# Towards Reliable Fetal Ultrasound Interpretation with Multi-Agent Collaboration

arXiv: https://arxiv.org/abs/2605.25357 · HTML: https://mlsanity.com/paper/2605.25357/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 56 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 21 of 21)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://mlsanity.com/paper/2311.10537/) (2023)
- [HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale](https://mlsanity.com/paper/2406.19280/) (2024)
- [MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making](https://mlsanity.com/paper/2404.15155/) (2024)
- [Almanac: Retrieval-Augmented Language Models for Clinical Medicine](https://mlsanity.com/paper/2303.01229/) (2023)
- [SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound](https://mlsanity.com/paper/1612.05601/) (2016)
- [USFM: A Universal Ultrasound Foundation Model Generalized to Tasks and Organs towards Label Efficient Image Analysis](https://mlsanity.com/paper/2401.00153/) (2023)
- [Beyond Adapting SAM: Towards End-to-End Ultrasound Image Segmentation via Auto Prompting](https://mlsanity.com/paper/2309.06824/) (2023)
- [A Review on Deep-Learning Algorithms for Fetal Ultrasound-Image Analysis](https://mlsanity.com/paper/2201.12260/) (2022)
- [CT-Agent: A Multimodal-LLM Agent for 3D CT Radiology Question Answering](https://mlsanity.com/paper/2505.16229/) (2025)
- [AutoFB: Automating Fetal Biometry Estimation from Standard Ultrasound Planes](https://mlsanity.com/paper/2107.05255/) (2021)
- [BiometryNet: Landmark-based Fetal Biometry Estimation from Standard Ultrasound Planes](https://mlsanity.com/paper/2206.14678/) (2022)
- [MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning](https://mlsanity.com/paper/2602.03320/) (2026)
- [Meissa: Multi-modal Medical Agentic Intelligence](https://mlsanity.com/paper/2603.09018/) (2026)
- [3DMedAgent: Unified Perception-to-Understanding for 3D Medical Analysis](https://mlsanity.com/paper/2602.18064/) (2026)
- [Generative Diffusion Model Bootstraps Zero-shot Classification of Fetal Ultrasound Images In Underrepresented African Populations](https://mlsanity.com/paper/2407.20072/) (2024)
- [Segmenting Fetal Head with Efficient Fine-tuning Strategies in Low-resource Settings: an empirical study with U-Net](https://mlsanity.com/paper/2407.20086/) (2024)
- [Advancing Fetal Ultrasound Image Quality Assessment in Low-Resource Settings](https://mlsanity.com/paper/2507.22802/) (2025)
- [HeartAgent: An Autonomous Agent System for Explainable Differential Diagnosis in Cardiology](https://mlsanity.com/paper/2603.10764/) (2026)

## Abstract (arXiv)

Automated fetal ultrasound interpretation requires a workflow from visual perception, including plane recognition and anatomical segmentation, to clinical understanding, including biometric measurement and diagnostic reporting. However, the prevailing "one-task, one-model" paradigm limits systematic integration of evidence across this multi-step process. Although multimodal large language models (MLLMs) show promising visual understanding, their limited domain-specific grounding and hallucination risks restrict reliability in fetal ultrasound analysis. To address these limitations, we propose FetUSAgents, a tool-augmented multi-agent system for comprehensive fetal ultrasound interpretation, supporting visual question answering (VQA), report generation, image captioning, and video summarization. FetUSAgents coordinates task-specific visual tools through collaborative LLM agents and decomposes clinical queries into subtasks that progress from anatomical recognition to quantitative measurement. We further introduce Dual-Path Evidence Arbitration (DPEA), which integrates LLM-based deliberative reasoning with structured computational evidence from specialized visual tools. A retrieval-enhanced evidence bank consolidates intermediate findings to support traceable and clinically grounded conclusions. In addition, we construct FetUS-VQA, a dedicated VQA benchmark for fetal ultrasound, comprising 1,892 images and 3,205 question-answer pairs across 10 clinical tasks. Extensive out-of-distribution experiments show that FetUSAgents outperforms general and medical MLLMs, exceeding the strongest baseline by more than 25 percent in VQA accuracy. These results suggest a scalable route toward evidence-driven clinical assistants for prenatal imaging. Code is available.