A Fully Open and Generalizable Foundation Model for Ultrasound Clinical Applications
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909788558852096 |
|---|---|
| author | Zhang, Hongyuan Wu, Yuheng Zhao, Mingyang Chen, Zhiwei Li, Rebecca Zhu, Fei Zhao, Haohan Yuan, Xiaohua Yang, Meng Qiu, Chunli Cong, Xiang Chen, Haiyan Luan, Lina Wong, Randolph H. L. Liao, Huai Graham, Colin A Chang, Shi Tao, Guowei Yi, Dong Lei, Zhen Navab, Nassir Ourselin, Sebastien Luo, Jiebo Liu, Hongbin Meng, Gaofeng |
| author_facet | Zhang, Hongyuan Wu, Yuheng Zhao, Mingyang Chen, Zhiwei Li, Rebecca Zhu, Fei Zhao, Haohan Yuan, Xiaohua Yang, Meng Qiu, Chunli Cong, Xiang Chen, Haiyan Luan, Lina Wong, Randolph H. L. Liao, Huai Graham, Colin A Chang, Shi Tao, Guowei Yi, Dong Lei, Zhen Navab, Nassir Ourselin, Sebastien Luo, Jiebo Liu, Hongbin Meng, Gaofeng |
| contents | Artificial intelligence (AI) that can effectively learn ultrasound representations by integrating multi-source data holds significant promise for advancing clinical care. However, the scarcity of large labeled datasets in real-world clinical environments and the limited generalizability of task-specific models have hindered the development of generalizable clinical AI models for ultrasound applications. In this study, we present EchoCare, a novel ultrasound foundation model for generalist clinical use, developed via self-supervised learning on our curated, publicly available, large-scale dataset EchoCareData. EchoCareData comprises 4.5 million ultrasound images, sourced from over 23 countries across 5 continents and acquired via a diverse range of distinct imaging devices, thus encompassing global cohorts that are multi-center, multi-device, and multi-ethnic. Unlike prior studies that adopt off-the-shelf vision foundation model architectures, we introduce a hierarchical classifier into EchoCare to enable joint learning of pixel-level and representation-level features, capturing both global anatomical contexts and local ultrasound characteristics. With minimal training, EchoCare outperforms state-of-the-art comparison models across 10 representative ultrasound benchmarks of varying diagnostic difficulties, spanning disease diagnosis, lesion segmentation, organ detection, landmark prediction, quantitative regression, imaging enhancement and report generation. The code and pretrained model are publicly released, rendering EchoCare accessible for fine-tuning and local adaptation, supporting extensibility to additional applications. EchoCare provides a fully open and generalizable foundation model to boost the development of AI technologies for diverse clinical ultrasound applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11752 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Fully Open and Generalizable Foundation Model for Ultrasound Clinical Applications Zhang, Hongyuan Wu, Yuheng Zhao, Mingyang Chen, Zhiwei Li, Rebecca Zhu, Fei Zhao, Haohan Yuan, Xiaohua Yang, Meng Qiu, Chunli Cong, Xiang Chen, Haiyan Luan, Lina Wong, Randolph H. L. Liao, Huai Graham, Colin A Chang, Shi Tao, Guowei Yi, Dong Lei, Zhen Navab, Nassir Ourselin, Sebastien Luo, Jiebo Liu, Hongbin Meng, Gaofeng Computer Vision and Pattern Recognition Artificial intelligence (AI) that can effectively learn ultrasound representations by integrating multi-source data holds significant promise for advancing clinical care. However, the scarcity of large labeled datasets in real-world clinical environments and the limited generalizability of task-specific models have hindered the development of generalizable clinical AI models for ultrasound applications. In this study, we present EchoCare, a novel ultrasound foundation model for generalist clinical use, developed via self-supervised learning on our curated, publicly available, large-scale dataset EchoCareData. EchoCareData comprises 4.5 million ultrasound images, sourced from over 23 countries across 5 continents and acquired via a diverse range of distinct imaging devices, thus encompassing global cohorts that are multi-center, multi-device, and multi-ethnic. Unlike prior studies that adopt off-the-shelf vision foundation model architectures, we introduce a hierarchical classifier into EchoCare to enable joint learning of pixel-level and representation-level features, capturing both global anatomical contexts and local ultrasound characteristics. With minimal training, EchoCare outperforms state-of-the-art comparison models across 10 representative ultrasound benchmarks of varying diagnostic difficulties, spanning disease diagnosis, lesion segmentation, organ detection, landmark prediction, quantitative regression, imaging enhancement and report generation. The code and pretrained model are publicly released, rendering EchoCare accessible for fine-tuning and local adaptation, supporting extensibility to additional applications. EchoCare provides a fully open and generalizable foundation model to boost the development of AI technologies for diverse clinical ultrasound applications. |
| title | A Fully Open and Generalizable Foundation Model for Ultrasound Clinical Applications |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.11752 |