Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.25748 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912659167772672 |
|---|---|
| author | Weng, Taohan Hu, Kaibing Liu, Henan Liu, Siya Liu, Xiaoyang Liu, Zhenyu Ren, Jiren Wang, Boyan Wang, Boyang Wang, Yiyu Wu, Yalun Yan, Chaoran Yan, Kaiwen Yu, Jinze Zhang, Chi Zhang, Duo Zheng, Haoyun Guo, Xiaoqing Souquet, Jacques Guo, Hongcheng Le, Anjie |
| author_facet | Weng, Taohan Hu, Kaibing Liu, Henan Liu, Siya Liu, Xiaoyang Liu, Zhenyu Ren, Jiren Wang, Boyan Wang, Boyang Wang, Yiyu Wu, Yalun Yan, Chaoran Yan, Kaiwen Yu, Jinze Zhang, Chi Zhang, Duo Zheng, Haoyun Guo, Xiaoqing Souquet, Jacques Guo, Hongcheng Le, Anjie |
| contents | Ultrasound is crucial in modern medicine but faces challenges like operator dependence, image noise, and real-time scanning, hindering AI integration. While large multimodal models excel in other medical imaging areas, they struggle with ultrasound's complexities. To address this, we introduce Dolphin v1.0 (V1) and its reasoning-augmented version, Dolphin R1-the first large-scale multimodal ultrasound foundation models unifying diverse clinical tasks in a single vision-language framework.To tackle ultrasound variability and noise, we curated a 2-million-scale multimodal dataset, combining textbook knowledge, public data, synthetic samples, and general corpora. This ensures robust perception, generalization, and clinical adaptability.The Dolphin series employs a three-stage training strategy: domain-specialized pretraining, instruction-driven alignment, and reinforcement-based refinement. Dolphin v1.0 delivers reliable performance in classification, detection, regression, and report generation. Dolphin R1 enhances diagnostic inference, reasoning transparency, and interpretability through reinforcement learning with ultrasound-specific rewards.Evaluated on U2-Bench across eight ultrasound tasks, Dolphin R1 achieves a U2-score of 0.5835-over twice the second-best model (0.2968) setting a new state of the art. Dolphin v1.0 also performs competitively, validating the unified framework. Comparisons show reasoning-enhanced training significantly improves diagnostic accuracy, consistency, and interpretability, highlighting its importance for high-stakes medical AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25748 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dolphin v1.0 Technical Report Weng, Taohan Hu, Kaibing Liu, Henan Liu, Siya Liu, Xiaoyang Liu, Zhenyu Ren, Jiren Wang, Boyan Wang, Boyang Wang, Yiyu Wu, Yalun Yan, Chaoran Yan, Kaiwen Yu, Jinze Zhang, Chi Zhang, Duo Zheng, Haoyun Guo, Xiaoqing Souquet, Jacques Guo, Hongcheng Le, Anjie Computer Vision and Pattern Recognition Artificial Intelligence Ultrasound is crucial in modern medicine but faces challenges like operator dependence, image noise, and real-time scanning, hindering AI integration. While large multimodal models excel in other medical imaging areas, they struggle with ultrasound's complexities. To address this, we introduce Dolphin v1.0 (V1) and its reasoning-augmented version, Dolphin R1-the first large-scale multimodal ultrasound foundation models unifying diverse clinical tasks in a single vision-language framework.To tackle ultrasound variability and noise, we curated a 2-million-scale multimodal dataset, combining textbook knowledge, public data, synthetic samples, and general corpora. This ensures robust perception, generalization, and clinical adaptability.The Dolphin series employs a three-stage training strategy: domain-specialized pretraining, instruction-driven alignment, and reinforcement-based refinement. Dolphin v1.0 delivers reliable performance in classification, detection, regression, and report generation. Dolphin R1 enhances diagnostic inference, reasoning transparency, and interpretability through reinforcement learning with ultrasound-specific rewards.Evaluated on U2-Bench across eight ultrasound tasks, Dolphin R1 achieves a U2-score of 0.5835-over twice the second-best model (0.2968) setting a new state of the art. Dolphin v1.0 also performs competitively, validating the unified framework. Comparisons show reasoning-enhanced training significantly improves diagnostic accuracy, consistency, and interpretability, highlighting its importance for high-stakes medical AI. |
| title | Dolphin v1.0 Technical Report |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.25748 |