发表机构
Faculty of Computer Science and Technology, Ocean University of China; School of Information Science and Engineering, Shandong University; the Qilu Second Hospital of Shandong University; Innovation School of Artificial Intelligence, Hefei University of Technology（中国海洋大学计算机科学与技术学院; 山东大学信息科学与工程学院; 山东大学第二齐鲁医院; 合肥工业大学人工智能创新学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有超声扫描方法泛化性与稳定性不足的问题，提出US-VLA模型，设计超声感知专家融合模块并构建US-VLA-Data数据集，在腹部超声探头操作任务中取得竞争力性能。
AI 中文摘要
人工智能辅助超声扫描通过为标准化图像采集提供实时指导并减少对操作者的依赖，提升了诊断的可靠性和效率。然而，现有的强化学习及学习辅助超声扫描方法通常依赖精心设计的奖励函数或大量交互数据，这限制了它们在不同设备、患者群体及复杂临床场景中的泛化能力和稳定性。为应对这些挑战，我们提出了用于自动化超声扫描的超声-视觉-动作模型（US-VLA），该模型可显式编码临床语义目标，并在实时超声反馈下生成连续的探头操作动作。具体而言，我们首先设计了超声感知专家融合模块，以联合整合超声观测结果与辅助上下文信息，使语义超声反馈能有效引导扫描过程。随后，我们构建了包含肝脏和肾脏检查的真实世界数据集US-VLA-Data，该数据集涵盖5个临床定义的标准切面，包含320条专家扫描轨迹和约80000个同步时间步。大量实验表明，US-VLA在超声探头操作任务中取得了具有竞争力的性能，表明其在评估的腹部超声场景内的有效性和良好的泛化性。源代码可在指定URL获取。
英文摘要
Artificial intelligence-assisted ultrasound scanning enhances diagnostic reliability and efficiency by providing real-time guidance for standardized image acquisition and reducing operator dependence. However, existing reinforcement learning and learning-assisted ultrasound scanning methods typically rely on carefully designed reward functions or extensive interaction data, which limits their generalization ability and stability across different devices, patient populations, and complex clinical scenarios. To address these challenges, we propose an ultrasound vision-language-action model (US-VLA) for automated ultrasound scanning that explicitly encodes clinical semantic goals and generates sequential probe manipulation actions under real-time ultrasound feedback. In particular, we first design an ultrasound-aware expert fusion module to jointly integrate ultrasound observations with auxiliary contextual information, enabling semantic ultrasound feedback to effectively guide the scanning process. Then, we construct US-VLA-Data, a real-world dataset covering liver and kidney examinations, which includes five clinically defined standard planes and comprises 320 expert scanning trajectories with approximately 80,000 synchronized timesteps. Extensive experiments demonstrate that US-VLA achieves competitive performance in ultrasound probe manipulation tasks, indicating its effectiveness and promising generalization within the evaluated abdominal ultrasound setting. The source code is available at https://github.com/VMVLab/US-VLA.
