Breast Ultrasound Diagnosis on Overall pooled micro average
0.741AUCUltrasoundAgents
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| UltrasoundAgentsBackbone=Qwen2.5-3B, Training Strategy=Three-stage RL (GRPO) and SFT, Inference Workflow=ROI -> attribute -> diagnosis evidence-chain2026.03 | 0.741 | 81.3 | 51.5 | 0.224 | |
| Qwen2.5-3B-COT-SFTBackbone=Qwen2.5-3B, Training Strategy=SFT on template-based reasoning data, Inference Workflow=Intermediate attribute evidence2026.03 | 0.71 | 75.1 | 46.8 | 0.204 | |
| Think-with-ImageBackbone=Qwen2.5-3B, Training Strategy=DeepEyes-style single-agent workflow, Inference Workflow=ROI localization -> crop-and-zoom -> re-analyze2026.03 | 0.512 | 68.3 | 10.1 | 0.004 | |
| Qwen2.5-3B-Zero-ShotBackbone=Qwen2.5-3B, Training Strategy=Zero-shot, Inference Workflow=Directly prompts on full image2026.03 | 0.476 | 60.2 | 11.7 | 0.014 |