Retrieval-Augmented Generation with Large Language Models in Radiology: From Theory to Practice

2025/06/04 by Anna Maria Fink, Alexander Rau, Marco Reisert +2 · 1 voice
Computer Science · Medicine · #Topic Modeling #Artificial Intelligence in Healthcare and Education #Radiomics and Machine Learning in Medical Imaging

paper · doi:10.1148/ryai.240790

openalex publication_date 2025/06/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/25

Abstract

Retrieval-augmented generation (RAG) integrates task-specific expert knowledge into large language model (LLM) queries, offering potential to improve diagnostic accuracy, transparency, and decision support. This approach enables LLMs to function as complementary tools for radiologists, helping optimize patient care and meet growing health care demands.

Citations

• Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models

Discussions

• Retrieval-augmented generation offers potential to improve diagnostic accuracy, transparency & decision support https://doi.org/10.1148/ryai.240790 @uni-freiburg.de #LargeLanguageModel #ML #MachineLea [bsky, 5 points, 0 comments]

Related

• Enhancing Large Language Models with Retrieval-Augmented Generation: A Radiology-Specific Approach
• RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering
• Development and Testing of Retrieval Augmented Generation in Large Language Models -- A Case Study Report
• Best Practices for Large Language Models in Radiology
• Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations