Research map / Large language models / Retrieval and knowledge
Organ-Aware Routing Mixture-of-Retrieval Augmented Generation for Fetal Ultrasound Reporting
Bin Pu, Siyu Wang, Rongbin Li, Xinpeng Ding, Lei Zhao, Chaoqi Chen, Shengli Li, Kenli Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace one-to-multiple retrieval with organ-wise multiple one-to-one retrieval (ablation) | ORM-RAG · FetusR | average diagnostic accuracy (%): 52.3 -> 65.3 | Improved |
| replace multiple-to-multiple retrieval with organ-wise one-to-one retrieval (ablation) | ORM-RAG · FetusR | average diagnostic accuracy (%): 43.8 -> 65.3 | Improved |
| add mixture-of-retrieval to baseline InternVL2-1B (ablation) | InternVL2-1B · FetusR | CIDEr: 2.293 -> 4.928 | Improved |
| add dynamic routing on top of MoR (ablation) | ORM-RAG · FetusR | average diagnostic accuracy (%): 62.0 -> 65.3 | Improved |
| add abnorm-aware supervision to retriever training (ablation) | ORM-RAG · FetusR | average diagnostic accuracy (%): 62.0 -> 65.3 | Improved |
| add abnorm-aware supervision to retriever training (ablation) | ORM-RAG · FetusR | retrieval R@5: 0.928 -> 0.917 | Mixed |
| add label trend continuity to global agreement in routing (ablation) | Dynamic routing · FetusR | average diagnostic accuracy (%): 63.9 -> 65.3 | Improved |
| add global agreement routing (vs no routing) (ablation) | Dynamic routing · FetusR | average diagnostic accuracy (%): 62.0 -> 63.9 | Improved |
| ORM-RAG vs BiomedCLIP retrieval baseline | ORM-RAG · FetusR | BLEU-4: 0.78 -> 0.79 | Improved |
Closest papers by meaning
- F$^2$-Assist: Multi-Phase Fetal Growth Forecast and Report Generation from Ultrasound Examination (CVPR 2026 · similarity 0.87)
- MCAT: Visual Query-Based Localization of Standard Anatomical Clips in Fetal Ultrasound Videos Using Multi-Tier Class-Aware Token Transformer (AAAI 2025 · similarity 0.86)
- Unsupervised Domain Adaptation for Anatomical Structure Detection in Ultrasound Images (ICML 2024 · similarity 0.86)
- FETAL-GAUGE: A BENCHMARK FOR ASSESSING VISION-LANGUAGE MODELS IN FETAL ULTRASOUND (ICLR 2026 · similarity 0.86)
- U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding (ICLR 2026 · similarity 0.85)
- Anatomical Knowledge Mining and Matching for Semi-supervised Medical Multi-structure Detection (AAAI 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
