A Large Language Model Framework for Seed Implant Brachytherapy: Adaptive Weight Optimization via Retrieval‐Augmented Generation
Annals of the New York Academy of Sciences · 2026-11 · 1565 (1)
DOI: 10.1111/nyas.70448 ↗Kurz gefasst
Fachartikel in der Zeitschrift Annals of the New York Academy of Sciences, online erschienen am 30.10.2026. Verfasst von Zhuo Xiao und 9 weiteren Autor:innen. Beteiligte Einrichtung: Image Processing Center, Beihang University, Beijing, People's Republic of China. Hauptthemen laut MEDLINE: Brachytherapy, Radiotherapy Planning, Computer-Assisted. Die Arbeit nennt 54 Literaturangaben. Gefördert von: Beijing Natural Science Foundation, Guangdong Science and Technology Programme, National Natural Science Foundation of China.
Abstract (Originalsprache)
Seed implant brachytherapy (SIBT) is an effective cancer treatment modality; however, clinical planning often relies on manual adjustment of objective function weights, leading to inefficiencies and suboptimal results. This study proposes an adaptive weight optimization framework for SIBT planning, driven by large language models (LLMs). A locally deployed DeepSeek‐R1 LLM is integrated with an automatic planning algorithm in an iterative loop. Starting with fixed weights, the LLM evaluates plan quality and recommends new weights in the next iteration. This process continues until convergence criteria are met, after which the LLM conducts a comprehensive evaluation to identify the optimal plan. A clinical knowledge base, constructed and queried via retrieval‐augmented generation (RAG), enhances the model's domain‐specific reasoning. The proposed method was retrospectively validated on 23 patient cases who underwent head‐and‐neck SIBT, showing that the LLM‐assisted approach maintained clinical target volume (CTV) coverage and reduced excessive target dose relative to fixed‐weight planning; in the eight patients with available organs at risk (OARs) contours, OAR dose metrics showed favorable numerical trends. The study demonstrates the potential of LLMs as assistive tools for SIBT planning under clinician supervision.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Image Processing Center, Beihang University, Beijing, People's Republic of China.
- State Key Laboratory of High-Efficiency Reusable Aerospace Transportation Technology, Beijing, People's Republic of China.
- Department of Radiation Oncology, Peking University Third Hospital, Beijing, People's Republic of China.
- Department of Radiation Oncology, Duke University Medical Center, Durham, North Carolina, USA.
Förderung
- Beijing Natural Science Foundation
- Guangdong Science and Technology Programme
- National Natural Science Foundation of China
- Natural Science Foundation of Beijing Municipality
Zitieren
APA
Xiao, Z., Yao, Q., Wang, J., Liu, B., Zhou, F., Sun, H., Ji, Z., Jiang, Y., Wang, J., & Wu, Q. (2026). A Large Language Model Framework for Seed Implant Brachytherapy: Adaptive Weight Optimization via Retrieval‐Augmented Generation. Annals of the New York Academy of Sciences, 1565(1). https://doi.org/10.1111/nyas.70448
Vancouver
Xiao Z, Yao Q, Wang J, Liu B, Zhou F, Sun H, et al. A Large Language Model Framework for Seed Implant Brachytherapy: Adaptive Weight Optimization via Retrieval‐Augmented Generation. Annals of the New York Academy of Sciences. 2026;1565(1). doi:10.1111/nyas.70448
BibTeX
@article{Xiao2026,
author = {Xiao, Zhuo and Yao, Qinglong and Wang, Jingjing and Liu, Bo and Zhou, Fugen and Sun, Haitao and Ji, Zhe and Jiang, Yuliang and Wang, Junjie and Wu, Qiuwen},
title = {A Large Language Model Framework for Seed Implant Brachytherapy: Adaptive Weight Optimization via Retrieval‐Augmented Generation},
journal = {Annals of the New York Academy of Sciences},
year = {2026},
volume = {1565},
number = {1},
doi = {10.1111/nyas.70448}
}
EUVIMED