 2 Expand

Fig 4.

Representative results of loss and accuracy during DCNN training with transfer learning.

Abbreviations: DCNN, deep convolutional neural network.

More »

Fig 4 Expand

Fig 5.

Representative results of loss and accuracy during DCNN training without transfer learning.

Abbreviations: DCNN, deep convolutional neural network.

More »

Fig 5 Expand

Table 3.

Representative result of confusion matrix between true labels and predicted labels by DCNN with transfer learning.

More »

Table 3 Expand

Table 4.

Representative result of confusion matrix between true labels and predicted labels by DCNN without transfer learning.

More »

Table 4 Expand

Table 5.

Result of averaged confusion matrix between true labels and predicted labels by DCNN with transfer learning.

More »

Table 5 Expand