Table 2 Binary classification results for combined vein segmentation with classified difficulty levels
From: Deep learning HRNet FCN for blood vessel identification in laparoscopic pancreatic surgery
Training set | Difficulty | Combined vein testing set | ||
|---|---|---|---|---|
Recall | Precision | Dice | ||
LDP | Low | 84.10% | 76.30% | 0.645 |
High | 60.20% | 73.40% | 0.465 | |
Whipple | Low | 82.50% | 86.60% | 0.668 |
High | 61.90% | 80.70% | 0.512 | |
All | Low | 92.40% | 85.60% | 0.738 |
High | 72.50% | 80.50% | 0.537 | |
