Author Affiliations
School of Information Science & Technology, Northwest University, Xi'an, Shaanxi 710127, Chinashow less
Fig. 1. Diagram of multi-channel splicing structure
Fig. 2. Structure of AttentionNet
Fig. 3. Mapping relationship between label and mapping graph
Fig. 4. Structure of Dense block
Fig. 5. Structure of DenseUnet
Fig. 6. Relationship between accuracy, loss value, and iterations of different networks on validation set. (a) Relationship between iterations and accuracy; (b) relationship between iterations and loss value
Fig. 7. Error analysis diagram
Fig. 8. Error analysis diagram of four training samples
Fig. 9. Test sample 03_365_2. (a) Raw data; (b) label; (c) pre-trained prediction map; (d) segmentation result of Dense_end
Fig. 10. Image data and location pixel distribution infographic. (a) Original image; (b) location pixel distribution infographic
Fig. 11. Segmentation effect of traditional DenseUnet and proposed method. (a) Original image; (b) label; (c) traditional DenseUnet; (d)proposed method
Network | DDice | DIOU | DVS |
---|
Unet | 94.19 | 89.68 | 96.49 | Traditional DenseUnet | 95.48 | 91.51 | 97.81 |
|
Table 1. Segmentation results of Unet and traditional DenseUnetunit: %
Network | Number of parameters |
---|
Traditional DenseUnet | 46978875 | Unet | 31030593 | Proposed Method | 39543451 |
|
Table 2. Number of parameters of different networks
Training sample | DDice | DIOU | DVS |
---|
Traditional DenseUnet | 95.48 | 91.50 | 97.81 | Dense_atten | 95.88 | 92.18 | 98.42 | Dense_pred | 94.03 | 89.00 | 97.77 | Dense_end | 96.42 | 93.19 | 98.00 |
|
Table 3. Comparison of segmentation results of different training samplesunit: %