EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RTPhy‐ChatBot: A RAG‐Based intelligent assistant for radiotherapy physics using LLaMA3 and AAPM reports

Shuoyang Wei iD, Ankang Hu, Zhiqun Wang iD, Xiangyin Meng iD, Lang Yu, Bo Yang, Jie Qiu

Journal of Applied Clinical Medical Physics · 2025

DOI: 10.1002/acm2.70263 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Clinical Medical Physics, 2025. Verfasst von Shuoyang Wei und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Peking Union Medical College Hospital, Beijing, China. Hauptthemen laut MEDLINE: Radiotherapy Planning, Computer-Assisted, Health Physics, Knowledge Bases, Neoplasms. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, Ministry of Science and Technology of the People's Republic of China, National High Level Hospital Clinical Research Funding.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Medical physics plays a crucial role in radiotherapy, with ongoing technological advancements aimed at improving treatment outcomes. However, the rapid pace of innovation presents challenges for medical physicists, who must continuously acquire and integrate complex information for effective decision‐making and communication.

Purpose

To support efficient knowledge acquisition, we developed RTPhy‐ChatBot, an intelligent assistant tailored to radiotherapy physics. The objective was to create a reliable and precise tool to assist medical physicists in their daily work.

Methods

The knowledge base for RTPhy‐ChatBot was constructed from publications by the American Association of Physicists in Medicine (AAPM), which were converted into markdown format, segmented, and embedded using the bge‐base‐en‐v1.5 model. RTPhy‐ChatBot employed the Meta‐LLaMA3‐8B‐Instruct model for response generation. We compared its performance with several commercial large language models (LLMs) across 20 template questions and evaluated the impact of zero‐shot chain‐of‐thought (CoT) reasoning. In addition to expert scoring by senior medical physicists, we conducted Rouge score analysis against synthesized reference answers.

Results

RTPhy‐ChatBot demonstrated strong performance in answering radiotherapy physics questions. Across 20 questions, it achieved an average score of 4.0 ± 0.9, compared to 3.9 ± 1.1 for Gemini‐2.0‐Flash, 4.0 ± 1.4 for GPT‐4o, and 3.8 ± 1.2 for Moonshot‐v1. It excelled in questions involving specific quality assurance standards. Rouge analysis yielded scores of 0.5127 (Rouge‐1), 0.2119 (Rouge‐2), and 0.2748 (Rouge‐L), closely matching commercial LLMs.

Conclusions

RTPhy‐ChatBot proved to be an effective intelligent assistant for radiotherapy physics, delivering accurate, referenced responses grounded in AAPM publications. Despite lacking online access, it matched or exceeded the performance of commercial LLMs in domain‐specific tasks. This pilot study highlights the potential of domain‐specific assistants in supporting clinical workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Radiotherapy Planning, Computer-AssistedHealth PhysicsKnowledge BasesNeoplasmsRadiotherapySoftwareHumansRadiotherapy DosageGenerative Artificial Intelligence

Stichwörter der Autor:innen

large language modelradiotherapy physicsretrieval‐augmented generation

Autor:innen und Institutionen

  • Department of Radiation Oncology, Peking Union Medical College Hospital, Beijing, China.
  • Department of Engineering Physics, Tsinghua University, Beijing, China.
  • Key Laboratory of Particle & Radiation Imaging (Tsinghua University), Ministry of Education, Beijing, China.

ORCID-Profile: Shuoyang Wei, Zhiqun Wang, Xiangyin Meng

Förderung

  • National Key R&D Program of China, Ministry of Science and Technology of the People's Republic of China
  • National High Level Hospital Clinical Research Funding

Zitieren

APA

Wei, S., Hu, A., Wang, Z., Meng, X., Yu, L., Yang, B., & Qiu, J. (2025). RTPhy‐ChatBot: A RAG‐Based intelligent assistant for radiotherapy physics using LLaMA3 and AAPM reports. Journal of Applied Clinical Medical Physics. https://doi.org/10.1002/acm2.70263

Vancouver

Wei S, Hu A, Wang Z, Meng X, Yu L, Yang B, et al. RTPhy‐ChatBot: A RAG‐Based intelligent assistant for radiotherapy physics using LLaMA3 and AAPM reports. Journal of Applied Clinical Medical Physics. 2025. doi:10.1002/acm2.70263

BibTeX
@article{Wei2025,
  author = {Wei, Shuoyang and Hu, Ankang and Wang, Zhiqun and Meng, Xiangyin and Yu, Lang and Yang, Bo and Qiu, Jie},
  title = {RTPhy‐ChatBot: A RAG‐Based intelligent assistant for radiotherapy physics using LLaMA3 and AAPM reports},
  journal = {Journal of Applied Clinical Medical Physics},
  year = {2025},
  doi = {10.1002/acm2.70263}
}
Kostenlos starten →