Deep learning methods face dual challenges of limited clinical samples and low inter-class differentiation among Diffuse Cystic Lung Diseases (DCLDs) in advancing Birt-Hogg-Dube syndrome (BHD) diagnosis via Computed Tomography (CT) imaging. While Multimodal Large Language Models (MLLMs) demonstrate diagnostic potential fo such rare diseases, the absence of domain-specific knowledge and referable radiological features intensify hallucination risks. To address this problem, we propose BHD-RAG, a multimodal retrieval-augmented generation framework that integrates DCLD-specific expertise and clinical precedents with MLLMs to improve BHD diagnostic accuracy. BHDRAG employs: (1) a specialized agent generating imaging manifestation descriptions of CT images to construct a multimodal corpus of DCLDs cases. (2) a cosine similarity-based retriever pinpointing relevant imagedescription pairs for query images, and (3) an MLLM synthesizing retrieved evidence with imaging data for diagnosis. BHD-RAG is validated on the dataset involving four types of DCLDs, achieving superior accuracy and generating evidence-based descriptions closely aligned with expert insights.
@article{arxiv.2511.19834,
title = {Large Language Model Aided Birt-Hogg-Dube Syndrome Diagnosis with Multimodal Retrieval-Augmented Generation},
author = {Haoqing Li and Jun Shi and Xianmeng Chen and Qiwei Jia and Rui Wang and Wei Wei and Hong An and Xiaowen Hu},
journal= {arXiv preprint arXiv:2511.19834},
year = {2025}
}