Multiple expert agents improve liver ultrasound report accuracy
SMILE: A Structured Multi-Agent Clinical Reasoning for Liver Ultrasound Understanding
Computer Vision and Pattern RecognitionComputation and LanguageMachine Learning
Summary
Interpreting liver ultrasound images is hard because the signs of disease can be small and varied. The authors propose a new system called SMILE that uses several expert 'agents', each specialized in a different reasoning task, to analyze the images. These agents then combine their insights through a final judge to produce accurate and unified medical reports. Tests show SMILE does better than current single-path models on liver ultrasound datasets, especially when training data is limited.
What this means in practice
- •For clinical informed decision teams: Generate detailed, structured liver ultrasound reports automatically to assist diagnosis in resource-constrained settings with limited labeled data.
- •For medical imaging software developers: Incorporate multi-agent reasoning models into ultrasound software to improve interpretation accuracy and produce clinically coherent text summaries.
Authors
Haris Ghafoor, Minjee Seo, Seonaeng cho, Keungmo Yang, Jaejun Lee, Kyungho Yoon
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{https://github.com/CMME-Lab/SMILE}{here}.