Medical Image Segmentation on EndoScene
89.3mDiceTransUNet
Evaluation results
| Method | Links | ||
|---|---|---|---|
| TransUNetTraining images used=1450/25942024.03 | 89.3 | 66 | |
| IPS-16PNumber of Trainable Parameters=1.3M, Training images used=1450/2594, Prompt points=162024.03 | 88.8 | 81 | |
| SSFormerTraining images used=1450/25942024.03 | 88.7 | 82.1 | |
| IPS-5PNumber of Trainable Parameters=1.3M, Training images used=1450/2594, Prompt points=52024.03 | 85.4 | 76.4 | |
| PraNetTraining images used=1450/25942024.03 | 83.5 | 79.7 | |
| IPS-3P|16PNumber of Trainable Parameters=1.3M, Training images used=1450/2594, Training prompt points=3, Testing prompt points=162024.03 | 81.5 | 72.1 | |
| IPS-3PNumber of Trainable Parameters=1.3M, Training images used=1450/2594, Prompt points=32024.03 | 80.6 | 71.8 | |
| IPS-3P|5PNumber of Trainable Parameters=1.3M, Training images used=1450/2594, Training prompt points=3, Testing prompt points=52024.03 | 80.4 | 71.6 | |
| Med2DNumber of Trainable Parameters=184.5M, Training images used=5838/7935, Prompt points=162024.03 | 72.7 | 62 | |
| Med2DNumber of Trainable Parameters=184.5M, Training images used=5838/7935, Prompt points=52024.03 | 72.2 | 62.3 | |
| U-netTraining images used=1450/25942024.03 | 71 | 62.7 | |
| Med2DNumber of Trainable Parameters=184.5M, Training images used=5838/7935, Prompt points=32024.03 | 69.7 | 59.7 | |
| SAMPrompt points=162024.03 | 69.2 | 61.3 | |
| SAMPrompt points=52024.03 | 65.6 | 58.2 | |
| SAMPrompt points=32024.03 | 51.3 | 41.4 |