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.

CT examples with lung nodules in different categories.

They are benign (left), primary malignant (middle) and metastatic malignant (right), alone with 3 different view areas including 40×40, 50×50 and 60×60.

More »

Fig 1 Expand

Fig 2.

Two kinds of the multi-view strategy.

The one-view-one-network strategy (top) employs a separate network for images from each view (cropping size), while the multi-view-one-network strategy (bottom) uses one network for all views.

More »

Fig 2 Expand

Fig 3.

The architectures of the 3D single view CNN (SV-CNN) (top) and 3D MV-CNN (bottom).

More »

Fig 3 Expand

Table 1.

The configuration of the network with chain architecture.

More »

Table 1 Expand

Fig 4.

The overall architecture of the 3D multi-view Inception network (left). This architecture applies to Inception1 and Inception2. The output sizes of each layer for the binary classification (middle) and the ternary classification (right) are different, which are also shown in this figure. Note that the output of each layer is a 5D tensor as described in the previous section. The details of the Inception module are shown in Fig 5.

More »

Fig 4 Expand

Fig 5.

The detail of the Inception module in Fig 4: 3D Inception1 (left) and 3D Inception2 (right).

More »

Fig 5 Expand

Fig 6.

The overall architecture of the Inception-ResNet network.

More »

Fig 6 Expand

Fig 7.

The process of generating 3D volume data.

More »

Fig 7 Expand

Table 2.

The number of patients and lesions.

More »

Table 2 Expand

Fig 8.

The error rate of the 3D SV-CNN (top) and 3D MV-CNN (bottom) with chain architecture for the binary classification.

From left to right, there are the error rates of Softmax, CNN1, CNN2 and CNN3, respectively.

More »

Fig 8 Expand

Fig 9.

The error rate of the 3D SV-CNN (top) and 3D MV-CNN (bottom) with chain architecture for the ternary classification.

From left to right, there are the error rates of Softmax, CNN1, CNN2 and CNN3, respectively.

More »

Fig 9 Expand

Table 3.

The result of the binary classification for the networks with chain architecture.

More »

Table 3 Expand

Table 4.

The result of the ternary classification for the networks with chain architecture.

More »

Table 4 Expand

Table 5.

The validation error rate of the classification for the 3D multi-view networks with DAG architecture.

More »

Table 5 Expand

Table 6.

Some classification results on LIDC-IDRI dataset.

More »

Table 6 Expand

Fig 10.

The ROC curves of MV-softmax, 3D MV-CNN1 and 3D MV-inception1.

More »

Fig 10 Expand

Fig 11.

The number of parameters vs. training time and validation error rate for the binary classification (left) and the ternary classification (right).

The area of the circles represents the corresponding validation error rate.

More »

Fig 11 Expand

Fig 12.

The result of grid search for the binary (left) and ternary (right) classification.

More »

Fig 12 Expand

Table 7.

Compare the multi-view-one-network strategy with the one-view-one-network strategy.

More »

Table 7 Expand