Author Affiliations
1Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing, School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou, Inner Mongolia 0 14010, China2School of Information Engineering, Inner Mongolia University of Technology, Hohhot, Inner Mongolia 0 10051, China3School of Computer Engineering and Science, Shanghai University, Shanghai 200444, Chinashow less
Fig. 1. Image data of BraTS 2018 dataset. (a) FLAIR; (b) gold standard; (c) mask
[15-17] Fig. 2. Schematic diagram of dilated convolutional path
Fig. 3. Schematic diagram of parallel CNN
Fig. 4. Kernel of the dilated convolution. (a) Standard convolution kernel; (b) dilated convolution with filling rate of 1; (c) dilated convolution with filling rate of 3
Fig. 5. Kernel of the jagged convolution
Fig. 6. Structure diagram of DenseNet model
Fig. 7. Module of dense connection
Fig. 8. Module of transition
Fig. 9. Average Dice coefficient of segmentation results of different deep networks
Fig. 10. Structure of dilated convolutions and Dice coefficients of its segmentation results. (a) Schematic diagram; (b) average Dice coefficients
Fig. 11. Evaluation index of brain tumor total segmentation results. (a)Average accuracy; (b) sensitivity index; (c) specificity index; (d) average Dice coefficient
Fig. 12. Visual segmentation of tumor tissues by optimization model. (a) Sagittal images; (b) axial images; (c) coronal images
Layer | Path of densely connected network |
---|
Convolution | 3×3×3 conv, stride 2 | Pooling | 3×3×3 max pooling, stride 2 | Densely connected | ×30,×30,×30,×30 | Transition | 1×1×1 conv, 2×2×2 average pooling, stride 2 | Densely connected | ×40,×40, ×40,×40 | Transition | 1×1×1 conv, 2×2×2 average pooling, stride 2 | Densely connected | ×50,×50,×50,×50 | Classificationlayer | 3×3×3 global average pooling, fully connected, Softmax |
|
Table 1. Structure of densely connected network Dense-12
Layer | Sensitivity | Specificity | Average Dice | Time /h |
---|
Dense-8 | 0.8076 | 0.9603 | 0.6719 | 141.7 | Dense-10 | 0.8315 | 0.9671 | 0.7095 | 189.6 | Dense-12 | 0.8784 | 0.9835 | 0.8690 | 256.0 | Dense-15 | 0.8619 | 0.9883 | 0.8836 | 359.5 |
|
Table 2. Comparison of CNNs with different depths
Model | Dice coefficient |
---|
Complete | Core | Enhancing |
---|
Dilatedconvolution-CNN | 0.90 | 0.73 | 0.71 | Ref.[6] | 0.88 | 0.79 | 0.73 | Ref.[32] | 0.88 | 0.87 | 0.81 | Ref.[33] | 0.87 | 0.81 | 0.78 | Ref.[11] | 0.90 | 0.76 | 0.73 | Ref.[34] | 0.88 | 0.83 | 0.77 | Ref.[35] | 0.90 | 0.85 | 0.81 |
|
Table 3. Comparison of segmentation results of various tumor tissues by different models