English

Towards Interpretable Radiology Report Generation via Concept Bottlenecks using a Multi-Agentic RAG

Information Retrieval 2025-04-30 v2 Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Image and Video Processing

Abstract

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 is available at https://github.com/tifat58/IRR-with-CBM-RAG.git.

Keywords

Cite

@article{arxiv.2412.16086,
  title  = {Towards Interpretable Radiology Report Generation via Concept Bottlenecks using a Multi-Agentic RAG},
  author = {Hasan Md Tusfiqur Alam and Devansh Srivastav and Md Abdul Kadir and Daniel Sonntag},
  journal= {arXiv preprint arXiv:2412.16086},
  year   = {2025}
}

Comments

Accepted in the 47th European Conference for Information Retrieval (ECIR) 2025

R2 v1 2026-06-28T20:44:06.948Z