Concept-Enhanced Multimodal RAG: Towards Interpretable and Accurate Radiology Report Generation

TL;DR

This paper introduces CEMRAG, a unified framework that enhances interpretability and accuracy in radiology report generation by decomposing visual data into clinical concepts and integrating them with retrieval-augmented generation, showing improved clinical and NLP metrics.

Contribution

The paper proposes a novel concept-enhanced multimodal RAG framework that unifies interpretability and factual accuracy in radiology report generation, outperforming existing methods.

Findings

Consistent improvements in clinical accuracy metrics.

Enhanced interpretability through visual concept decomposition.

Challenging the trade-off between interpretability and performance.

Abstract

Radiology Report Generation (RRG) through Vision-Language Models (VLMs) promises to reduce documentation burden, improve reporting consistency, and accelerate clinical workflows. However, their clinical adoption remains limited by the lack of interpretability and the tendency to hallucinate findings misaligned with imaging evidence. Existing research typically treats interpretability and accuracy as separate objectives, with concept-based explainability techniques focusing primarily on transparency, while Retrieval-Augmented Generation (RAG) methods targeting factual grounding through external retrieval. We present Concept-Enhanced Multimodal RAG (CEMRAG), a unified framework that decomposes visual representations into interpretable clinical concepts and integrates them with multimodal RAG. This approach exploits enriched contextual prompts for RRG, improving both interpretability and factual accuracy. Experiments on MIMIC-CXR and IU X-Ray across multiple VLM architectures, training regimes, and retrieval configurations demonstrate consistent improvements over both conventional RAG and concept-only baselines on clinical accuracy metrics and standard NLP measures. These results challenge the assumed trade-off between interpretability and performance, showing that transparent visual concepts can enhance rather than compromise diagnostic accuracy in medical VLMs. Our modular design decomposes interpretability into visual transparency and structured language model conditioning, providing a principled pathway toward clinically trustworthy AI-assisted radiology.