Opto-Electronic Engineering, Volume. 50, Issue 10, 230161-1(2023)
Adaptive feature fusion cascade Transformer retinal vessel segmentation algorithm
Figures & Tables(21)
Fig. 1. Adaptive feature fusion cascade Transformer retinal vessel segmentation algorithm
Fig. 8. Results of retinal vessel segmentation by different algorithms
Fig. 9. Image of retinal blood vessel local segmentation by different algorithms
Fig. 10. Comparison between P-R curve and ROC curve of different algorithms in DRIVE dataset
Fig. 11. Comparison between P-R curve and ROC curve of different algorithms in CHASE_DB1 dataset
Fig. 12. Plot of training loss curves in DRIVE dataset and CHASE_DB1 dataset
Table 1. Performance metrics of different algorithms for the DRIVE dataset /%
View tableView in ArticleTable 1. Performance metrics of different algorithms for the DRIVE dataset /%
数据集 方法 Acc Sen Spe F1 AUC DRIVE U-Net 96.97 80.19 98.58 82.26 98.66 Attention U-Net 97.04 79.19 98.75 82.41 98.72 Dense U-Net 96.99 79.60 98.66 82.25 98.69 FR U-Net 97.04 78.96 98.78 82.42 98.74 Ours 97.09 80.38 98.69 82.87 98.81
Table 2. Performance metrics of different algorithms for the CHASE-DB1 dataset /%
View tableView in ArticleTable 2. Performance metrics of different algorithms for the CHASE-DB1 dataset /%
数据集 方法 Acc Sen Spe F1 AUC CHASE_DB1 U-Net 97.50 80.79 98.62 80.32 98.92 Attention U-Net 97.57 78.99 98.82 80.43 98.92 Dense U-Net 97.53 81.51 98.54 80.80 98.95 FR U-Net 97.44 80.28 98.60 79.85 98.76 Ours 97.60 81.05 98.71 81.02 98.99
Table 3. Performance metrics of different algorithms for the STARE dataset /%
View tableView in ArticleTable 3. Performance metrics of different algorithms for the STARE dataset /%
数据集 方法 Acc Sen Spe F1 AUC STARE U-Net 97.53 79.22 99.06 83.15 99.05 Attention U-Net 97.55 78.98 99.09 83.17 99.06 Dense U-Net 97.55 79.68 99.05 83.36 99.09 FR U-Net 97.51 79.84 98.96 82.99 99.01 Ours 97.57 80.32 98.99 83.42 99.10
Table 4. Comparison results of DRIVE dataset /%
View tableView in ArticleTable 4. Comparison results of DRIVE dataset /%
方法 Acc Sen Spe AUC 文献[ 23 ]96.38 78.05 98.16 96.82 文献[ 24 ]94.80 73.52 97.75 96.78 文献[ 25 ]95.56 78.14 98.10 97.80 文献[ 26 ]96.10 81.25 97.63 文献[ 27 ]95.76 79.43 98.14 98.23 文献[ 28 ]95.68 79.21 98.10 98.06 文献[ 29 ]95.68 81.15 97.80 98.10 Ours 97.09 80.38 98.69 98.81
Table 5. Comparison results of CHASE_DB1 dataset /%
View tableView in ArticleTable 5. Comparison results of CHASE_DB1 dataset /%
方法 Acc Sen Spe AUC 文献[ 25 ]97.11 76.97 98.65 96.48 文献[ 26 ]94.52 72.79 96.58 96.81 文献[ 27 ]95.90 81.95 97.27 97.84 文献[ 28 ]95.78 80.12 97.30 文献[ 29 ]95.87 79.47 98.55 98.86 文献[ 30 ]96.35 78.18 98.19 98.10 文献[ 31 ]96.64 80.75 98.41 98.72 Ours 97.60 81.05 98.71 98.99
Table 6. Comparison results of STARE dataset /%
View tableView in ArticleTable 6. Comparison results of STARE dataset /%
方法 Acc Sen Spe AUC 文献[ 25 ]97.11 78.67 98.80 96.70 文献[ 26 ]95.48 72.65 97.59 96.86 文献[ 28 ]95.86 80.78 97.21 文献[ 29 ]96.92 82.98 98.55 98.95 文献[ 30 ]96.78 83.52 98.23 98.75 文献[ 32 ]97.47 81.90 98.74 97.06 Ours 97.57 80.32 98.99 99.10
Table 7. Analysis of ablation experiments on the DRIVE dataset /%
View tableView in ArticleTable 7. Analysis of ablation experiments on the DRIVE dataset /%
模型 Acc Sen Spe F1 AUC S1 96.97 80.19 98.58 82.26 98.66 S2 97.06 79.69 98.73 82.62 98.75 S3 97.06 78.18 98.87 82.36 98.87 S4 97.09 80.38 98.69 82.87 98.81
Table 8. Analysis of ablation experiments on the CHASE-DB1 dataset /%
View tableView in ArticleTable 8. Analysis of ablation experiments on the CHASE-DB1 dataset /%
模型 Acc Sen Spe F1 AUC S1 97.50 80.79 98.62 80.32 98.66 S2 97.55 79.01 98.80 80.31 98.95 S3 97.59 80.52 98.74 80.85 98.99 S4 97.60 81.05 98.71 81.02 98.99
Table 9. Analysis of ablation experiments on the STARE dataset /%
View tableView in ArticleTable 9. Analysis of ablation experiments on the STARE dataset /%
模型 Acc Sen Spe F1 AUC S1 97.53 79.22 99.06 83.15 99.05 S2 97.55 79.38 99.04 83.16 99.04 S3 97.55 79.90 99.01 83.32 99.08 S4 97.57 80.32 98.99 83.42 99.10
Tools
Get Citation
Copy Citation Text
Liming Liang, Baohe Lu, Pengwei Long, Yuan Yang. Adaptive feature fusion cascade Transformer retinal vessel segmentation algorithm[J]. Opto-Electronic Engineering, 2023, 50(10): 230161-1
Paper Information
Category: Article
Received: Jul. 3, 2023
Accepted: Oct. 7, 2023
Published Online: Jan. 22, 2024
The Author Email: Baohe Lu (卢宝贺)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20