Agentic AI and Large Language Models in Radiology: Opportunities and Hallucination Challenges
Bioengineering · 26.11.2025 · 12 (12) · 1303
DOI: 10.3390/bioengineering12121303 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Bioengineering, online erschienen am 26.11.2025. Verfasst von Sara Salehi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Radiology Informatics Lab, Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Mayo Clinic Department of Radiology.
Abstract (Originalsprache)
The field of radiology is experiencing rapid adoption of large language models (LLMs), yet their tendency to generate hallucinations (plausible but incorrect information) remains a significant barrier to trust. This comprehensive review evaluates emerging agentic artificial intelligence (AI) approaches, including multi-agent role-based systems, retrieval-augmented generation (RAG), and uncertainty quantification, to assess their potential for reducing hallucinations in radiology workflows. Evidence from 2024 to 2025 demonstrates that agentic AI can improve diagnostic accuracy and reduce error rates, though these methods remain computationally demanding and lack comprehensive clinical validation. Multi-agent frameworks enable cross-validation through role-based specialization and systematic workflow orchestration, while RAG strategies enhance accuracy by grounding responses in verified medical literature. Within multi-agent systems, uncertainty quantification enables agents to communicate confidence levels to one another, allowing them to appropriately weigh each other’s contributions during collaborative analysis. While multi-agent frameworks and RAG strategies show significant promise, practical deployment will require careful integration with human oversight, robust evaluation metrics tailored to medical imaging tasks, and regulatory adaptation to ensure safe clinical use in diverse patient populations and imaging modalities.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Radiology Informatics Lab, Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA.
- Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA.
- Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA.
ORCID-Profile: Sara Salehi, Yashbir Singh, Kelly K Horst, Quincy A Hathaway, Bradley J Erickson
Förderung
- Mayo Clinic Department of Radiology
Zitieren
APA
Salehi, S., Singh, Y., Horst, K. K., Hathaway, Q. A., & Erickson, B. J. (2025). Agentic AI and Large Language Models in Radiology: Opportunities and Hallucination Challenges. Bioengineering, 12(12), 1303. https://doi.org/10.3390/bioengineering12121303
Vancouver
Salehi S, Singh Y, Horst KK, Hathaway QA, Erickson BJ. Agentic AI and Large Language Models in Radiology: Opportunities and Hallucination Challenges. Bioengineering. 2025;12(12):1303. doi:10.3390/bioengineering12121303
BibTeX
@article{Salehi2025,
author = {Salehi, Sara and Singh, Yashbir and Horst, Kelly K and Hathaway, Quincy A and Erickson, Bradley J},
title = {Agentic AI and Large Language Models in Radiology: Opportunities and Hallucination Challenges},
journal = {Bioengineering},
year = {2025},
volume = {12},
number = {12},
pages = {1303},
doi = {10.3390/bioengineering12121303}
}
EUVIMED