arXiv cs.CL· Haris Ghafoor, Minjee Seo, Seonaeng cho, Keungmo Yang, Jaejun Lee, Kyungho Yoon·· 11 小时前AI 评分31
SMILE：面向肝脏超声理解的结构化多智能体临床推理框架
SMILE: A Structured Multi-Agent Clinical Reasoning for Liver Ultrasound Understanding
AI 导读
SMILE 是一个结构化多智能体临床推理框架，用图像解读、临床分期推理和 VQA 三个专家智能体分别解读肝脏超声图像，再由 judge VLM 以共识过滤提示词汇总为统一输出。在公开肝脏超声数据集和内部临床数据集上，SMILE 的 ROUGE-1 最高提升 19.0%、临床 F1 提升 18.8%，VQA F1 分别达 0.82 和 0.65。模型、数据集与代码已公开。
正文 · 原文
Abstract:Automated liver ultrasound report generation improves the diagnosis of liver diseases by producing clinically structured descriptions of anatomical and disease-related findings. However, current generative vision-language models (VLMs) often rely on a single reasoning pathway that maps ultrasound appearance directly to textual descriptions. In addition to the inherent vision-language modality gap, this design is limited for liver ultrasound because disease interpretation is constrained by subtle visual evidence, heterogeneous disease patterns, and limited paired supervision. To address these limitations, we propose SMILE, a Structured Multi-agent clInicaL rEasoning framework that uses multiple complementary specialist agents to interpret ultrasound images and consolidates their outputs through a judge-guided consensus mechanism. Our approach employs three specialized agents: an image interpretation agent for morphological descriptions, a clinical-stage reasoning agent, and a visual question answering (VQA) agent for targeted queries. These agent responses are then aggregated and scrutinized by a judge VLM using a consensus filtering prompt to produce a unified, clinically coherent output. Across a public liver ultrasound dataset and an internal clinical dataset, SMILE consistently outperforms state-of-the-art VLMs, achieving up to 19.0\% improvement in ROUGE-1 and 18.8\% improvement in clinical F1-score, while reaching VQA F1-scores of 0.82 and 0.65 on public and internal datasets, respectively. These results demonstrate the potential of SMILE for data-scarce and limited-supervision clinical settings. Our models, datasets, and code are available \href{this https URL}{here}.
| Comments: | Accepted at Winter Conference on Applications of Computer Vision (WACV) 2027 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.02581 [cs.CV] |
| (or arXiv:2611.02581v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.02581 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haris Ghafoor [view email]
[v1]
Mon, 2 Nov 2026 06:05:38 UTC (1,900 KB)
来源：arXiv cs.CL · arxiv.org