Scholarlink

<p>While promising in general medical imaging like CT and MRI, large vision-language models (LVLMs) struggle in ultrasonography due to a profound visual-semantic gap and a scarcity of instruction-following data. Translating the inherently noisy and operator-dependent ultrasound images into precise clinical descriptions remains a complex reasoning challenge for general-purpose vision-language models. To bridge this gap, we develop <b>SonoInstruct</b>, a large-scale multi-source dataset curated from over 30 ultrasound sources, providing 110k+ images and 260k+ instruction-following instances. For comprehensive evaluation, we establish <b>SonoBench</b>, a multi-dimensional benchmark suite that assesses eight core capabilities, including performance in out-of-distribution (OOD) scenarios. To verify the effectiveness of our dataset, we fine-tuned Qwen3-VL-2B-Instruct on SonoInstruct, yielding Qwen3-VL-2B-Sono, which achieves a 30.3% relative improvement over the base model on the SonoBench benchmark. These results demonstrate that SonoInstruct effectively bridges the gap between noisy sonographic images and clinical reasoning, establishing a robust foundation for AI-driven ultrasound applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A multimodal instruction dataset and benchmark for ultrasound understanding

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月26日

查看全文
  • Shijie Wang,
  • Yingnan Wu,
  • Yilun Zhang,
  • Zeyu Lai,
  • Wei Lou,
  • Dexing Kong

摘要

While promising in general medical imaging like CT and MRI, large vision-language models (LVLMs) struggle in ultrasonography due to a profound visual-semantic gap and a scarcity of instruction-following data. Translating the inherently noisy and operator-dependent ultrasound images into precise clinical descriptions remains a complex reasoning challenge for general-purpose vision-language models. To bridge this gap, we develop SonoInstruct, a large-scale multi-source dataset curated from over 30 ultrasound sources, providing 110k+ images and 260k+ instruction-following instances. For comprehensive evaluation, we establish SonoBench, a multi-dimensional benchmark suite that assesses eight core capabilities, including performance in out-of-distribution (OOD) scenarios. To verify the effectiveness of our dataset, we fine-tuned Qwen3-VL-2B-Instruct on SonoInstruct, yielding Qwen3-VL-2B-Sono, which achieves a 30.3% relative improvement over the base model on the SonoBench benchmark. These results demonstrate that SonoInstruct effectively bridges the gap between noisy sonographic images and clinical reasoning, establishing a robust foundation for AI-driven ultrasound applications.