# Towards Real-World Ultrasound Understanding: Large Vision-Language Models from Multi-Image Examinations with Long-Form Reports

arXiv: https://arxiv.org/abs/2607.01908 · HTML: https://mlsanity.com/paper/2607.01908/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 20 of 20)

- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [Kimi-VL Technical Report](https://mlsanity.com/paper/2504.07491/) (2025)
- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale](https://mlsanity.com/paper/2406.19280/) (2024)
- [R2GenGPT: Radiology Report Generation with Frozen LLMs](https://mlsanity.com/paper/2309.09812/) (2023)
- [HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation](https://mlsanity.com/paper/2502.09838/) (2025)
- [USFM: A Universal Ultrasound Foundation Model Generalized to Tasks and Organs towards Label Efficient Image Analysis](https://mlsanity.com/paper/2401.00153/) (2023)
- [MedGemma 1.5 Technical Report](https://mlsanity.com/paper/2604.05081/) (2026)
- [FetalCLIP: A Visual-Language Foundation Model for Fetal Ultrasound Image Analysis](https://mlsanity.com/paper/2502.14807/) (2025)
- [A Fully Open and Generalizable Foundation Model for Ultrasound Clinical Applications](https://mlsanity.com/paper/2509.11752/) (2025)
- [Multimodal Large Language Models for Medical Report Generation via Customized Prompt Tuning](https://mlsanity.com/paper/2506.15477/) (2025)
- [EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence](https://mlsanity.com/paper/2509.14977/) (2025)
- [Ultrasound-CLIP: Semantic-Aware Contrastive Pre-training for Ultrasound Image-Text Understanding](https://mlsanity.com/paper/2604.01749/) (2026)
- [HAIBU-ReMUD: Reasoning Multimodal Ultrasound Dataset and Model Bridging to General Specific Domains](https://mlsanity.com/paper/2506.07837/) (2025)
- [UMind-VL: A Generalist Ultrasound Vision-Language Model for Unified Grounded Perception and Comprehensive Interpretation](https://mlsanity.com/paper/2511.22256/) (2025)

## Abstract (arXiv)

Large vision-language models (LVLMs) have achieved strong performance across many medical imaging tasks, yet their application to ultrasound remains limited due to its inherent complexity and variability. In this work, we revisit what is truly needed to enable real-world ultrasound understanding. Instead of introducing complex architectures or elaborate training strategies, we show that data scale and clinically faithful data alignment are the key factors. We construct a large-scale dataset of 1.5M real-world ultrasound examinations, containing 17.7M images, multi-organ coverage, and paired uncurated clinical reports. Crucially, we organize the data at the examination level, aligning multiple images with their corresponding reports to reflect real clinical workflows. We then fine-tune a standard LVLM using low-rank adaptation (LoRA) on this dataset without task-specific modifications. Surprisingly, this simple recipe already leads to strong performance across diverse ultrasound understanding tasks, outperforming prior methods designed with more complex pipelines. Beyond these results, we present model and data scaling analyses that provide insights into the role of scale in ultrasound LVLMs.