Pelvic fracture detection on Pelvic X-ray VIS (test)
0.9334AUCPelFANet
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PelFANetArchitecture=dual-input, attention-fused framework2025.09 | 0.9334 | 84.71 | |
| DRR20Backbone=ResNet-based, Pretraining=Digitally Reconstructed Radiographs (DRR) synthetic data2025.09 | 0.929 | 85.2 | |
| ImageNet+DRR20Backbone=ResNet-based, Pretraining=ImageNet and DRR2025.09 | 0.928 | 83.9 | |
| ImageNet+DRR20_FullBackbone=ResNet-based, Pretraining=ImageNet and DRR (Full)2025.09 | 0.9151 | 83.3 | |
| ImageNetBackbone=ResNet-based, Pretraining=ImageNet2025.09 | 0.8961 | 8,000 |