Publikation
Towards Interpretable Radiology Report Generation via Concept Bottlenecks Using a Multi-agentic RAG
Hasan Md Tusfiqur Alam; Devansh Srivastav; Md Abdul Kadir; Daniel Sonntag
In: Claudia Hauff; Craig Macdonald; Dietmar Jannach; Gabriella Kazai; Franco Maria Nardini; Fabio Pinelli; Fabrizio Silvestri; Nicola Tonellotto (Hrsg.). Advances in Information Retrieval - 47th European Conference on Information Retrieval, ECIR 2025, Lucca, Italy, April 6-10, 2025, Proceedings, Part III. European Conference on Information Retrieval (ECIR-2025), 47th European Conference on Information Retrieval, located at ECIR 2025, April 6-10, Lucca, Italy, Pages 201-209, Lecture Notes in Computer Science, Vol. 15574, Springer, 4/2025.
Zusammenfassung
Deep learning has advanced medical image classification, but interpretability challenges hinder its clinical adoption. This study enhances interpretability in Chest X-ray (CXR) classification by using concept bottleneck models (CBMs) and a multi-agent Retrieval-Augmented Generation (RAG) system for report generation. By modeling relationships between visual features and clinical concepts, we create interpretable concept vectors that guide a multi-agent RAG system to generate radiology reports, enhancing clinical relevance, explainability, and transparency. Evaluation of the generated reports using an LLM-as-a-judge confirmed the interpretability and clinical utility of our model’s outputs. On the COVID-QU dataset, our model achieved 81% classification accuracy and demonstrated robust report generation performance, with five key metrics ranging between 84% and 90%. This interpretable multi-agent framework bridges the gap between high-performance AI and the explainability required for reliable AI-driven CXR analysis in clinical settings. Our code will be released at https://github.com/tifat58/IRR-with-CBM-RAG