RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering

Overview

• This is the official repository of the paper RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering.

• Preprint version: URL.

Main Python modules required for the software can be installed from ./requirements:

$ conda env create -f requirements.yaml
$ conda activate radiorag

Note: This might take a few minutes.

---

In case you use this repository, please cite the original paper:

S. Tayebi Arasteh, M. Lotfinia, K. Bressem, R. Siepmann, L. Adams, D. Ferber, C. Kuhl, J.N. Kather, S. Nebelung, D. Truhn. "RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering." Radiology: Artificial Intelligence, (2025), 7(4):e240476. DOI: https://doi.org/10.1148/ryai.240476

BibTex

@article {radiorag25,
author = {Tayebi Arasteh, Soroosh and Lotfinia, Mahshad, and Bressem, Keno and Siepmann, Robert and Adams, Lisa and Ferber, Dyke and Kuhl, Christiane and Kather, Jakob Nikolas and Nebelung, Sven and Truhn, Daniel},
title = {RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering},
year = {2025},
pages = {e240476},
volume = {7},
issue = {4},
doi = {https://doi.org/10.1148/ryai.240476},
journal = {Radiology: Artificial Intelligence}
}