Exploring the Potential of Retrieval Augmented Generation for Question Answering in Radiology: Initial Findings and Future Directions
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti250482 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Yongli Mou und 4 weiteren Autor:innen. Beteiligte Einrichtung: Chair of Computer Science 5, RWTH Aachen University, Germany. Hauptthemen laut MEDLINE: Radiology Information Systems, Information Storage and Retrieval, Radiology. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
This study explores the application of Retrieval-Augmented Generation (RAG) for question answering in radiology, an area where intelligent systems can significantly impact clinical decision-making. A preliminary experiment tested a naive RAG setup on nice radiology-specific questions with a textbook as the reference source, showing moderate improvements over baseline methods. The paper discusses lessons learned and potential enhancements for RAG in handling radiology knowledge, suggesting pathways for future research in integrating intelligent health systems in medical practice.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Chair of Computer Science 5, RWTH Aachen University, Germany.
- Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Germany.
Zitieren
APA
Mou, Y., Siepmann, R. M., Truhnn, D., Sowe, S., & Decker, S. (2025). Exploring the Potential of Retrieval Augmented Generation for Question Answering in Radiology: Initial Findings and Future Directions. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250482
Vancouver
Mou Y, Siepmann RM, Truhnn D, Sowe S, Decker S. Exploring the Potential of Retrieval Augmented Generation for Question Answering in Radiology: Initial Findings and Future Directions. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250482
BibTeX
@article{Mou2025,
author = {Mou, Yongli and Siepmann, Robert Malte and Truhnn, Daniel and Sowe, Sulayman and Decker, Stefan},
title = {Exploring the Potential of Retrieval Augmented Generation for Question Answering in Radiology: Initial Findings and Future Directions},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti250482}
}
EUVIMED