A Multimodal Multi-Agent Framework for Radiology Report Generation
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:DFD2IR3Drecord.jsonopen to challenge →
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction
MedGuards introduces a multi-agent in-context learning framework for medical error detection and correction plus the KPCS metric, reporting improvements on four multilingual clinical note datasets.
-
Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation
MARL-Rad trains region-specific and global agents with reinforcement learning on clinical rewards to produce more accurate radiology reports than prior methods on MIMIC-CXR and IU X-ray datasets.
-
MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction
MedGuards proposes a multi-agent system for medical error detection and correction plus the KPCS metric, reporting gains on four multilingual clinical-note datasets.
-
MARCH: Multi-Agent Radiology Clinical Hierarchy for CT Report Generation
MARCH is a multi-agent system mimicking radiology department hierarchy that generates more clinically accurate and linguistically correct CT reports than prior single-model approaches.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.