A Multimodal Multi-Agent Framework for Radiology Report Generation
This work addresses the problem of improving radiology report generation for clinical applications, though it appears incremental as it builds on existing multimodal and retrieval-augmented methods.
The paper tackles the problem of generating radiology reports from medical images by addressing challenges like factual inconsistency and hallucination, proposing a multimodal multi-agent framework aligned with clinical reasoning workflows, and reports that it outperforms a strong baseline in automatic metrics and LLM-based evaluations, producing more accurate and structured reports.
Radiology report generation (RRG) aims to automatically produce diagnostic reports from medical images, with the potential to enhance clinical workflows and reduce radiologists' workload. While recent approaches leveraging multimodal large language models (MLLMs) and retrieval-augmented generation (RAG) have achieved strong results, they continue to face challenges such as factual inconsistency, hallucination, and cross-modal misalignment. We propose a multimodal multi-agent framework for RRG that aligns with the stepwise clinical reasoning workflow, where task-specific agents handle retrieval, draft generation, visual analysis, refinement, and synthesis. Experimental results demonstrate that our approach outperforms a strong baseline in both automatic metrics and LLM-based evaluations, producing more accurate, structured, and interpretable reports. This work highlights the potential of clinically aligned multi-agent frameworks to support explainable and trustworthy clinical AI applications.