EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Empowering PET imaging reporting with retrieval-augmented large language models and reading reports database: a pilot single center study

Hongyoon Choi iD, Dongjoo Lee, Yeon-Koo Kang, Minseok Suh

European Journal of Nuclear Medicine and Molecular Imaging · 2025

DOI: 10.1007/s00259-025-07101-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Nuclear Medicine and Molecular Imaging, 2025. Verfasst von Hongyoon Choi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Nuclear Medicine, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea. chy1000@snu.ac.kr. Hauptthemen laut MEDLINE: Positron-Emission Tomography, Natural Language Processing, Databases, Factual, Information Storage and Retrieval. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Seoul National University Hospital.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

The potential of Large Language Models (LLMs) in enhancing a variety of natural language tasks in clinical fields includes medical imaging reporting. This pilot study examines the efficacy of a retrieval-augmented generation (RAG) LLM system considering zero-shot learning capability of LLMs, integrated with a comprehensive database of PET reading reports, in improving reference to prior reports and decision making.

Methods

We developed a custom LLM framework with retrieval capabilities, leveraging a database of over 10 years of PET imaging reports from a single center. The system uses vector space embedding to facilitate similarity-based retrieval. Queries prompt the system to generate context-based answers and identify similar cases or differential diagnoses. From routine clinical PET readings, experienced nuclear medicine physicians evaluated the performance of system in terms of the relevance of queried similar cases and the appropriateness score of suggested potential diagnoses.

Results

The system efficiently organized embedded vectors from PET reports, showing that imaging reports were accurately clustered within the embedded vector space according to the diagnosis or PET study type. Based on this system, a proof-of-concept chatbot was developed and showed the framework’s potential in referencing reports of previous similar cases and identifying exemplary cases for various purposes. From routine clinical PET readings, 84.1% of the cases retrieved relevant similar cases, as agreed upon by all three readers. Using the RAG system, the appropriateness score of the suggested potential diagnoses was significantly better than that of the LLM without RAG. Additionally, it demonstrated the capability to offer differential diagnoses, leveraging the vast database to enhance the completeness and precision of generated reports.

Conclusion

The integration of RAG LLM with a large database of PET imaging reports suggests the potential to support clinical practice of nuclear medicine imaging reading by various tasks of AI including finding similar cases and deriving potential diagnoses from them. This study underscores the potential of advanced AI tools in transforming medical imaging reporting practices.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Positron-Emission TomographyNatural Language ProcessingDatabases, FactualInformation Storage and RetrievalPilot ProjectsHumansLarge Language Models

Stichwörter der Autor:innen

Artificial intelligenceLarge language modelPET reportsRetrieval-augmented generation

Autor:innen und Institutionen

  • Department of Nuclear Medicine, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea. chy1000@snu.ac.kr.
  • Department of Nuclear Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea. chy1000@snu.ac.kr.
  • Portrai, Inc., Seoul, Republic of Korea. chy1000@snu.ac.kr.
  • Portrai, Inc., Seoul, Republic of Korea.
  • Department of Nuclear Medicine, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea.
  • Department of Nuclear Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea.

ORCID-Profile: Hongyoon Choi

Förderung

  • Seoul National University Hospital

Zitieren

APA

Choi, H., Lee, D., Kang, Y. K., & Suh, M. (2025). Empowering PET imaging reporting with retrieval-augmented large language models and reading reports database: a pilot single center study. European Journal of Nuclear Medicine and Molecular Imaging. https://doi.org/10.1007/s00259-025-07101-9

Vancouver

Choi H, Lee D, Kang YK, Suh M. Empowering PET imaging reporting with retrieval-augmented large language models and reading reports database: a pilot single center study. European Journal of Nuclear Medicine and Molecular Imaging. 2025. doi:10.1007/s00259-025-07101-9

BibTeX
@article{Choi2025,
  author = {Choi, Hongyoon and Lee, Dongjoo and Kang, Yeon-Koo and Suh, Minseok},
  title = {Empowering PET imaging reporting with retrieval-augmented large language models and reading reports database: a pilot single center study},
  journal = {European Journal of Nuclear Medicine and Molecular Imaging},
  year = {2025},
  doi = {10.1007/s00259-025-07101-9}
}
Kostenlos starten →