摘要
Ultrasound is the preferred early cancer screening modality due to non-ionizing radiation, cost-effectiveness, and real-time imaging, yet conventional diagnosis relies heavily on physician expertise, causing significant subjectivity and limited efficiency. Vision-Language Models (VLMs) show promise but lack ultrasound-specific knowledge and multi-organ generalization. We propose EchoVLM, the first open-source 10-billion-parameter ultrasound-tailored VLM with a Mixture-of-Experts (MoE) architecture. It is infused with knowledge across seven anatomical systems, trained on 208,941 clinical cases, 1.47 million ultrasound key-frame images, and over 100 diseases or imaging findings. Supporting clinical report generation, diagnosis prediction, and Visual Question Answering (VQA), it outperforms Qwen2-VL by 7.58 BLEU-1 and 3.45 ROUGE-1 points in report generation. This work shows substantial potential for establishing a general-purpose ultrasound VLM and lays a technical foundation for clinical translation.
| 源语言 | 英语 |
|---|---|
| 主期刊名 | Long Papers |
| 编辑 | Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens |
| 出版商 | Association for Computational Linguistics (ACL) |
| 页 | 10800-10822 |
| 页数 | 23 |
| ISBN(电子版) | 9798891763906 |
| DOI | |
| 出版状态 | 已出版 - 2026 |
| 活动 | 64th Annual Meeting of the Association for Computational Linguistics, ACL 2026 - San Diego, 美国 期限: 2 7月 2026 → 7 7月 2026 |
丛书
| 姓名 | Proceedings of the Annual Meeting of the Association for Computational Linguistics |
|---|---|
| 卷 | 1 |
| ISSN(印刷版) | 0736-587X |
会议
| 会议 | 64th Annual Meeting of the Association for Computational Linguistics, ACL 2026 |
|---|---|
| 国家/地区 | 美国 |
| 市 | San Diego |
| 时期 | 2/07/26 → 7/07/26 |
联合国可持续发展目标
此成果有助于实现下列可持续发展目标:
-
可持续发展目标 3 良好健康与福祉
学术指纹
探究 'EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence' 的科研主题。它们共同构成独一无二的学术指纹。引用此
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver