Table 3.
Evaluation results of the four best validation models on the CSD test set; the best metrics are highlighted in bold
| CSD | DSC | ASD | PRE (%) | SEN (%) | SPE (%) |
|---|---|---|---|---|---|
| U-Net | 0.705 | 61.69 | 65.5 | 76.8 | 99.905 |
| V-Net | 0.817 | 0.99 | 80.7 | 82.9 | 99.953 |
| UNETR | 0.822 | 3.68 | 80.9 | 83.8 | 99.953 |
| SwinUNETR | 0.853 | 2.67 | 84.8 | 86.0 | 99.963 |
CSD Cerebrovascular segmentation dataset, MLD Middle cerebral artery M1 segment with lenticulostriate artery segmentation dataset, DSC Dice similarity coefficient, ASD Average surface distance, PRE Precision, SEN Sensitivity, SPE Specificity