CBM-RAG: Demonstrating Enhanced Interpretability in Radiology Report Generation with Multi-Agent RAG and Concept Bottleneck Models
This work addresses interpretability and reliability challenges for clinical adoption in radiology, though it appears incremental as it builds on existing CBMs and RAG methods.
The paper tackled the problem of low interpretability and reliability in automated radiology report generation by combining Concept Bottleneck Models with a Multi-Agent RAG system, resulting in a framework that delivers interpretable predictions, mitigates hallucinations, and generates high-quality reports.
Advancements in generative Artificial Intelligence (AI) hold great promise for automating radiology workflows, yet challenges in interpretability and reliability hinder clinical adoption. This paper presents an automated radiology report generation framework that combines Concept Bottleneck Models (CBMs) with a Multi-Agent Retrieval-Augmented Generation (RAG) system to bridge AI performance with clinical explainability. CBMs map chest X-ray features to human-understandable clinical concepts, enabling transparent disease classification. Meanwhile, the RAG system integrates multi-agent collaboration and external knowledge to produce contextually rich, evidence-based reports. Our demonstration showcases the system's ability to deliver interpretable predictions, mitigate hallucinations, and generate high-quality, tailored reports with an interactive interface addressing accuracy, trust, and usability challenges. This framework provides a pathway to improving diagnostic consistency and empowering radiologists with actionable insights.