Large Language Models in the Radiology Workflow: Current Applications, Challenges, and Future Perspectives.
Abstract
Large language models (LLMs) have attracted increasing research interest in radiology owing to their capacity for natural language processing and, more recently, multimodal image-text reasoning. This review provides a clinically oriented overview of LLM applications across the radiology workflow, encompassing scan protocols, image interpretation, radiology reporting, and communication with patients and clinicians. Although the existing general-purpose multimodal LLMs show promise in diagnostic tasks, their image-interpretation performance is limited; they often prioritize textual context over visual information, and they are prone to hallucinations. In contrast, LLMs have demonstrated practical utility in radiology reporting, including structured radiology reporting, summarization, automated data extraction, and clinically meaningful report categorization. This review also discusses the reporting guidelines and performance evaluation methodologies specific to LLM research to promote more scientifically rigorous and reproducible studies in this rapidly evolving field. Finally, we outline the future directions for LLM research to support the responsible and effective integration of LLMs in radiology practice.
Related
- Artificial Intelligence in Emergency Radiology: Current Applications, Challenges, and Future Directions.
- Advances in Smart Hydrogels for Myocardial Infarction Therapy: A Scoping Review of Applications, Challenges, and Future Perspectives.
- A Systems Approach toward AI-Enabled Radiology Dictation for Workflow Efficiency in India.
- Sycophancy in Large Language Models in Oral and Maxillofacial Radiology: The Impact of Misleading Context on Image- and Text-Based Diagnostic Scenarios
- Knowledge distillation-based lightweight generative large language models for standardized quality control of Chinese radiology reports
BibTeX
@article{suh2026large,
title = {{Large Language Models in the Radiology Workflow: Current Applications, Challenges, and Future Perspectives.}},
author = {Pae Sun Suh and Woo Hyun Shim and Hwon Heo and Chong Hyun Suh},
journal = {Journal of the Korean Society of Radiology},
year = {2026},
month = sep,
doi = {10.3348/jksr.2026.0080},
url = {https://europepmc.org/article/MED/42903037},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - Large Language Models in the Radiology Workflow: Current Applications, Challenges, and Future Perspectives.
AU - Pae Sun Suh
AU - Woo Hyun Shim
AU - Hwon Heo
AU - Chong Hyun Suh
PY - 2026
DA - 2026/09/29
JO - Journal of the Korean Society of Radiology
DO - 10.3348/jksr.2026.0080
UR - https://europepmc.org/article/MED/42903037
AB - Large language models (LLMs) have attracted increasing research interest in radiology owing to their capacity for natural language processing and, more recently, multimodal image-text reasoning. This review provides a clinically oriented overview of LLM applications across the radiology workflow, encompassing scan protocols, image interpretation, radiology reporting, and communication with patients and clinicians. Although the existing general-purpose multimodal LLMs show promise in diagnostic tasks, their image-interpretation performance is limited; they often prioritize textual context over visual information, and they are prone to hallucinations. In contrast, LLMs have demonstrated practical utility in radiology reporting, including structured radiology reporting, summarization, automated data extraction, and clinically meaningful report categorization. This review also discusses the reporting guidelines and performance evaluation methodologies specific to LLM research to promote more scientifically rigorous and reproducible studies in this rapidly evolving field. Finally, we outline the future directions for LLM research to support the responsible and effective integration of LLMs in radiology practice.
SN - 2951-0805
ER -