RADAR: Enhancing Radiology Report Generation with Supplementary Knowledge Injection
This work addresses inefficiencies in radiology report generation for medical AI applications, though it is incremental as it builds on existing multimodal LLM approaches.
The paper tackles the problem of redundant information integration in radiology report generation by proposing RADAR, a framework that leverages both internal LLM knowledge and external retrieval to enhance reports, achieving state-of-the-art performance on datasets like MIMIC-CXR with improvements in language quality and clinical accuracy.
Large language models (LLMs) have demonstrated remarkable capabilities in various domains, including radiology report generation. Previous approaches have attempted to utilize multimodal LLMs for this task, enhancing their performance through the integration of domain-specific knowledge retrieval. However, these approaches often overlook the knowledge already embedded within the LLMs, leading to redundant information integration. To address this limitation, we propose Radar, a framework for enhancing radiology report generation with supplementary knowledge injection. Radar improves report generation by systematically leveraging both the internal knowledge of an LLM and externally retrieved information. Specifically, it first extracts the model's acquired knowledge that aligns with expert image-based classification outputs. It then retrieves relevant supplementary knowledge to further enrich this information. Finally, by aggregating both sources, Radar generates more accurate and informative radiology reports. Extensive experiments on MIMIC-CXR, CheXpert-Plus, and IU X-ray demonstrate that our model outperforms state-of-the-art LLMs in both language quality and clinical accuracy.