# Adapting Vision-Language Foundation Model for Next Generation Medical Ultrasound Image Analysis

arXiv: https://arxiv.org/abs/2506.08849 · HTML: https://mlsanity.com/paper/2506.08849/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 34 of its 66 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Placed in

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

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [Demystifying CLIP Data](https://mlsanity.com/paper/2309.16671/) (2023)
- [PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents](https://mlsanity.com/paper/2303.07240/) (2023)
- [OmniVL:One Foundation Model for Image-Language and Video-Language Tasks](https://mlsanity.com/paper/2209.07526/) (2022)
- [Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?](https://mlsanity.com/paper/2112.13906/) (2021)
- [USFM: A Universal Ultrasound Foundation Model Generalized to Tasks and Organs towards Label Efficient Image Analysis](https://mlsanity.com/paper/2401.00153/) (2023)
- [ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Dataset](https://mlsanity.com/paper/2405.10004/) (2024)
- [Are Natural Domain Foundation Models Useful for Medical Image Classification?](https://mlsanity.com/paper/2310.19522/) (2023)
- [UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities](https://mlsanity.com/paper/2412.10372/) (2024)
- [5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks](https://mlsanity.com/paper/2408.08345/) (2024)
- [Exploring Transfer Learning in Medical Image Segmentation using Vision-Language Models](https://mlsanity.com/paper/2308.07706/) (2023)
- [MicroSegNet: A Deep Learning Approach for Prostate Segmentation on Micro-Ultrasound Images](https://mlsanity.com/paper/2305.19956/) (2023)

## Built on by (most cited first, 6 of 6)

- [BleedOrigin: Dynamic Bleeding Source Localization in Endoscopic Submucosal Dissection via Dual-Stage Detection and Tracking](https://mlsanity.com/paper/2507.15094/) (2025)
- [Multiscale Switch for Semi-Supervised and Contrastive Learning in Medical Ultrasound Image Segmentation](https://mlsanity.com/paper/2603.18655/) (2026)
- [Adaptive transfer learning for surgical tool presence detection in laparoscopic videos through gradual freezing fine-tuning](https://mlsanity.com/paper/2510.15372/) (2025)
- [UltraG-Ray: Physics-Based Gaussian Ray Casting for Novel Ultrasound View Synthesis](https://mlsanity.com/paper/2603.29022/) (2026)
- [Risk-Routed Implicit Boundary Refinement for Robust Ultrasound Image Segmentation](https://mlsanity.com/paper/2607.21787/) (2026)
- [Learning Features, Not Layouts: Feature-Axis Attention as a Transfer Prior for Medical Imaging](https://mlsanity.com/paper/2610.13012/) (2026)

## Abstract (arXiv)

Vision-Language Foundation Models (VLFMs) exhibit remarkable generalization, yet their direct application to medical ultrasound is severely hindered by a profound modality gap. The unique acoustic physics of ultrasound, characterized by speckle noise, shadowing, and heterogeneous textures, often degrades the performance of off-the-shelf VLFMs. To bridge this gap, we propose a novel Hybrid Tuning (HT) strategy for the parameter-efficient adaptation of CLIP-based models to ultrasound analysis. Instead of updating the pre-trained weights, HT freezes the visual backbone and integrates a specialized lightweight adapter. This adapter features a Frequency Filtering module to suppress domain-specific periodic artifacts and a Noise Estimation module to dynamically calibrate feature representations. Extensive evaluations across six multi-center datasets demonstrate that our HT-enhanced models significantly outperform existing state-of-the-art adapters and medical VLFMs in both segmentation and classification tasks. Notably, HT exhibits exceptional data efficiency in few-shot scenarios and robust cross-dataset generalization. Our findings prove that preserving pre-trained semantic priors while explicitly modeling ultrasound-specific noise is key to unlocking foundational intelligence in automated ultrasound diagnosis. The source code is available at https://github.com/jinggqu/NextGen-UIA.